20th week of 2017 patent applcation highlights part 50 |
Patent application number | Title | Published |
20170140186 | INFORMATION PROVISION SYSTEM, COMMUNICATION TERMINAL, AND INFORMATION PROVISION PROGRAM - An information provision system includes: a reading section that reads an information code; a situation acquisition section that acquires a situation when the information code is read by the reading section; a determination section that determines a situation when the information code is read, based on (i) read information that is obtained by decoding the information code that is read and (ii) the situation acquired by the situation acquisition section; a provided information generation section that generates provided information that is different from the read information, the provided information matching with the situation when the information code is read; and a provision section that provides the provided information that is generated. | 2017-05-18 |
20170140187 | Portable Optical Reader - A portable optical reader is provided with LED light sources | 2017-05-18 |
20170140188 | Portable Optical Reader - A portable optical reader is provided with: a reading part | 2017-05-18 |
20170140189 | ULTRAVIOLET FLUORESCENT BARCODE READING METHOD AND DEVICE - An ultraviolet fluorescent barcode reading method and device, the reading method comprising the following steps: S | 2017-05-18 |
20170140190 | MULTIMEDIA SERVICE PUSHING METHOD AND SYSTEM BASED ON TWO-DIMENSIONAL CODE - The invention discloses a multimedia service pushing method and a multimedia service pushing system based on two-dimensional codes. The multimedia service pushing method comprises the steps that: a multimedia terminal receives multimedia content and multimedia service information sent by a multimedia server, generates a two-dimensional code image according to the multimedia service information, and overlaying the two-dimensional code image on the multimedia content for display; when a scanning terminal detects the two-dimensional code image on the multimedia terminal, the scanning terminal parses the two-dimensional code image to obtain a service command, sends a service request to a service server according to the service command, and obtains service content corresponding to the service command; and the scanning terminal or the multimedia terminal receives the service content and displays the service content. The multimedia service pushing method and the multimedia service pushing system based on the two-dimensional codes achieve the effect of automatically acquiring single or multiple pieces of service content corresponding to the multimedia service information through scanning and parsing the two-dimensional code images via the scanning terminal, reduces the space occupation of the multimedia service information, is convenient to operate and control, and brings great convenience to users. | 2017-05-18 |
20170140191 | SYMBOL DETECTOR, IMAGE PROCESSING DEVICE, AND SYMBOL DETECTING METHOD - A symbol detector includes a binarization processor configured to read a symbol image in a uniaxial direction and output a first pixel value or a second pixel value obtained by binarization of a pixel value of each pixel of the symbol image, a calculator configured to calculate a second ratio of a first consecutive value and a second consecutive value obtained before and after the first consecutive value in a case where the first consecutive value and the second consecutive value are switched alternately, and a transmitter configured to output the symbol image in a case where a difference between the calculated second ratio and the first ratio is equal to or lower than a predetermined value, and stop outputting the symbol image in a case where the difference is higher than the predetermined value. | 2017-05-18 |
20170140192 | Feature-Based Matcher for Distorted Fingerprint Matching - In one aspect, methods that use a novel representation, referred to as an octant feature vector (OFV), are used for matching distorted fingerprints. For instance, a feature-based matcher for distorted fingerprint matching may use a two-step local and global matching scheme to compare a set of feature vectors that are derived from minutiae of a reference fingerprint and a search fingerprint. The relative geometric relationships between the reference minutia and nearest minutiae may be derived and encoded into a feature vector based on orientation difference. The OFV is invariant to the rigid transformations and is insensitive to nonlinear distortions since the relative geometric relationships are independent from the rigid transformation. | 2017-05-18 |
20170140193 | Minutiae Grouping for Distorted Fingerprint Matching - In some implementations, a computer-implemented method includes an iterative minutiae matching technique that initially groups mated minutiae within a list of all possible minutiae between a reference fingerprint and a search fingerprint, and then successively performs a geometric consistency check of the mated minutiae within the group. In some instances, the iterative matching technique enables improved identification of globally aligned mated minutiae within distorted regions, which may be used to subsequently improve the calculation of a similarity score between a reference fingerprint and a search fingerprint. | 2017-05-18 |
