04th week of 2020 patent applcation highlights part 47 |
Patent application number | Title | Published |
20200026908 | NAME AND FACE MATCHING - Described are methods, systems, and computer-program product embodiments for selecting a face image based on a name. In some embodiments, a method includes receiving the name. Based on the name, a name vector is selected from a plurality of name vectors in a dataset that maps a plurality of names to a plurality of corresponding name vectors in a vector space, where each name vector includes representations associated with a plurality of words associated with each name. A plurality of face vectors corresponding to a plurality of face images is received. A face vector is selected from the plurality of face vectors based on a plurality of similarity scores calculated for the plurality of corresponding face vectors, where for each name vector, a similarity score is calculated based on the name vector and each face vector. The face image is output based on the selected face vector. | 2020-01-23 |
20200026909 | Computer Systems and Computer-Implemented Methods of Use Thereof Configured to Recognize User Activity During User Interaction with Electronic Computing Devices - A computer-implemented method and system that entails a continuous tracking of a plurality of representations over a predetermined time duration. The method and system also entails a continuous application of at least one eye-gaze movement tracking (EGMT) algorithm to the visual input to form a time series of eye-gaze vectors and a continuous continuously input of the time series of eye-gaze vectors into an Activity Tracking Neural Network (ATNN). The ATNN classifies at least one activity of the at least one user over the predetermined time duration and outputs a measure of the at least one user's engagement with the classified activity. | 2020-01-23 |
20200026910 | GESTURE IDENTIFICATION, CONTROL, AND NEURAL NETWORK TRAINING METHODS AND APPARATUSES, AND ELECTRONIC DEVICES - A gesture identification method includes: performing gesture information detection on an image by means of a neural network, to obtain a potential hand region, a potential gesture category and a potential gesture category probability in the image, the potential gesture category including a gesture-free category and at least one gesture category; and if the obtained potential gesture category with the maximum probability is the gesture-free category, not outputting position information of the potential hand region of the image; or otherwise, outputting the position information of the potential hand region of the image and the obtained potential gesture category with the maximum probability. | 2020-01-23 |
20200026911 | 3D Event Sequence Capture and Image Transform Apparatus and Method of Operation - A method for 3D security cameras to selectively capture and transmit images to avoid congestion of a network coupling them to a central server. Skeleton detection circuits perform conditional event capture when triggered. Head, hands, and feet are associated with pixel blocks. Sequences of images provide indicia of remarkable forces, motions, and weapons. Images are transformed to effectively alert a user. Security cameras may be mobile, body-worn, and fixed in location. Location and identity indicia utilize a 3D location model. | 2020-01-23 |
20200026912 | INFORMATION PROCESSING APPARATUS AND NON-TRANSITORY COMPUTER READABLE MEDIUM STORING PROGRAM - An information processing apparatus includes a storage unit that previously stores a classification rule corresponding to an attribute of an applicant, an acquisition unit that acquires content of an electronic document from an image of the document, and a setting unit that reads the classification rule corresponding to the attribute of the applicant of the document from the storage unit, and sets a classification item of the document based on the content of the document, which is acquired by the acquisition unit, and the classification rule which is read from the storage unit. | 2020-01-23 |
20200026913 | BLOCKWISE EXTRACTION OF DOCUMENT METADATA - Methods, computer program products, and systems are presented. The methods include, for instance: obtaining a document image, wherein the document image includes a plurality of objects; identifying a plurality of macroblocks within the document image; performing microblock processing within macroblocks of the plurality of macroblocks, wherein the microblock processing includes examining content of microblocks within a macroblock for extraction of key-value pairs, the examining content including performing an ontological analysis of microblocks, wherein the microblock processing includes associating confidence levels to the extracted key-value pairs; and outputting metadata based on the performing microblock processing within macroblocks of the plurality of macroblocks. | 2020-01-23 |
20200026914 | INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING SYSTEM FOR EXTRACTING INFORMATION ON ELECTRONIC PAYMENT FROM BILL IMAGE - An information processing device includes a display section, a control unit, an operating section, and a communication section. The control unit functions as: an identification information extracting section that extracts, from a bill image, identification information indicating a demander; a type determination section that determines a type of bill associated with the identification information; a region identifying section that identifies, based on a format associated with the type of bill determined by the type determination section, a region of the bill image containing character images related to an electronic payment; a payment information extracting section that extracts characters related to the electronic payment from the region; and a display control section that allows the display section to display the characters related to the electronic payment. When the operating section accepts an instruction to make settlement, the communication section sends to a settlement server the characters related to the electronic payment. | 2020-01-23 |
20200026915 | INFORMATION PROCESSING APPARATUS AND INFORMATION PROCESSING METHOD - An information processing apparatus includes processing circuitry. The circuitry acquires first ledger sheet definition information and second ledger sheet definition information from a memory. The first ledger sheet definition information defines relative positions of an item and a value of the item in a ledger sheet. The second ledger sheet definition information defines relative positions of an item and a value of the item in a ledger sheet unique to a user. Based on at least one of the first ledger sheet definition information and the second ledger sheet definition information, the circuitry extracts an item and a value of the item from reading result information that associates a character string read from a ledger sheet image with information representing a position of the character string, and the circuitry outputs the extracted item and value of the item as a recognition result. | 2020-01-23 |
20200026916 | SYSTEMS AND METHODS FOR PREDICTIVE ANALYSIS REPORTING - Systems and methods may utilize a predictive analysis model to analyze a contract or other document. A system may parse a document and/or a repository of information associated with the document. The system may identify one or more terms in the document and corresponding terms in the repository. The system may determine a difference parameter between a first term extracted from the document and a second term extracted from the repository. The system may determine whether the difference between the first term and the second term, represented by the difference parameter, is likely to be acceptable to the user using a predictive analysis model. The system may report a validation parameter indicating a level of acceptability associated with the difference. User feedback on the accuracy of the predictive analysis model is used to train, modify, and improve the predictive analysis model. | 2020-01-23 |
20200026917 | AUTHENTICATION METHOD, APPARATUS AND SYSTEM - A method, an apparatus and system for authentication are provided. The method includes: acquiring, on reception of an authentication request sent by a terminal, target point information, and sending the target point information to the terminal, so that the terminal displays a position point to be gazed at by a user on a screen base on the target point information; receiving first eye information acquired by the terminal when the user gazes at the position point; and performing identity authentication on the user based on the first eye information and the target point information. With the method, the apparatus, and the system for authentication, identify authentication is performed based on the eye information and the coordinates of the position point, so as to verify the iris, increase the security of payment and confirm the pay willingness of the user. | 2020-01-23 |
20200026918 | LENS SYSTEM FOR HIGH QUALITY VISIBLE IMAGE ACQUISITION AND INFRA-RED IRIS IMAGE ACQUISITION - This disclosure is directed to systems and methods for acquiring IR light and visible light images. A lens may be configured to operate in at least a first configuration and a second configuration. The lens may have a first filter over a first portion of the lens and a second filter over a second portion of the lens. In the first configuration, a third filter may operate with the lens and the second filter to allow visible light from a first object located beyond a predetermined distance from the lens to pass and be focused on a sensor for image acquisition. In the second configuration, a fourth filter may operate with the lens and the first filter to allow IR light from a second object located within the predetermined distance to pass and be focused on the sensor for image acquisition. | 2020-01-23 |
20200026919 | Parental Advisory Computer Systems and Computer-Implemented Methods of Use Thereof - Some embodiments of a computer-implemented method and system can entail continuously obtaining a visual input comprising a plurality of representations of at least one eye of at least one user to continuously track the plurality of representations over a predetermined time duration. The at least one processor can continually apply at least one eye-gaze movement tracking (EGMT) algorithm to form a time series of eye-gaze vectors. Continually inputting the time series of eye-gaze vectors into an Activity Tracking Neural Network (ATNN) can determine an attentiveness level of the at least one user over the predetermined time duration. The at least one processor can initiate a first action when the attentiveness level is equal to or above a predetermined threshold attentiveness value throughout the predetermined time duration; and initiate a second action when the attentiveness level is below the predetermined threshold attentiveness value throughout the predetermined time duration. | 2020-01-23 |