20170140194 | FINGERPRINT IDENTIFICATION DEVICE, TOUCH PANEL, INPUT DEVICE AND FINGERPRINT IDENTIFICATION METHOD - The present disclosure provides a fingerprint identification device, a touch panel, an input device and a fingerprint identification method. The fingerprint identification device includes a fingerprint identification module, gate lines and signal lines. The gate lines and the signal lines cross so as to define a plurality of sensing regions including a thin film transistors and a sensing electrode connected to the thin film transistors. A gate electrode of the thin film transistor is connected to the corresponding gate line, a source electrode is connected to the corresponding signal line, and a drain electrode is connected to the corresponding sensing electrode. The signal lines include signal-transmitting lines and signal-receiving lines, the sensing electrodes include transmitting electrodes and receiving electrodes. An electric field is generated between the transmitting electrode and the receiving electrode adjacent to the transmitting electrode, and a direction of the electric field is from the transmitting electrode to the receiving electrode adjacent to the transmitting electrode. The fingerprint identification module is connected to the signal-receiving lines, and determines, by detecting the intensity of the electric field when a finger is in the electric field, a fingerprint of the finger. | 2017-05-18 |
20170140195 | FINGERPRINT RECOGNITION CHIP PACKAGING STRUCTURE AND PACKAGING METHOD - A fingerprint recognition chip packaging structure and a packaging method. The packaging structure includes: a substrate provided with a substrate surface; a sensor chip coupled on the surface of the substrate, where the sensor chip is provided with a first surface and a second surface opposite the first surface, the first surface of the sensor chip is provided with a sensing area, and the second surface of the sensor chip is arranged on the surface of the substrate; a capping layer arranged on the surface of the sensing area of the sensor chip, where the material of the capping layer is a polymer; and, a lamination layer arranged on the surface of the substrate and that of the sensor chip, where the lamination layer exposes the capping layer. The packaging structure allows for reduced requirements on the sensitivity of the sensor chip, thus broadening applications. | 2017-05-18 |
20170140196 | Fingerprint Sensor-Compatible Overlay Material - A fingerprint sensor-compatible overlay material which uses anisotropic conductive material to enable accurate imaging of a fingerprint through an overlay is disclosed. The anisotropic conductive material has increased conductivity in a direction orthogonal to the fingerprint sensor, increasing the capacitive coupling of the fingerprint to the sensor surface, allowing the fingerprint sensor to accurately image the fingerprint through the overlay. Methods for forming a fingerprint sensor-compatible overlay are also disclosed. | 2017-05-18 |
20170140197 | OLED PANEL, TERMINAL AND METHOD FOR CONTROLLING IDENTIFICATION - The present disclosure provides an OLED panel, a mobile device and a method for controlling identification, and belongs to the field of display technology. The OLED panel includes an array substrate, an OLED layer disposed on the array substrate, a fingerprint collecting unit array disposed in the array substrate, or a fingerprint collecting unit array disposed between the array substrate and the OLED layer, and a control circuit connected to the fingerprint collecting unit array. | 2017-05-18 |
20170140198 | FINGERPRINT IDENTIFICATION DEVICE AND METHOD - A fingerprint identification device includes a substrate, at least two electrode areas, at least one dedicated sensing signal line, plural electrode selection switch groups, and plural signal lines. Each electrode area has plural electrodes. The signal lines are divided into plural first directional signal lines and plural second directional signal lines. The first directional signal lines are perpendicular to the second directional signal lines. The plural electrode selection switch groups sequentially or dynamically select at least one electrode as a sensing electrode block in each electrode area. The plural electrode selection switch groups configure the electrodes surrounding the sensing electrode block as at least two corresponding deflection electrode blocks. Each sensing electrode block is corresponding to at least two deflection electrode blocks. Each deflection electrode block has plural electrodes. | 2017-05-18 |