20200026920 | INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, EYEWEAR TERMINAL, AND AUTHENTICATION SYSTEM - There is provided an information processing apparatus including a display control unit configured to, when an authentication image including an iris of an eye of a user is obtained, cause a display unit to display an authentication UI for obtaining an authentication image with which it is easy to perform iris authentication. | 2020-01-23 |
20200026921 | SYSTEM, PORTABLE TERMINAL DEVICE, SERVER, PROGRAM, AND METHOD FOR VIEWING CONFIRMATION - The system is for confirming that a user of a portable terminal device has viewed posted material in a plurality of places by visiting one of the posted places, the system including the portable terminal device and a server, the device including a portable-terminal control unit, a portable-terminal communication unit, an image capturing unit, a portable-terminal storage unit, and a position-information obtaining unit, the server including a server control unit, a server communication unit, and a server storage unit that stores authenticated images about the posted material in the individual posted places in association with position information of the posted places, wherein the portable-terminal control unit sends a viewing confirmation request including a viewed image, the normalization information, and the portable-terminal position information to the server by using the portable-terminal communication unit, and the server control unit determines whether the viewed image is valid on the basis of the request. | 2020-01-23 |
20200026922 | Selectively Alerting Users of Real Objects in a Virtual Environment - A computer-implemented technique is described herein for discriminatively apprising the user of the existence of some, but not necessarily all, physical objects in a physical environment in the course of the user's interaction with a virtual environment. In operation, the technique allows the user to selectively identify one or more objects-of-interest, such as people, walls, computing devices, etc. The technique then uses a scene analysis component to automatically detect the presence of the selected objects-of-interest in the physical environment, while the user interacts with the virtual environment. The technique provides alert information which notifies the user of the existence of any objects-of-interest that it detects. By virtue of the above-summarized strategy, the technique can apprise the user of objects-of-interest in the user's vicinity without cluttering the user's virtual experience with extraneous information pertaining to the physical environment. | 2020-01-23 |
20200026923 | SYSTEM FOR AUTOMATICALLY DETECTING NEW HOME CONSTRUCTION PROGRESS - A system for automatically detecting new home construction progress is provided. The system includes an image classification controller that sends the digital photograph to a first digital image classification model which determines a first prediction score associated with a first physical attribute identifier. The build task test engine controller determines a first build task that has been completed in the new home using a first physical attribute identifier, a first prediction score, and first build task completion tests. The build task notification controller generates an electronic message that indicates the first build task has been completed. | 2020-01-23 |
20200026924 | SMART DISPLAY APPARATUS AND CONTROL SYSTEM - A computer-implemented method executed by a processor for reducing exposure of a plurality of objects to environmental conditions by employing a smart room tracking system is presented. The computer-implemented method includes counting a number of individuals within a space including the plurality of objects via one or more image capture devices and determining whether each individual makes direct eye contact with any of the plurality of objects by evaluating orientation, posture, and eye movement of each individual. The computer-implemented method further includes shielding, via an object viewing controller, an object of the plurality of objects from view when no direct eye contact is determined and making an object of the plurality of objects viewable, via the object viewing controller, when direct eye contact is determined. | 2020-01-23 |
20200026925 | METHOD, DEVICE AND APPARATUS FOR GENERATING ELECTRONIC MAP, STORAGE MEDIUM, AND ACQUISITION ENTITY - Embodiments of the present disclosure provide a method and a device for generating an electronic map, an electronic device, a computer readable storage medium, and an acquisition entity. The method includes: obtaining a first point cloud sequence and a second point cloud sequence for a preset region; generating a first grid map for the first point cloud sequence and a second grid map for the second point cloud sequence, wherein a grid in each of the first grid map and the second grid map at least comprises reflection value information of a point cloud; and optimizing the first point cloud sequence based on the first grid map and the second grid map. | 2020-01-23 |
20200026926 | Focalized Behavioral Measurements in a Video Stream - A system and method for analyzing behavior in a video is described. The method includes extracting a plurality of salient fragments of a video; generating a focalized visualization, based on a time anchor, from one or more of the plurality of salient fragments of the video; tagging a human subject in the focalized visualization with a unique identifier; and analyzing behavior of the human subject, using the focalized visualization, to generate a behavior score associated with the unique identifier and the time anchor. | 2020-01-23 |
20200026927 | Analysis of Operator Behavior Focalized on Machine Events - A system and method for analyzing behavior in a video is described. The method includes extracting a plurality of salient fragments of a video; associating a time anchor with an occurrence of a first machine event of a machine operated by a human subject; generating a focalized visualization, based on the time anchor, from one or more of the plurality of salient fragments of the video; tagging the human subject in the focalized visualization with a unique identifier; and analyzing behavior of the human subject, using the focalized visualization, to generate a behavior score associated with the unique identifier and the first machine event. | 2020-01-23 |
20200026928 | DEEP LEARNING FOR DENSE SEMANTIC SEGMENTATION IN VIDEO WITH AUTOMATED INTERACTIVITY AND IMPROVED TEMPORAL COHERENCE - Techniques related to automatically segmenting video frames into per pixel dense object of interest and background regions are discussed. Such techniques include applying a segmentation convolutional neural network (CNN) to a CNN input including a current video frame, a previous video frame, an object of interest indicator frame, a motion frame, and multiple feature frames each including features compressed from feature layers of an object classification convolutional neural network as applied to the current video frame to generate candidate segmentations and selecting one of the candidate segmentations as a final segmentation of the current video frame. | 2020-01-23 |
20200026929 | 3D Event Sequence Capture and Image Transform Apparatus and System - A system with 3D security cameras selectively captures and transmits images to avoid congestion of a network coupling them to a central server. Skeleton detection circuits enable conditional event capture when triggered. Head, hands, and feet are associated with pixel blocks. Sequences of images provide indicia of remarkable forces, motions, and weapons. Images are transformed to effectively alert a user. Security cameras may be mobile, body-worn, and fixed in location. | 2020-01-23 |
20200026930 | LANE LINE DETECTION METHOD AND APPARATUS - The present disclosure provides a lane line detection method and apparatus. The lane line detection method is applicable for an in-vehicle device and includes: determining a region of interest in an image to be detected; extracting lane line pixel features in the region of interest; combining similar lane line pixel features to generate a superpixel corresponding to the combined lane line pixel features; and performing a clustering and fitting process for respective superpixels to obtain a target lane line. | 2020-01-23 |
20200026931 | DRIVER FATIGUE WARNING SYSTEM - A driver-fatigue warning system suitable for use in an automated vehicle includes a camera, an alert-device, and a controller. The camera renders an image of a lane-marking and of an object proximate to a host-vehicle. The alert-device is operable to alert an operator of the host-vehicle of driver-fatigue. The controller is in communication with the camera and the alert-device. The controller determines a vehicle-offset of the host-vehicle relative to the lane-marking based on the image. The controller determines an offset-position of the object relative to the lane-marking based on the image. The controller determines that a lane-departure has occurred when the vehicle-offset is less than a deviation-threshold. The controller does not count occurrences of lane-departures when the offset-position is less than an offset-threshold, and activates the alert-device when the count of the occurrences of lane-departures exceeds a crossing-threshold indicative of driver-fatigue. | 2020-01-23 |
20200026932 | DRIVER FATIGUE WARNING SYSTEM - A driver-fatigue warning system suitable for use in an automated vehicle includes a camera, an alert-device, and a controller. The camera renders an image of a lane-marking and of an object proximate to a host-vehicle. The alert-device is operable to alert an operator of the host-vehicle of driver-fatigue. The controller is in communication with the camera and the alert-device. The controller determines a vehicle-offset of the host-vehicle relative to the lane-marking based on the image. The controller determines an offset-position of the object relative to the lane-marking based on the image. The controller determines that a lane-departure has occurred when the vehicle-offset is less than a deviation-threshold. The controller does not count occurrences of lane-departures when the offset-position is less than an offset-threshold, and activates the alert-device when the count of the occurrences of lane-departures exceeds a crossing-threshold indicative of driver-fatigue. | 2020-01-23 |
20200026933 | Estimation of Time to Collision in a Computer Vision System - A method for estimating time to collision (TTC) of a detected object in a computer vision system is provided that includes determining a three dimensional (3D) position of a camera in the computer vision system, determining a 3D position of the detected object based on a 2D position of the detected object in an image captured by the camera and an estimated ground plane corresponding to the image, computing a relative 3D position of the camera, a velocity of the relative 3D position, and an acceleration of the relative 3D position based on the 3D position of the camera and the 3D position of the detected object, wherein the relative 3D position of the camera is relative to the 3D position of the detected object, and computing the TTC of the detected object based on the relative 3D position, the velocity, and the acceleration. | 2020-01-23 |
20200026934 | IMAGE PROCESSING APPARATUS - An image processing apparatus ( | 2020-01-23 |
20200026935 | TRAFFIC SIGNAL RECOGNITION DEVICE AND AUTONOMOUS DRIVING SYSTEM - The traffic signal recognition device includes a traffic signal recognition unit configured to perform processing for recognizing the traffic signal based on the result of imaging performed by a camera, an external situation recognition unit configured to recognize a size and position of a surrounding vehicle, and a occluded situation determination unit configured to determine whether or not the area in front of a host vehicle is in the traffic signal occluded situation, in which the line of sight from the camera to the traffic signal is blocked by the surrounding vehicle. The traffic signal recognition unit is configured not to perform the processing for recognizing the traffic signal within a difficulty zone and not to perform the processing for recognizing the traffic signal if it is determined that the area in front of the host vehicle is in the traffic signal occluded situation. | 2020-01-23 |
20200026936 | VEHICLE LAMP DETECTION METHODS AND APPARATUSES, METHODS AND APPARATUSES FOR IMPLEMENTING INTELLIGENT DRIVING, MEDIA AND DEVICES - A vehicle lamp detection method includes: obtaining an image block including an image of a vehicle; and performing vehicle lamp detection on the image block by means of a deep neural network, to obtain a vehicle lamp detection result. | 2020-01-23 |
20200026937 | INFORMATION PROVIDING DEVICE, VEHICLE, AND INFORMATION PROVIDING METHOD - An information providing device can appropriately select how to provide information from the outside depending on the number of occupants in a vehicle. The information providing device includes an individual recognition function that recognizes the occupant in the vehicle, and performs individual recognition in the vehicle before the information is provided to the vehicle occupant. The vehicle includes the information providing device. In an information providing method, the individual recognition in the vehicle is performed prior to providing the occupant in the vehicle with the information. | 2020-01-23 |
20200026938 | OCCUPANT STATE RECOGNITION APPARATUS - An occupant state recognition apparatus including an eyelid opening recognition unit configured to recognize an eyelid opening of a driver and maximum and minimum values of the eyelid opening; an eye state determination unit configured to determine that the eye is in an eye open state if the eyelid opening becomes greater than or equal to a preset threshold value, and to determine that the eye is in an eye closed state if the eyelid opening becomes less than the threshold value; and a threshold value resetting unit configured to reset the threshold value to a value between the maximum value and the minimum value of the eyelid opening, if the maximum value (or the minimum value) has not become greater (or less) than or equal to the threshold value for a predetermined period or a period corresponding to a predetermined number of times of eyelid opening and closing. | 2020-01-23 |
20200026939 | ELECTRONIC DEVICE AND METHOD FOR CONTROLLING THE SAME - The present disclosure relates to an electronic device capable of performing multimodal biometric authentication, and the electronic device may include a memory configured to store information; a plurality of sensors configured to receive biometric information; a controller configured to: receive contextual information from one or more of the plurality of sensors; receive first biometric information from a first sensor of the plurality of sensors; perform a first biometric authentication comprising a generated similarity value between the received first biometric information and first biometric user information stored in the memory, wherein the first biometric authentication uses a first comparison threshold which varies based on the received contextual information; when the first biometric authentication is successful, execute the function according to the successful authentication; when the first biometric authentication is unsuccessful, perform a second biometric authentication using a second biometric information received from a second sensor of the plurality of sensors; and when a result of the first biometric authentication cannot be determined, perform a third biometric authentication using a third biometric information received from a third sensor of the plurality of sensors. | 2020-01-23 |
20200026940 | USER IDENTITY VERIFICATION METHOD, APPARATUS AND SYSTEM - This specification discloses a user identity verification method, apparatus, and system, relating to the field of information technology. The method comprises: receiving a facial image and one or more eye-print pair images corresponding to an identity verification object from a client, wherein a number of the one or more eye-print pair images corresponds to a number of eye-print collection steps, comparing the facial image to a preset facial image and comparing the one or more eye-print pair images to preset eye-print templates, and sending successful identity verification information to a client when comparison results for the facial image and the one or more eye-print pair images meet preset conditions. | 2020-01-23 |
20200026941 | PERSPECTIVE DISTORTION CHARACTERISTIC BASED FACIAL IMAGE AUTHENTICATION METHOD AND STORAGE AND PROCESSING DEVICE THEREOF - A perspective distortion characteristic based facial image authentication method and storage and processing device thereof are proposed. The method includes: S | 2020-01-23 |
20200026942 | Network, System and Method for Image Processing - A network for image processing is provided, and more particularly, for coarse-to-fine recognition of image processing. The network includes a shared convolution layer, and a first subnet and a second subnet both subsequent to the shared convolution layer; the first subnet comprises a first skipping module comprising one or more skip-dense blocks iteratively stacked with one or more transition layers, a first pooling layer subsequent to the first skipping module, and a first classification layer subsequent to the first pooling layer; the second subnet comprises a second skipping module comprising one or more skip-dense blocks iteratively stacked with one or more layers, a second pooling layer subsequent to the second skipping module, and a second classification layer subsequent to the second pooling layer; and wherein a skip-dense block of the second subnet is selected to guide a transition layer of the first subnet, and the level of the guiding skip-dense block is deeper than the level of the guided transition layer. This network is also related to a system and a method thereof. | 2020-01-23 |
20200026943 | SYSTEM AND METHOD FOR IDENTIFICATION AND PRIORITIZATION OF ONE OR MORE ATTRIBUTES IN AN IMAGE - A system and method for identification and prioritization of one or more attributes is provided. The system includes an image processing subsystem configured to receive a scanned image from a scanning device. The image processing subsystem is also configured to process the scanned image using one or more image processing techniques. The system also includes an identification subsystem coupled to the image processing subsystem. The identification subsystem is configured to identify one or more attributes from a processed image, where the one or more attributes includes a barcode or an image. The system or method further includes a prioritization subsystem coupled to the identification subsystem. The prioritization subsystem is configured to prioritize one or more identified attributes in a predefined order. The system further includes a recognition subsystem coupled to the identification subsystem. The recognition subsystem is configured to recognize a face of a user upon identification of the image. | 2020-01-23 |
20200026944 | SYSTEM FOR EXTRACTING TEXT FROM IMAGES - A system for extracting text from images comprises a processor configured to receive a digital copy of an image and identify a portion of the image, wherein the portion comprises text to be extracted. The processor further determines orientation of the portion of the image, and extracts text from the portion of the image considering the orientation of the portion of the image. | 2020-01-23 |
20200026945 | OBJECT DETECTION APPARATUS, TRAFFIC MONITORING SYSTEM, METHOD OF CONTROLLING AN OBJECT DETECTION APPARATUS AND PROGRAM - An object detection apparatus is provided with a discriminator applier and a candidate area calculator. The discriminator applier applies a discriminator which detects an object to images acquired in past and calculates object detection information including at least location information of the object detected by the discriminator, in a learning phase. The candidate area calculator performs a machine-learning by use of the object detection information and calculates object candidate area information including at least information specifying a candidate area in which the object may appear in an image. | 2020-01-23 |
20200026946 | METHOD FOR MATCHING LICENSE PLATE NUMBER, AND METHOD AND ELECTRONIC DEVICE FOR MATCHING CHARACTER INFORMATION - A method for matching a license plate number, comprises: obtaining a first license plate number to be matched; obtaining a license plate number library, wherein the license plate number library includes at least one second license plate number; calculating, based on a visual similarity of characters, a difficult degree in editing a character string required to converting between each second license plate number and the first license plate number; and determining, according to the difficult degree in editing a character string, at least one second license plate number matched with the first license plate number. | 2020-01-23 |