20170140199 | Automatic Ruler Detection - In some implementations, a method includes: receiving, from the camera, a sample image that includes a fingerprint and a mensuration reference device, where the sample image is associated with a resolution; identifying (i) a plurality of edge candidate groups within the sample image, and (ii) a set of regularity characteristics associated with each of the plurality of edge candidate groups; determining that the associated set of regularity characteristics indicates the mensuration reference device; identifying a ruler candidate group, from each of the plurality of edge candidate groups, based at least on determining that the associated set of regularity characteristics indicates the mensuration reference device; computing a scale associated with the sample image based at least on extracting a set of ruler marks from the identified ruler candidate group; and generating, based at least on the scale associated with the sample image, a scaled image. | 2017-05-18 |
20170140200 | VEHICLE FINGERPRINT BOOKMARK - Provided in the present disclosure is a fingerprint bookmark system which may be implemented in a vehicle with one or more configurable interior settings. The fingerprint bookmark system may contain a scanner which may be configured to record a fingerprint from a vehicle occupant such that a fingerprint image showing the fingerprint and a duration data for the fingerprint image are recorded by the scanner. The system may contain one or more processors which may be configured to compare the duration data associated with the fingerprint image with a duration threshold. The one or more processors may be configured to initiate a search to obtain a bookmark for the fingerprint shown in the fingerprint image when the duration data is less than the duration threshold. The one or more processors may be further configured to create a new bookmark when the duration data exceeds the duration threshold. | 2017-05-18 |
20170140201 | SCREEN MODULE, FINGERPRINT ACQUISITION METHOD, AND ELECTRONIC DEVICE - A screen module, a fingerprint acquisition method, and an electronic device are provided. The screen module includes: a fingerprint unit comprising a plurality of fingerprint sensors, which are located in a content display area of the screen module and configured to perform fingerprint acquisition; a processing component connected with the fingerprint unit, the processing component being configured to, after a triggering operation of a user's finger on the content display area is detected, actuate fingerprint sensors in a scanning area corresponding to the triggering operation to acquire fingerprint data of the user in the scanning area; and data transmission lines connected to the plurality of fingerprint sensors, and configured to transmit fingerprint data acquired by the fingerprint sensors in the scanning area to the processing component. | 2017-05-18 |
20170140202 | Fingerprint Sensor Device and Method - A fingerprint sensor package and method are provided. Embodiments include a sensor and a sensor surface material encapsulated within the fingerprint sensor package. An array of electrodes of the sensor are electrically connected using through vias that are located either in the sensor, in connection blocks separated from the sensor, or through connection blocks, or else connected through other connections such as wire bonds. A high voltage die is attached in order to increase the sensitivity of the fingerprint sensor. | 2017-05-18 |
20170140203 | METHOD, APPARATUS, AND PROGRAM FOR JUDGING GRID QUALITY - An image obtaining section obtains a radiation image that includes a periodic pattern of a grid. A frequency analyzing section performs frequency analysis on the radiation image to obtain a frequency spectrum of the radiation image. A peak determining section determines a peak within the frequency spectrum to be a target of processing. A first judging section measures the width of the peak which is the target of processing, and judges the quality of the grid based on the measured width of the peak. | 2017-05-18 |
20170140204 | BIOMETRIC TEMPLATE SECURITY AND KEY GENERATION - Methods and systems for securing biometric templates and generating secret keys are provided. One or more images are received. Interest points are identified based on the received images, and a plurality of obfuscating data points are generated based on the interest points. An obfuscated template based on the interest points and the obfuscating data points is created and stored. A secret key can be encoded using a subset of at least one of the obfuscating data points and the interest points in the template. | 2017-05-18 |
20170140205 | AUTOMATED COMPOUND STRUCTURE CHARACTERIZATION IN OVERHEAD IMAGERY - A system for automatically characterizing areas of interest (e.g., urban areas, forests, and/or other compound structures) in high resolution overhead imagery through manipulation of a dictionary of visual words. The pixels of an input overhead image are initially clustered into a plurality of hierarchically-arranged connected components of a first hierarchical data structure. Image descriptors (e.g., shape, spectral, etc.) of the connected components are then clustered into a plurality of hierarchically-arranged nodes of a second hierarchical data structure. The nodes at a particular level in the second hierarchical data structure become a dictionary of visual words. Subsets of the visual words may be used to label the cells of a grid over the geographic area as falling into one of a number of areas of interest. Categorization information from the grid may be mapped into a resultant image whereby pixels depict their respective type of area of interest. | 2017-05-18 |