20200026947 | TEXT LINE NORMALIZATION SYSTEMS AND METHODS - A method for estimating text heights of text line images includes estimating a text height with a sequence recognizer. The method further includes normalizing a vertical dimension and/or position of text within a text line image based on the text height. The method may also further include calculating a feature of the text line image. In some examples, the sequence recognizer estimates the text height with a machine learning model. | 2020-01-23 |
20200026948 | Systems and Methods for Decoding Image Files Containing Depth Maps Stored as Metadata - Systems and methods in accordance with embodiments of the invention are configured to render images using light field image files containing an image synthesized from light field image data and metadata describing the image that includes a depth map. One embodiment of the invention includes a processor and memory containing a rendering application and a light field image file including an encoded image, a set of low resolution images, and metadata describing the encoded image, where the metadata comprises a depth map that specifies depths from the reference viewpoint for pixels in the encoded image. In addition, the rendering application configures the processor to: locate the encoded image within the light field image file; decode the encoded image; locate the metadata within the light field image file; and post process the decoded image by modifying the pixels based on the depths indicated within the depth map and the set of low resolution images to create a rendered image. | 2020-01-23 |
20200026949 | HASH-BASED APPEARANCE SEARCH - Methods, systems, and techniques for performing a hash-based appearance search. A processor is used to obtain a hash vector that represents a search subject that is depicted in an image. The hash vector includes one or more hashes as a respective one or more components of the hash vector. The processor determines which one or more of the hashes satisfy a threshold criterion and which one or more of the components of the hash vector qualify as a scoring component. The one or more components that qualify correspond to a respective one or more hashes that satisfy the threshold criterion and that are represented in a scoring database that is generated based on different examples of a search target. The processor determines a score representing a similarity of the search subject to the different examples of the search target. | 2020-01-23 |
20200026950 | INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND NON-TRANSITORY RECORDING MEDIUM - An information processing apparatus includes processing circuitry that acquires an electronic file containing first text data, and determines, based on the acquired electronic file, whether to use the first text data or second text data to perform a process. The second text data is generated through character recognition performed on an image contained in the acquired electronic file. | 2020-01-23 |
20200026951 | SYSTEMS AND METHODS FOR END-TO-END HANDWRITTEN TEXT RECOGNITION USING NEURAL NETWORKS - The present disclosure provides systems and methods for end-to-end handwritten text recognition using neural networks. Most existing hybrid architectures involve high memory consumption and large number of computations to convert an offline handwritten text into a machine readable text with respective variations in conversion accuracy. The method combine a deep Convolutional Neural Network (CNN) with a RNN (Recurrent Neural Network) based encoder unit and decoder unit to map a handwritten text image to a sequence of characters corresponding to text present in the scanned handwritten text input image. The deep CNN is used to extract features from handwritten text image whereas the RNN based encoder unit and decoder unit is used to generate converted text as a set of characters. The disclosed method requires less memory consumption and less number of computations with better conversion accuracy over the existing hybrid architectures. | 2020-01-23 |
20200026952 | ELECTRONIC APPARATUS, METHOD FOR PROCESSING IMAGE AND COMPUTER-READABLE RECORDING MEDIUM - The disclosure relates to an artificial intelligence (AI) system utilizing a machine learning algorithm, and application thereof. In particular, an electronic apparatus according to the disclosure includes a memory storing a trained artificial intelligence model, and a processor configured to acquire a plurality of feature values by inputting an input image to the artificial intelligence model. The trained artificial intelligence model applies each of a plurality of filters to a plurality of feature maps extracted from the input image and includes a pooling layer for acquiring feature values for the plurality of feature maps to which each of the plurality of filters is applied. | 2020-01-23 |
20200026953 | METHOD AND SYSTEM OF EXTRACTION OF IMPERVIOUS SURFACE OF REMOTE SENSING IMAGE - A method of extraction of an impervious surface of a remote sensing image. The method includes: 1) obtaining a remote sensing image of a target region, performing normalization for image data, and dividing the normalized target region image into a sample image and a test image; 2) extracting an image feature of each sample image by constructing a deep convolutional network for feature extraction of the remote sensing image; 3) performing pixel-by-pixel category prediction for each sample image respectively; 4) constructing a loss function by using an error between a prediction value and a true value of the sample image and performing update training for network parameters of the deep convolutional network and network parameters relating to the category prediction; and 5) extracting an image feature from the test image through the deep convolutional network based on the training result obtained in 4). | 2020-01-23 |
20200026954 | VIDEO TRACKING WITH DEEP SIAMESE NETWORKS AND BAYESIAN OPTIMIZATION - An apparatus, method, system and computer readable medium for video tracking. An exemplar crop is selected to be tracked in an initial frame of a video. Bayesian optimization is applied with each subsequent frame of the video by building a surrogate model of an objective function using Gaussian Process Regression (GPR) based on similarity scores of candidate crops collected from a search space in a current frame of the video. A next candidate crop in the search space is determined using an acquisition function. The next candidate crop is compared to the exemplar crop using a Siamese neural network. Comparisons of new candidate crops to the exemplar crop are made using the Siamese neural network until the exemplar crop has been found in the current frame. The new candidate crops are selected based on an updated surrogate model. | 2020-01-23 |
20200026955 | Computation of Audience Metrics Focalized on Displayed Content - A system and method for analyzing behavior in a video is described. The method includes extracting a plurality of salient fragments of a video; associating a time anchor with a presentation of a first media content to a human subject; generating a focalized visualization, based on the time anchor, from one or more of the plurality of salient fragments of the video; tagging the human subject in the focalized visualization with a unique identifier; and analyzing behavior of the human subject, using the focalized visualization, to generate a behavior score associated with the unique identifier and the first media content. | 2020-01-23 |
20200026956 | Custom Auto Tagging of Multiple Objects - There is described a computing device and method in a digital medium environment for custom auto tagging of multiple objects. The computing device includes an object detection network and multiple image classification networks. An image is received at the object detection network and includes multiple visual objects. First feature maps are applied to the image at the object detection network and generate object regions associated with the visual objects. The object regions are assigned to the multiple image classification networks, and each image classification network is assigned to a particular object region. The second feature maps are applied to each object region at each image classification network, and each image classification network outputs one or more classes associated with a visual object corresponding to each object region. | 2020-01-23 |
20200026957 | EMOTION CLASSIFICATION BASED ON EXPRESSION VARIATIONS ASSOCIATED WITH SAME OR SIMILAR EMOTIONS - Techniques are described that facilitate automatically distinguishing between different expressions of a same or similar emotion. In one embodiment, a computer-implemented is provided that comprises partitioning, by a device operatively coupled to a processor, a data set comprising facial expression data into different clusters of the facial expression data based on one or more distinguishing features respectively associated with the different clusters, wherein the facial expression data reflects facial expressions respectively expressed by people. The computer-implemented method can further comprise performing, by the device, a multi-task learning process to determine a final number of the different clusters for the data set using a multi-task learning process that is dependent on an output of an emotion classification model that classifies emotion types respectively associated with the facial expressions. | 2020-01-23 |
20200026958 | HIGH-DIMENSIONAL IMAGE FEATURE MATCHING METHOD AND DEVICE - A high-dimensional image feature matching method and device relating to the field of image retrieval. The method includes extracting a high-dimensional image feature of an image to be retrieved; dividing the high-dimensional image feature of the image to be retrieved into a plurality of low-dimensional image features; comparing each of the low-dimensional image features of the image to be retrieved with clustering centers at each layer of the low-dimensional image features of the images in a database; and determining a similarity the low-dimensional image feature between the image to be retrieved and each of some images in the database according to a comparison result, so that at least one feature matching the high-dimensional image feature of the image to be retrieved is retrieved in the database. | 2020-01-23 |