20170140206 | Symbol Detection for Desired Image Reconstruction - In some implementations, a computer-implemented method includes: obtaining a captured image including, (i) a latent fingerprint to be captured, and (ii) a template, surrounding the latent fingerprint, that contains plurality of symbols; extracting, using an image processing technique, one or more characteristics for each of the plurality of symbols; calculating a resolution for the captured image based at least on the extracted one or more characteristics for each of the plurality of symbols; generating a reconstructed desired image, based at least on (i) the calculated resolution of the captured image, and (ii) the one or more extracted characteristics for each of the plurality of symbols; and providing the reconstructed desired image to a fingerprint identification system to perform a particular fingerprint operation. | 2017-05-18 |
20170140207 | Fingerprint Matching Using Virtual Minutiae - A fingerprint matching system for fingerprint matching using virtual minutiae includes a fingerprint scanning device, including (i) an interface to a fingerprint scanner, and (ii) a sensor associated with the fingerprint scanner, configured to identify a match between a search fingerprint representing a fingerprint of a subject and a reference fingerprint from among a plurality of reference fingerprints representing fingerprints of a plurality of historical subjects; a database containing the plurality of reference fingerprints representing fingerprints of the plurality of historical subjects; and a computing device in communication with said database and said fingerprint scanning device. | 2017-05-18 |
20170140208 | SYSTEM AND METHOD FOR REVIEWING AND ANALYZING CYTOLOGICAL SPECIMENS - Systems and methods are directed to computer-assisted navigation of images of a cytological specimen, including the acts of analyzing a first image of the cytological specimen to identify a plurality of objects of interest within the cytological specimen, displaying a plurality of images each comprising one of the plurality of identified objects of interest within the cytological specimen and including a second image of at least one object of interest, and displaying, responsive to receiving a user selection of the second image of the at least one object of interest, a field of view of the at least one object of interest and neighboring objects of interest, wherein the second image of the at least one object of interest has a first magnification, and wherein the field of view of the at least one object of interest is displayed at a second magnification different than the first magnification. | 2017-05-18 |
20170140209 | IMAGE RECOGNITION METHOD AND DEVICE FOR GAME - An image recognition method and device for implementing game play features of a game related to the field of image processing is disclosed. By allowing a communication device controlled by a player participating in the game to capture images and apply the image recognition features on the captured images, game play operations may be applied to other players included in the captured image within a context of the game play of the game. | 2017-05-18 |
20170140210 | IMAGE PROCESSING APPARATUS AND IMAGE PROCESSING METHOD - One of the aspects of the present invention discloses an image processing apparatus and an image processing method. The image processing apparatus comprises: an image acquisition unit configured to acquire an image containing a face; a region location unit configured to locate at least one region which represents attributes of the face in the acquired image; a feature extraction unit configured to extract features from the located regions; and a feature integration unit configured to integrate the features of the located regions which are symmetrical with each other based on symmetry of the face. According to the present invention, the dimension of the features used for image processing could be reduced and the image processing accuracy could be maintained as much as possible. | 2017-05-18 |
20170140211 | FACE COMPARISON DEVICE, METHOD, AND RECORDING MEDIUM - A face comparison device according to the present invention includes: an occluded-feature point estimation unit that estimates an occluded-feature point that is a feature point of an invisible face, and outputs position information of the occluded-feature point; a pseudo-feature point estimation unit that estimates a pseudo-feature point that is an erroneously detected feature point not captured within the input image due to occlusion, and outputs position information of the pseudo-feature point; and a comparison unit that generates a normalized image of the input image by using the position information of the occluded-feature point and the pseudo-feature point, generates a normalized image of an acquired comparison image, and compares the first facial feature vector extracted from the normalized image of the input image and the second facial feature vector extracted from the generated normalized image of the comparison image. | 2017-05-18 |
20170140212 | Facial Matching System - In some implementations, a computer-implemented method for recognizing facial images may include a multi-stage facial verification process to improve the speed and accuracy of a facial recognition operation. For example, a facial recognition module may include multiple stages where a subset of data is analyzed recursively to improve the speed of the facial recognition processes. The multiple stages may be arranged in a fast-to-slow and coarse-to-fine arrangements such that a match decision may be made at each successive stage. | 2017-05-18 |
20170140213 | RECOGNIZING UNKNOWN PERSON INSTANCES IN AN IMAGE GALLERY - Methods and systems for recognizing people in images with increased accuracy are disclosed. In particular, the methods and systems divide images into a plurality of clusters based on common characteristics of the images. The methods and systems also determine an image cluster to which an image with an unknown person instance most corresponds. One or more embodiments determine a probability that the unknown person instance is each known person instance in the image cluster using a trained cluster classifier of the image cluster. Optionally, the methods and systems determine context weights for each combination of an unknown person instance and each known person instance using a conditional random field algorithm based on a plurality of context cues associated with the unknown person instance and the known person instances. The methods and systems calculate a contextual probability based on the cluster-based probabilities and context weights to identify the unknown person instance. | 2017-05-18 |
20170140214 | SYSTEMS AND METHODS FOR DYNAMICALLY GENERATING EMOJIS BASED ON IMAGE ANALYSIS OF FACIAL FEATURES - Systems, methods, and non-transitory computer-readable media can acquire real-time image data depicting at least a portion of a face of a user of a computing system (or device). The real-time image data can be analyzed to determine a state associated with at least the portion of the face. An emoji can be provided based on the state associated with at least the portion of the face. The emoji can be inputted in a communication to be made by the user. | 2017-05-18 |
20170140215 | GESTURE RECOGNITION METHOD AND VIRTUAL REALITY DISPLAY OUTPUT DEVICE - Disclosed are a gesture recognition method for virtual reality display output device and a virtual reality display output electronic device. The recognition method includes: acquiring first and second videos from first and second cameras respectively; separating first and second plane gestures associated with first and second plane information of first and second hand graphs in the first and second video from the first and second videos respectively; converting the first plane information and the second plane information into spatial information using a binocular imaging way, and generating a spatial gesture including the spatial information; acquiring an execution instruction corresponding to the spatial gesture; and executing the execution instruction. The embodiments of the present disclosure can recognize a three-dimensional gesture using an ordinary camera, so as to greatly reduce the cost and technical risks of the virtual reality display output device. | 2017-05-18 |
20170140216 | Gesture-Based Object Measurement Method and Apparatus - In the field of man-machine interaction technologies, a gesture-based object measurement method and apparatus, which are used to improve measurement efficiency. According to this method, after image information is collected, contour information of a to-be-measured object is automatically extracted and partitioned off, and a measurement parameter value such as a length, an area, or a volume is calculated on this basis. In this way, not only real-time online measurement is implemented, a measurement process is simpler, and more convenient, visual, and effective, and augmented reality (AR) measurement efficiency can be improved, but also the measurement process is more harmonious and natural, and closer to a human intention, and a measurement result is more accurate. | 2017-05-18 |
20170140217 | SYSTEM AND METHOD FOR QUANTIFYING REFLECTION E.G. WHEN ANALYZING LAMINATED DOCUMENTS - A system for computerized authentication of a laminated object, the system comprising a digital medium storing a digital image of at least a portion of the laminated object in a computer-implemented memory; a shininess analyzer operative, using a processor, to generate shininess data quantifying shininess of the digital image; and a parameterized computerized authentication sub-system operative to differentially perform at least one laminated object authentication operation based on the shininess data. | 2017-05-18 |
20170140218 | SYSTEMS AND METHODS FOR PROVIDING QUANTITATIVE EVALUATION OF MAP QUALITY - Systems, methods, and non-transitory computer-readable media can acquire a first map that represents a particular geographical region. The first map can be associated with an image map. A first vector map can be generated based on the image map with which the first map is associated. A second map that represents the particular geographical region can be acquired. The second map can be different from the first map and can be associated with a second vector map. One or more quantitative evaluations for at least one of the first map or the second map can be provided based on the first vector map and the second vector map. | 2017-05-18 |