20200026959 | ELECTRONIC APPARATUS AND LEARNING METHOD OF ELECTRONIC APPARATUS - Artificial intelligence for machine learning to provide an optimized response sentence in reply to an input sentence. | 2020-01-23 |
20200026960 | REGRESSION-BASED LINE DETECTION FOR AUTONOMOUS DRIVING MACHINES - In various examples, systems and methods are disclosed that preserve rich spatial information from an input resolution of a machine learning model to regress on lines in an input image. The machine learning model may be trained to predict, in deployment, distances for each pixel of the input image at an input resolution to a line pixel determined to correspond to a line in the input image. The machine learning model may further be trained to predict angles and label classes of the line. An embedding algorithm may be used to train the machine learning model to predict clusters of line pixels that each correspond to a respective line in the input image. In deployment, the predictions of the machine learning model may be used as an aid for understanding the surrounding environment—e.g., for updating a world model—in a variety of autonomous machine applications. | 2020-01-23 |
20200026961 | High precision subtractive pattern recognition for image and other applications - A computer-implemented method includes selecting a kernel and kernel parameters for a first Support Vector Machine (SVM) model, testing the SVM model on a feature matrix T of n feature vectors of length m to produce false positive (FP) data set and false negative (FN) data set by a computer processor, wherein n and m are integer numbers, copying the feature matrix T to produce a feature matrix T_best, and checking if a ratio (T_best sample number)/(SVM support vector number) is above a threshold for the SVM model on T_best. If the ratio is above the threshold, SVM predictions are performed using the SVM model on the feature matrix T_best. The first SVM model can be used classify the faces or the objects in the images. An image-product design can be created based on the faces or the objects in the images classified by the first SVM model using the feature matrix T_best. | 2020-01-23 |
20200026962 | MODELING POST-LITHOGRAPHY STOCHASTIC CRITICAL DIMENSION VARIATION WITH MULTI-TASK NEURAL NETWORKS - A method of modeling distributions of post-lithography critical dimensions includes the following steps. A plurality of aerial images of respective portions of a physical design layout of a semiconductor wafer are generated, and the plurality of aerial images are employed as training data. In the method, first and second portions of a neural network architecture are generated. The first portion includes a neural network which is shared by a plurality of output channels, and the second portion includes a plurality of neural networks, wherein each of the plurality of neural networks respectively correspond to one of the plurality of output channels. The method further includes training the first and second portions of the neural network architecture with the training data, and outputting the distributions of the post-lithography critical dimensions based on the plurality of output channels. | 2020-01-23 |
20200026963 | REDUCING COMPUTATIONAL COSTS OF DEEP REINFORCEMENT LEARNING BY GATED CONVOLUTIONAL NEURAL NETWORK - A method is provided for reducing a computational cost of deep reinforcement learning using an input image to provide a filtered output image composed of pixels. The method includes generating a moving gate in which the pixels of the filtered output image to be masked are assigned a first gate value and the pixels of the filtered output image to be passed through are assigned a second gate value. The method further includes applying the input image and the moving gate to a GCNN to provide the filtered output image such that only the pixels of the input image used to compute the pixels assigned the second gate value are processed by the GCNN while bypassing the pixels of the input image useable to compute the pixels assigned the first gate to reduce an overall processing time of the input image in order to provide the filtered output image. | 2020-01-23 |
20200026964 | High recall subtractive pattern recognition for image and other applications - A computer-implemented method is disclosed for image recognition and other applications. The method employs an SVM model and can reduce false negatives and increase recognition accuracies by raising the sample-to-support-vector ratio. | 2020-01-23 |
20200026965 | METHODS AND SYSTEMS FOR BUDGETED AND SIMPLIFIED TRAINING OF DEEP NEURAL NETWORKS - Methods and systems for budgeted and simplified training of deep neural networks (DNNs) are disclosed. In one example, a trainer is to train a DNN using a plurality of training sub-images derived from a down-sampled training image. A tester is to test the trained DNN using a plurality of testing sub-images derived from a down-sampled testing image. In another example, in a recurrent deep Q-network (RDQN) having a local attention mechanism located between a convolutional neural network (CNN) and a long-short time memory (LSTM), a plurality of feature maps are generated by the CNN from an input image. Hard-attention is applied by the local attention mechanism to the generated plurality of feature maps by selecting a subset of the generated feature maps. Soft attention is applied by the local attention mechanism to the selected subset of generated feature maps by providing weights to the selected subset of generated feature maps in obtaining weighted feature maps. The weighted feature maps are stored in the LSTM. A Q value is calculated for different actions based on the weighted feature maps stored in the LSTM. | 2020-01-23 |
20200026966 | INFORMATION TRANSITION MANAGEMENT PLATFORM - A device may receive audio-video content regarding a system; segment the audio-video content to generate audio content and video content; process the audio content based on generating the audio content; process the video content based on generating the video content; identify a hierarchy for the set of sections based on processing the audio content and the video content; generate a system understanding document based on the hierarchy of the set of sections and based on the audio content and the video content; and store the system understanding document in a knowledge base. | 2020-01-23 |
20200026967 | SPARSE MRI DATA COLLECTION AND CLASSIFICATION USING MACHINE LEARNING - A system, method and program product for implementing a sparse sampling strategy for acquiring MRI data. A method includes: collecting and labeling a training dataset of MRI scans for a predetermined diagnostic; selecting a sampling shape and associated parameter values; sampling each MRI scan in the training data set using the sampling shape and associated parameter values to generate a set of sparse samples; training a neural network using the sparse samples and assigning an accuracy to a resulting trained neural network; and adjusting the associated parameter values, and repeating the sampling and training until optimized parameter values are established. | 2020-01-23 |
20200026968 | SYSTEM AND METHOD TO DETECT TRAPPED FLEXIBLE MATERIAL - One general aspect includes a memory configured to include a program and a processor configured to execute the program, where the program enables the processor to: after a first vehicle ingress/egress event, activate a sensor to capture a reference image of a portion of a vehicle body; after a second vehicle ingress/egress event, activate the sensor to capture a test image of the portion of the vehicle body; determine whether the test image includes one or more objects not found in the reference image; and release the door from the body or produce a notification or prevent vehicle movement or some combination thereof, based on the determination of whether the test image includes one or more objects not found in the reference image. | 2020-01-23 |
20200026969 | IMAGE DETECTION METHODS AND APPARATUS - A method for designating a given image as similar/dissimilar with respect to a reference image is provided. The method includes normalizing the image. Normalizing includes performing pre-processing and a lossy compression on the given image to obtain a lossy representation. The pre-processing includes at least one of cropping, fundamental extracting, gray scale converting and lower color bit converting. The method also includes comparing the lossy representation of the given image with a reference representation, which is a version of a reference spam image after the reference spam image has undergone a similar normalizing process as normalizing. The method further includes, if the lossy representation of the given image matches the reference representation, designating the given image similar to the reference image. The method yet also includes, if the lossy representation of the given image does not match the reference representation, designating the given image dissimilar to the reference image. | 2020-01-23 |
20200026970 | System and Method for Processing Character Images and Transforming Font Within a Document - The present disclosure relates to a system and method to transform character images from one representation to another representation. According to some embodiments of the present disclosure, a form may be processed to separate background data from content data, wherein character images from one or both the background data and the content data may be transformed. In some aspects, one or both handwritten font and type font may be processed in the character images, wherein the original fonts may be transformed into a uniform type font. In some embodiments, the character images may be translated to their correct state, wherein the translation may occur before or after the transformation. In some implementations, the translation and font transformation may allow for more efficient and effective character recognition. | 2020-01-23 |
20200026971 | AUTOMATIC GENERATION OF AN ANIMATED IMAGE FOR THE PRINTING THEREOF ON A LENTICULAR SUPPORT - The method for generating a final image for the printing thereof on a lenticular support includes an acquisition of a first file including a plurality of images; an automatic extraction of a determined number of images of the first file as a function of a maximum number of images to extract, the images being ordered according to a first order; a redimensioning of the images as a function of a parameter of density of lenses per unit surface area of a predefined printable support, called the pitch; an interlacing of the extracted images; and a generation of a final image to be printed on a lenticular support. | 2020-01-23 |
20200026972 | POWER SUPPLY WITH WIRELESSLY SUPPORTED PHASE OFFSET CONTROL FOR ACOUSTO-MAGNETIC SYSTEMS - Systems and methods for synchronizing operations of incompatible systems. The methods comprise: programming receiver operations of a Power Supply (“PS”) so that PS is interoperable with a first system of the incompatible systems; receiving by PS a wireless universal synchronization signal from a beacon of the first system; determining, by PS, a value for a phase offset setting of an internal signal conditioner circuit based on information contained in the wireless universal synchronization signal; generating a phase shifted Alternating Current (“AC”) signal by applying a phase offset to an input AC power signal in accordance with the determined value for the phase offset setting; buffering the phase shifted AC signal to generate an output AC power signal; and using a zero crossing of the output AC power signal to synchronize transmit and receive operations of a second system of the incompatible systems with the first system's transmit and receive operations. | 2020-01-23 |
20200026973 | SYSTEM AND APPARATUS FOR ENCRYPTED DATA COLLECTION USING RFID CARDS - A secure smart card is described. The smart card can include a processor, a memory and a transceiver. The smart card can communicate with various terminals and store a digital signature and other information on the card. Another terminal can validate the information stored on the smart card using the digital signature. In certain embodiments, the terminal can also validate the information by using a blockchain. The advanced design of the smart card obviates the need for a network connection. | 2020-01-23 |
20200026974 | SMART TAPE AND LOGISTICS SYSTEM USING THE SAME - A smart tape has a flexible substrate, chip, conductive glue, shielding layer and back glue layer. The chip is disposed above or below the flexible substrate. The conductive glue is electrically connected to the chip through the flexible substrate and has a specific pattern, so as to function as a sensing unit for sensing whether the smart tape has been peeled off. The shielding layer is disposed above the chip to protect the chip and prevent oxidation of the conductive glue. The back glue layer is disposed below the flexible substrate. | 2020-01-23 |
20200026975 | METHOD FOR RECORDING A REFERENCE BIOMETRIC DATA ITEM IN A BIOMETRIC SMART CARD - Disclosed is a method for recording a reference biometric data item in a biometric smart card including a biometric sensor. The recording of a biometric data item acquired by the biometric sensor, as a reference biometric data item, is completed in response to the validation, by the biometric smart card, of a personal secret code of the biometric smart card user entered on a first external device to authorise a transaction between the biometric smart card and a second external device by way of the first external device. | 2020-01-23 |
20200026976 | Method, System, and Computer Program Product for Harmonizing Industrial Machines with an Intelligent Industrial Assistant Having a Set of Predefined Commands - Provided is a method for harmonizing industrial machines with an intelligent industrial assistant having a set of predefined commands. The method may include providing at least one first industrial machine having a first proprietary input/output (I/O) interface having a plurality of states, each state associated with at least one of an input or an output of the first proprietary I/O interface. At least one state of the plurality of states may be mapped to each command of a first subset of a set of predefined commands. A customized interface for the first industrial machine(s) may be generated based on the mapping of the at least one state of the plurality of states to each command of the first subset of the set of predefined commands. The intelligent industrial assistant may connect to the first industrial machine(s) using the customized interface. A system and computer program product are also disclosed. | 2020-01-23 |
20200026977 | ELECTRONIC APPARATUS AND CONTROL METHOD THEREOF - A method for controlling an electronic apparatus includes storing a plurality of artificial intelligence models in a first memory, based on receiving a control signal for loading a first artificial intelligence model among the plurality of stored artificial intelligence models into a second memory, identifying an available memory size of the second memory, and based on a size of the first artificial intelligence model being larger than the available memory size of the second memory, obtaining a first compression artificial intelligence model by compressing the first artificial intelligence model based om the available memory size of the second memory, and loading the first compression artificial intelligence model into the second memory. | 2020-01-23 |
20200026978 | NEURAL PROCESSOR - A neural processor. In some embodiments, the processor includes a first tile, a second tile, a memory, and a bus. The bus may be connected to the memory, the first tile, and the second tile. The first tile may include: a first weight register, a second weight register, an activations buffer, a first multiplier, and a second multiplier. The activations buffer may be configured to include: a first queue connected to the first multiplier and a second queue connected to the second multiplier. The first queue may include a first register and a second register adjacent to the first register, the first register being an output register of the first queue. The first tile may be configured: in a first state: to multiply, in the first multiplier, a first weight by an activation from the output register of the first queue, and in a second state: to multiply, in the first multiplier, the first weight by an activation from the second register of the first queue. | 2020-01-23 |
20200026979 | NEURAL PROCESSOR - A neural processor. In some embodiments, the processor includes a first tile, a second tile, a memory, and a bus. The bus may be connected to the memory, the first tile, and the second tile. The first tile may include: a first weight register, a second weight register, an activations buffer, a first multiplier, and a second multiplier. The activations buffer may be configured to include: a first queue connected to the first multiplier and a second queue connected to the second multiplier. The first queue may include a first register and a second register adjacent to the first register, the first register being an output register of the first queue. The first tile may be configured: in a first state: to multiply, in the first multiplier, a first weight by an activation from the output register of the first queue, and in a second state: to multiply, in the first multiplier, the first weight by an activation from the second register of the first queue. | 2020-01-23 |
20200026980 | NEURAL PROCESSOR - A neural processor. In some embodiments, the processor includes a first tile, a second tile, a memory, and a bus. The bus may be connected to the memory, the first tile, and the second tile. The first tile may include: a first weight register, a second weight register, an activations buffer, a first multiplier, and a second multiplier. The activations buffer may be configured to include: a first queue connected to the first multiplier and a second queue connected to the second multiplier. The first queue may include a first register and a second register adjacent to the first register, the first register being an output register of the first queue. The first tile may be configured: in a first state: to multiply, in the first multiplier, a first weight by an activation from the output register of the first queue, and in a second state: to multiply, in the first multiplier, the first weight by an activation from the second register of the first queue. | 2020-01-23 |
20200026981 | SPIKING NEURAL NETWORK FOR PROBABILISTIC COMPUTATION - Described is a system for computing conditional probabilities of random variables for Bayesian inference. The system implements a spiking neural network of neurons to compute the conditional probability of two random variables X and Y. The spiking neural network includes an increment path for a synaptic weight that is proportional to a product of the synaptic weight and a probability of X, a decrement path for the synaptic weight that is proportional to a probability of X, Y, and delay and spike timing dependent plasticity (STDP) parameters such that the synaptic weight increases and decreases with the same magnitude for a single firing event. | 2020-01-23 |
20200026982 | Techniques For Estimating And Forecasting Solar Power Generation - A computer system is configured to group solar power systems that provide electric power to an electricity distribution system into clusters. The computer system identifies a solar source meter in each of the clusters that is representative of the respective one of the clusters as a bellwether meter. Each of the bellwether meters monitors a power output of one of the solar power systems in one of the clusters. The computer system receives solar power generation data from the bellwether meters. The computer system generates a solar power generation forecast for each of the clusters of the solar power systems using the solar power generation data from the bellwether meters in respective ones of the clusters. | 2020-01-23 |
20200026983 | Method and apparatus for signal matching - A signal matching apparatus comprising at least one receiving unit adapted to receive a signal; at least one memory unit adapted to store predefined reference data and at least one neural network configured to compare a signal profile of the received signal and/or signal parameters derived from the received signal with reference data stored in said memory unit to determine a similarity between the received signal and the predefined reference data. | 2020-01-23 |
20200026984 | METHODS AND APPARATUS TO DETECT PHYSICAL CHANGES IN AN ENVIRONMENT - Methods, apparatus, systems and articles of manufacture to detect changes in a physical environment are disclosed. An example apparatus includes a descriptor generator to generate a first descriptor, the descriptor generator including: a chirp producer to emit a chirp into the environment, a chirp recorder to record a response to the chirp from the environment, and a chirp response encoder to generate an encoding of the response to the chirp; a descriptor similarity generator to generate a similarity value, the similarity value to compare the first descriptor to a second descriptor; and a physical change indicator to, in response to the similarity value exceeding a similarity threshold, indicate that a physical change has occurred in the environment. | 2020-01-23 |