20170140219 | Adding Value to a Rendered Document - A system for processing data captured from rendered documents is described. The system provides a way for authors and publishers to add value to printed documents using associated supplemental material. The system can use text scanned from a document and context to identify an electronic document that corresponds to the scanned document. A user can then access supplemental material associated with the digital document. | 2017-05-18 |
20170140220 | System for Identifying a Photographic Camera Model Associated with a JPEG-Compressed Image, and Associated Method, Uses and Applications - A system and method are described for identifying a photographic camera model from a photograph taking the form of an optionally TIFF-compressed image and fulfilling a relationship between the expectation and the variance of the pixels of the image. This relationship is dependent, inter alia, on two parameters, “c” and “d”, and these two parameters determine a fingerprint characterising the camera model. The system includes an image processing device that can process the photograph to estimate parameters “c” and “d”. The system also includes a device for carrying out statistical hypothesis tests on the distribution of the pixels of the photograph and a statistical analysis device for determining if the photograph was taken by the camera model by comparing the “c” and “d” parameters obtained from the photograph and the known “c” and “d” parameters of the camera model. | 2017-05-18 |
20170140221 | DUAL FUNCTION CAMERA FOR INFRARED AND VISIBLE LIGHT WITH ELECTRICALLY-CONTROLLED FILTERS - A dual function camera is described for infrared and visible light imaging using electrically controlled filters. An example has an image sensor to image visible and infrared light, a lens system to image a scene onto the image sensor, and an electrically activated filter that selectively prevents visible light from the scene from impinging on the image sensor while capturing an infrared image. | 2017-05-18 |
20170140222 | Biometric Authentication, and Near-Eye Wearable Device - Biometric authentication can comprise: obtaining, in response to an access request, verification information for biometric authentication and a piece of depth information corresponding to a presentation depth of the verification information; presenting the verification information at the presentation depth according to the piece of depth information; acquiring gaze point depth information of an eye of a user during presentation of the verification information; and analyzing whether the gaze point depth information is consistent with the piece of depth information, to determine whether the biometric authentication succeeds. Also, verification information for biometric authentication can be presented at a depth corresponding to the verification information, and whether the biometric authentication succeeds can be determined by determining whether a gaze point depth of an eye of a user during presentation of the verification information is consistent with the depth, thereby improving accuracy of authentication and security of object access. | 2017-05-18 |
20170140223 | GAZE DETECTION DEVICE - [Problem] To reduce the size of a head-mounted display or other typical display device comprising a gaze detection device. | 2017-05-18 |
20170140224 | GAZE DETECTION DEVICE - Problem: The purpose is to reduce the size of a gaze detection device. | 2017-05-18 |
20170140225 | INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING SYSTEM - An information processing device for supporting an operation procedure in maintenance of an apparatus includes a storage unit configured to store part list information for the operation procedure in the maintenance, and part definition information for specifying a part that the apparatus has; a specification unit configured to specify a part of an operation subject to be used in the operation procedure, and a first part number that is a number of the part, based on the part list information; a capturing unit configured to generate image data of an image of the apparatus; an analyzing unit configured to specify the part of the operation subject in the image data, and a second part number that is a number of the part, based on the part definition information; and a display control unit configured to display maintenance information based on a result of comparing the first and second part numbers. | 2017-05-18 |
20170140226 | APPARATUS AND METHOD FOR IDENTIFYING A STILL IMAGE CONTAINED IN MOVING IMAGE CONTENTS - Apparatus for identifying one or more still images in one or more moving image contents. An identifying unit is configured to identify one or more still images included in the moving image contents having one or more features that closely resemble particular features. A display controller is configured to cause the display on a timeline associated with the moving image contents of the location of an identified still image in at least one of the moving image contents. | 2017-05-18 |