20200026985 | SYSTEM AND METHOD FOR CHARACTERIZING AN ARBITRARY-LENGTH TIME SERIES USING PRE-SELECTED SIGNATURES - One embodiment provides a system for facilitating characterization of a time series of data associated with a physical system. During operation, the system determines one or more signatures, wherein a signature indicates a basis function for a known time series of data. The system trains a neural network based on the signatures as a known output. The system applies the trained neural network to the time series to generate a probability that the time series is characterized by a respective signature. The system enhances an analysis of the time series data and the physical system based on the probability. | 2020-01-23 |
20200026986 | NEURAL NETWORK METHOD AND APPARTUS WITH PARAMETER QUANTIZATION - A neural network method of parameter quantization includes obtaining channel profile information for first parameter values of a floating-point type in each channel included in each of feature maps based on an input in a first dataset to a floating-point parameters pre-trained neural network; determining a probability density function (PDF) type, for each channel, appropriate for the channel profile information based on a classification network receiving the channel profile information as a dataset; determining a fixed-point representation, based on the determined PDF type, for each channel, statistically covering a distribution range of the first parameter values; and generating a fixed-point quantized neural network based on the fixed-point representation determined for each channel. | 2020-01-23 |
20200026987 | NEURAL NETWORK BASED POSITION ESTIMATION OF TARGET OBJECT OF INTEREST IN VIDEO FRAMES - Visual target tracking is task of locating a target in consecutive frame of a video. Conventional systems observe target behavior frames of the video. However, dealing with this problem is very challenging when video has illumination variations, occlusion, change in size and view of the object due to relative motion between camera and object. Embodiments of the present disclosure addresses this problem by implementing Neural Network (NN), its features and their corresponding gradients. Present disclosure explicitly guides the NN by feeding target object of interest (ToI) defined by a bounding box in the first frame of the video. With this guidance, NN generates target activation map via convolutional features map and their gradient maps, thus giving tentative location of the ToI to further exploit to locate target object precisely by using correlation filter(s) and peak location estimator, thus repeating process for every frame of video to track ToI accurately. | 2020-01-23 |
20200026988 | METHODS AND SYSTEMS USING IMPROVED TRAINING AND LEARNING FOR DEEP NEURAL NETWORKS - Methods and systems are disclosed using improved training and learning for deep neural networks. In one example, a deep neural network includes a plurality of layers, and each layer has a plurality of nodes. For each L layer in the plurality of layers, the nodes of each L layer are randomly connected to nodes in a L+1 layer. For each L+1 layer in the plurality of layers, the nodes of each L+1 layer are connected to nodes in a subsequent L layer in a one-to-one manner. Parameters related to the nodes of each L layer are fixed. Parameters related to the nodes of each L+1 layers are updated, and L is an integer starting with 1. In another example, a deep neural network includes an input layer, output layer, and a plurality of hidden layers. Inputs for the input layer and labels for the output layer are determined related to a first sample. Similarity between different pairs of inputs and labels between a second sample with the first sample is estimated using Gaussian regression process. | 2020-01-23 |
20200026989 | PERFORMING CONSECUTIVE MAC OPERATIONS ON A SET OF DATA USING DIFFERENT KERNELS IN A MAC CIRCUIT - A circuit arrangement includes an array of MAC circuits, wherein each MAC circuit includes a cache configured for storage of a plurality of kernels. The MAC circuits are configured to receive a first set of data elements of an IFM at a first rate. The MAC circuits are configured to perform first MAC operations on the first set of the data elements and a first one of the kernels associated with a first OFM depth index during a first MAC cycle, wherein a rate of MAC cycles is faster than the first rate. The MAC circuits are configured to perform second MAC operations on the first set of the data elements and a second one of the kernels associated with a second OFM depth index during a second MAC cycle that consecutively follows the first MAC cycle. | 2020-01-23 |
20200026990 | NEURAL NETWORK SYSTEM - A neural network system for execution of a sum-of-products operation includes a memory device and a controller. The memory device includes a 3D array having a plurality of memory cells with programmable conductances disposed in cross-points of a plurality of cell body lines and gate lines, a gate driver coupled to the gate lines and applying control gate voltages in combination with the programmable conductances for corresponding to weights of terms in the sum-of-products operation, a input driver used to apply voltages to the memory cells corresponding to input variables, a plurality of input lines connecting the cell body lines to the input driver, a sensing circuit used to sense currents passing through the memory cells corresponding the terms in the sum-of-products operation, a buffer circuit used to store the terms. The controller is used to control the memory device summing up the terms in the sum-of-products operation. | 2020-01-23 |
20200026991 | In-Memory Computing Devices for Neural Networks - An in-memory computing device includes a plurality of synaptic layers including a first type of synaptic layer and a second type of synaptic layer. The first type of synaptic layer comprises memory cells of a first type of memory cell and the second type of synaptic layer comprises memory cells of a second type, the first type of memory cell being different than the second type of memory cell. The first and second types of memory cells can be different types of memories, have different structures, different memory materials, and/or different read/write algorithms, any one of which can result in variations in the stability or accuracy of the data stored in the memory cells. | 2020-01-23 |
20200026992 | HARDWARE NEURAL NETWORK CONVERSION METHOD, COMPUTING DEVICE, COMPILING METHOD AND NEURAL NETWORK SOFTWARE AND HARDWARE COLLABORATION SYSTEM - A hardware neural network conversion method, a computing device, a compiling method and a neural network software and hardware collaboration system for converting a neural network application into a hardware neural network fulfilling a hardware constraint condition are disclosed. The method comprises: obtaining a neural network connection diagram corresponding to the neural network application; splitting the neural network connection diagram into neural network basic units; converting each of the neural network basic units so as to form a network having equivalent functions thereto and formed by connecting basic module virtual entities of neural network hardware; and connecting the obtained basic unit hardware network according to the sequence of splitting so as to create a parameter file for the hardware neural network. The present disclosure provides a novel neural network and a brain-like computing software and hardware system. | 2020-01-23 |
20200026993 | NEURAL NETWORK CIRCUIT - A neural network circuit includes: multiple storage portions that include a memristor; multiple D/A converters that receive data, causing a signal voltage to be applied to multiple voltage input terminals of the storage portions; multiple drive amplifiers that are connected between to the D/A converters and the voltage input terminals; multiple I/V conversion amplifiers that are connected to at least one current output terminal of the storage portions; multiple A/D converters; and a series circuit of a first switch and a second switch that is disposed in a feedback loop of each of the drive amplifiers; and a series circuit of a third switch and a fourth switch that is disposed in a feedback loop of each of the I/V conversion amplifiers. | 2020-01-23 |
20200026994 | METHODS AND SYSTEMS OF NEURON LEAKY INTEGRATE AND FIRE CIRCUITS - Embodiments include methods and systems of neuron leaky integrate and fire circuit (NLIFC). Aspects include: receiving an input current having both AC component and DC component at an input terminal of the NLIFC, extracting AC component of input current, generating a number of swing voltages at a swing node using extracted AC component of the input current, transferring charge from a pull-up node to a neuron membrane potential (NP) node through an integration diode and a pull-up diode to raise a voltage at NP node over an integration capacitor gradually and the voltage at NP node shows integration value of AC component of input current, implementing leaky decay function of the neuron leaky integrate and fire circuit, detecting a timing of neuron fire using an analog comparator, resetting a neuron membrane potential level for a refractory period after neuron fire, and generating fire output signal of the NLIFC. | 2020-01-23 |
20200026995 | Memristor Spiking Architecture - A circuit for a neuron of a multi-stage compute process is disclosed. The circuit comprises a weighted charge packet (WCP) generator. The circuit may also include a voltage divider controlled by a programmable resistance component (e.g., a memristor). The WCP generator may also include a current mirror controlled via the voltage divider and arrival of an input spike signal to the neuron. WCPs may be created to represent the multiply function of a multiply accumulate processor. The WCPs may be supplied to a capacitor to accumulate and represent the accumulate function. The value of the WCP may be controlled by the length of the spike in signal times the current supplied through the current mirror. Spikes may be asynchronous. Memristive components may be electrically isolated from input spike signals so their programmed conductance is not affected. Positive and negative spikes and WCPs for accumulation may be supported. | 2020-01-23 |