20170140227 | SURROUNDING ENVIRONMENT RECOGNITION DEVICE - The present invention addresses the problem of providing a surrounding environment recognition device that presents to a user a sensing-enabled range that varies depending on a contamination state of a lens. The present invention is characterized by comprising: an image-capturing unit that acquires an image; an application execution unit that executes an application for recognizing an object to be recognized from the image; a lens state diagnosis unit that diagnoses the lens state of a camera on the basis of the image; a sensing range determination unit that determines a sensing-enabled range allowing the sensing of the object to be recognized with the lens state diagnosed by the lens state diagnosis unit when the application is executed, and a sensing-disabled range not enabling the sensing of the object to be recognized; and a notification control unit that notifies the sensing-enabled range of the sensing range determination unit. | 2017-05-18 |
20170140228 | System And Method For Capturing A Rear Part Of A Vehicle - A system for a vehicle ( | 2017-05-18 |
20170140229 | EXTERNAL ENVIRONMENT RECOGNIZING DEVICE FOR VEHICLE AND VEHICLE BEHAVIOR CONTROL DEVICE - A position of a moving object is reliably detected with high accuracy using only an image around a vehicle. A rear camera mounted on a vehicle obtains an original image around the vehicle, a movement region detector detects a moving object from the original image, and a difference calculator detects the moving object from a bird's-eye view image of the vehicle generated by a bird's-eye view image processor. A moving object position identifying part identifies a position of the moving object based on a distance from the vehicle to the moving object detected by the movement region detector or the difference calculator, a lateral direction position of the moving object, and an actual width of the moving object detected by the movement region detector when a detected object determination part determines that the moving objects detected by the movement region detector and the difference calculator are the same moving object. | 2017-05-18 |
20170140230 | DRIVING ASSIST APPARATUS, DRIVING ASSIST METHOD, AND NON-TRANSITORY COMPUTER READABLE RECORDING MEDIUM STORING PROGRAM - A driving assist apparatus includes an image acquisition part to acquire a captured image around a vehicle, a position information acquisition part to acquire position information of a first object existing around the vehicle and detected by a sensor, a detection range determination part to determine a detection range of the first object within the captured image based on the position information of the first object, and an object recognition part to perform image processing on, within the captured image, an image existing in a range other than the detection range of the first object, thereby to recognize a second object that is different from the first object. Hence, a processing time taken for recognizing the second object from the captured image can be shortened. | 2017-05-18 |
20170140231 | METHOD AND SYSTEM FOR MOVING OBJECT DETECTION WITH SINGLE CAMERA - Disclosed are systems and methods for detecting moving objects. A computer-implemented method for detecting moving objects comprises obtaining a streaming video captured by a camera; extracting an input image sequence including a series of images from the streaming video; tracking point features and maintaining a set of point trajectories for at least one of the series of images; measuring a likelihood for each point trajectory to determine whether it belongs to a moving object using constraints from multi-view geometry; and determining a conditional random field (CRF) on an entire frame to obtain a moving object segmentation. | 2017-05-18 |
20170140232 | APPARATUS DETECTING DRIVING INCAPABILITY STATE OF DRIVER - An apparatus detecting driving incapability state of a driver includes: a head detection portion that detects a head of the driver based on an image of a driver's seat captured by an imaging device mounted on a vehicle; and a shake detection portion that detects the driver is incapable of driving when an amplitude of a shake of the head detected by the head detection portion is smaller than a first amplitude or larger than a second amplitude, which is larger than the first amplitude, before a shake determination time elapses after external force has been applied to the vehicle during travel of the vehicle. | 2017-05-18 |
20170140233 | METHOD AND SYSTEM FOR CALIBRATION OF A FINGERPRINT SENSING DEVICE - There is provided a method of initiating a calibration operation of a fingerprint sensing device comprising an array of sensing elements for sensing a fingerprint pattern, the method comprising acquiring information indicative of a change of an environmental parameter influencing the operation of the fingerprint sensing device; and if the change is larger than a predetermined threshold value, performing a calibration operation of the fingerprint sensing device. There is also provided a method of initiating a calibration operation of a fingerprint sensing device comprising an array of sensing elements for sensing a fingerprint pattern, the method comprising: receiving information indicative of an event in a device in which the fingerprint sensing device is arranged; if the event is one of a group of predetermined events, performing a calibration operation of the fingerprint sensing device. | 2017-05-18 |