20200026996 | Method, Apparatus and Computer Program for generating robust automatic learning systems and testing trained automatic learning systems - A method for training an automated learning system includes processing training input with a first neural network and processing the output of the first neural network with a second neural network. The input layer of the second neural network corresponding to the output layer of the first neural network. The output layer of the second neural network corresponding to the input layer of the first neural network. An objective function is determined using the output of the second neural network and a predetermined modification magnitude. The objective function is approximated using random Cauchy projections which are propagated through the second neural network. | 2020-01-23 |
20200026997 | METHOD OF MANAGING DATA REPRESENTATION FOR DEEP LEARNING, METHOD OF PROCESSING DATA FOR DEEP LEARNING AND DEEP LEARNING SYSTEM PERFORMING THE SAME - A method of processing data for a deep learning system driven by a plurality of heterogeneous resources is provided. The method includes, when a first task including at least one of a plurality of operations is to be performed, receiving first path information indicating a first computing path for the first task. The first computing path includes a sequence of operations included in the first task and a driving sequence of resources for performing the operations included in the first task. The method further includes setting data representation formats of the resources for performing the operations included in the first task based on data representation information and the first path information. The data representation information indicates an optimized data representation format for each of the plurality of heterogeneous resources. | 2020-01-23 |
20200026998 | INFORMATION PROCESSING APPARATUS FOR CONVOLUTION OPERATIONS IN LAYERS OF CONVOLUTIONAL NEURAL NETWORK - According to one embodiment, an information processing apparatus for convolution operations in layers of a convolutional neural network, includes a memory and a product-sum operating circuitry. The memory is configured to store items of information indicative of an input, a weight to the input, and a bit width determined for each filter of the weight. The product-sum operating circuitry is configured to perform a product-sum operation based on the items of information indicative of the input, the weight, and the bit width, stored in the memory. | 2020-01-23 |
20200026999 | METHODS AND SYSTEMS FOR BOOSTING DEEP NEURAL NETWORKS FOR DEEP LEARNING - Methods and systems are disclosed for boosting deep neural networks for deep learning. In one example, in a deep neural network including a first shallow network and a second shallow network, a first training sample is processed by the first shallow network using equal weights. A loss for the first shallow network is determined based on the processed training sample using equal weights. Weights for the second shallow network are adjusted based on the determined loss for the first shallow network. A second training sample is processed by the second shallow network using the adjusted weights. In another example, in a deep neural network including a first weak network and a second weak network, a first subset of training samples is processed by the first weak network using initialized weights. A classification error for the first weak network on the first subset of training samples is determined. The second weak network is boosted using the determined classification error of the first weak network with adjusted weights. A second subset of training samples is processed by the second weak network using the adjusted weights. | 2020-01-23 |
20200027000 | METHODS AND SYSTEMS FOR ANNOTATING REGULATORY REGIONS OF A MICROBIAL GENOME - Methods and systems for annotating regulatory regions of a microbial genome. A method disclosed herein includes extracting data related to at least one promoter of the regulatory regions of the microbial genome, wherein the data includes at least one promoter sequence and data available for at least one promoter subtype. Based on extracted at least one feature of the at least one promoter sequence, the method further includes configuring at least one predictive model using the deep learning based neural network to predict the at least one promoter subtype associated with the at least one promoter sequence. The method further includes annotating at least one unknown promoter sequence into the at least one promoter subtype using the at least one configured predictive model. | 2020-01-23 |
20200027001 | NEURAL NETWORK BASED RECOGNITION APPARATUS AND METHOD OF TRAINING NEURAL NETWORK - A neural network recognition method includes obtaining a first neural network that includes layers and a second neural network that includes a layer connected to the first neural network, actuating a processor to compute a first feature map from input data based on a layer of the first neural network, compute a second feature map from the input data based on the layer connected to the first neural network in the second neural network, and generate a recognition result based on the first neural network from an intermediate feature map computed by applying an element-wise operation to the first feature map and the second feature map. | 2020-01-23 |
20200027002 | CATEGORY LEARNING NEURAL NETWORKS - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a clustering of images into a plurality of semantic categories. In one aspect, a method comprises: training a categorization neural network, comprising, at each of a plurality of iterations: processing an image depicting an object using the categorization neural network to generate (i) a current prediction for whether the image depicts an object or a background region, and (ii) a current embedding of the image; determining a plurality of current cluster centers based on the current values of the categorization neural network parameters, wherein each cluster center represents a respective semantic category; and determining a gradient of an objective function that includes a classification loss and a clustering loss, wherein the clustering loss depends on a similarity between the current embedding of the image and the current cluster centers. | 2020-01-23 |
20200027003 | PACKAGE METHOD OF RADIOACTIVE DISMANTLED PARTS - A packaging methodology for radioactive dismantled parts of nuclear facilities is provided. This methodology integrates voxelization and metaheuristic to discretize the irregular 3D shape of various dismantled parts and put them into the containers with greatest efficiency. To enumerate the possible locations and orientations of an irregular part effectively, the solid models of the dismantled parts are descripted to user-specified voxelization operations. Therefore, discretized parts and container yield a finite space of optimal solutions and make the evolution algorithm viable for optimization quest. This methodology improves the package efficiency of the radioactive dismantled parts to reduce the required quantity of the storage containers. | 2020-01-23 |
20200027004 | Content Explanation Method and Apparatus - A content explanation method and apparatus applied to content explanation includes identifying, by a content explanation apparatus, an emotion of the user, when identifying a negative emotion showing that the user is confused about delivered multimedia information, obtaining, by the content explanation apparatus, a target representation manner of target content in a target intelligence type, where the target content is content about which the user is confused in the multimedia information delivered to the user by an information delivery apparatus associated with the content explanation apparatus, and presenting, by the content explanation apparatus, the target content to the user in the target representation manner. | 2020-01-23 |
20200027005 | SYSTEMS AND METHODS FOR ACCELERATING EXECUTION OF PROCESSES BASED ON ARTIFICIAL INTELLIGENCE (AI) PREDICTION OF BLOCKCHAIN CONSENSUS - A method for using a distributed ledger (DL) of a blockchain applicable to a network of blockchain nodes is provided. The method reduces a time period between an assertion placed on the blockchain by an assertor blockchain node and execution of one or more action items dependent on a consensus of the assertion, by: creating an Artificial Intelligence (AI) model, by one of the blockchain nodes of the network, using historical data stored by the DL, wherein the network of blockchain nodes further comprises the assertor blockchain node; calculating an index value indicating a probability that the consensus is true, based on the AI model and the historical data stored by the DL, by the one of the blockchain nodes, wherein each of the blockchain nodes comprises a computer system including at least a processor, a system memory element, and a communication device configured to send and receive data transmissions between the blockchain nodes of the network; and when the index value exceeds a predefined threshold, initiating the execution of the one or more action items dependent on the consensus, by the one of the blockchain nodes. | 2020-01-23 |
20200027006 | SYSTEM AND METHOD FOR HIERARCHICAL METRIC TEMPORAL PLANNING AND RE-PLANNING - Advanced systems and methods for temporal planning employ a temporal logic for representing and reasoning about temporal constraints over both logic and numeric (discrete and continuous) variables and continuous time. A temporal planning language represents a world model, and adapts the temporal planning language to support formulas expressing the temporal logic. Embodiments of the present disclosure also can receive a temporal planning problem and derive one or more solutions to the temporal planning problem using one or more of the formulas. Embodiments of the present disclosure further address re-planning such as, for example, when a new objective task is added to the set of objective tasks to be performed, when an existing objective task is cancelled, and/or when some event occurs unpredictably and invalidates the current plan. | 2020-01-23 |
20200027007 | CONVERSATIONAL OPTIMIZATION OF COGNITIVE MODELS - Systems and methods to generate cognitive models are described. A particular apparatus includes a memory having program code and a processor configured to access the memory and to execute the program code to process user input that includes a natural language dialogue-based command pertaining to a cognitive model, to automatically run analysis on the cognitive model and to present a user in natural language with a recommendation to modify the cognitive model. | 2020-01-23 |