20170140234 | IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD AND COMPUTER-READABLE STORAGE MEDIUM - According to an embodiment, an image processing apparatus includes an interface that receives a first image and a second image. A processor extracts a first character string appearing on the first image, and a second character string appearing on the second image. The processor determines that both the first character string and the second character string correspond to a photographed subject in the first image and second image. The processor cuts out each of the characters constituting the first character string, in units of a character. The processor cuts out each of the characters constituting the second character string, in units of a character. The processor calculates a first similarity degree group and a second similarity degree group. The processor recognizes a character string of the subject, based on the first similarity degree group and the second similarity degree group. | 2017-05-18 |
20170140235 | REMOTE CONTROL DEVICE BASED ON COMPUTER VISION TECHNOLOGY - Provided is a remote control device based on computer vision technology, the remote control device includes a main body and a stand base connected with the main body. The main body includes a control unit, an output unit, a power supply unit, and a switch at least partially enclosed by a case. The control unit includes a visual sensor that collects image information and a microcontroller that outputs a control instruction to a controlled device via the output unit according to the image information collected by the visual sensor. The power supply unit is configured to supply power to the control unit and the output unit. The switch is configured to control the working state of the remote control device. | 2017-05-18 |
20170140236 | UTILIZING INTERACTIVE DEEP LEARNING TO SELECT OBJECTS IN DIGITAL VISUAL MEDIA - Systems and methods are disclosed for selecting target objects within digital images. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user indicators to select targeted objects in digital images. Specifically, the disclosed systems and methods can transform user indicators into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object. | 2017-05-18 |
20170140237 | Methods For Vehicle Identification And Specification Recall With Localization Optimization For License Plate Recognition - A procedure for acquiring and utilizing vehicle license plate image data during a vehicle service or inspection process. Acquired license plate images are evaluated to identify visible license plate features including license plate characters and a license plate jurisdiction. The information is communicated to a data archive system which is configured to employ a set of jurisdiction localization rules to match a specific vehicle identification number to the license plate data. A compilation of the identified and matched data is communicated to a vehicle service system or inspection system, for utilization in a vehicle service procedure or inspection process. | 2017-05-18 |
20170140238 | METHOD AND APPARATUS FOR RECEIVING A LOCATION OF A VEHICLE SERVICE CENTER FROM AN IMAGE - Some aspects of the invention relate to a mobile apparatus including an image sensor configured to convert an optical image into an electrical signal. The optical image includes an image of a vehicle license plate. The mobile apparatus includes a license plate detector configured to process the electrical signal to recover information from the vehicle license plate image. The mobile apparatus includes an interface configured to transmit the vehicle license plate information to a remote apparatus and receive a location of a vehicle service center corresponding to the vehicle license plate image in response to the transmission. | 2017-05-18 |
20170140239 | IMAGE-PROCESSING DEVICE AND IMAGE-PROCESSING METHOD - An image processing device comprises a trail extraction section that extracts a region where pixel values continuously become a given value or more, within image data made up of a plurality of pixel values, as a trail, a trail determination section that determines movement state of the trail that has been extracted by the trail extraction section, and a trail detection section that detects type of the trail based on movement state that has been determined by the trail determination section. | 2017-05-18 |
20170140240 | NEURAL NETWORK COMBINED IMAGE AND TEXT EVALUATOR AND CLASSIFIER - Deep learning is applied to combined image and text analysis of messages that include images and text. A convolutional neural network is trained against the images and a recurrent neural network against the text. A classifier predicts human response to the message, including classifying reactions to the image, to the text, and overall to the message. Visualizations are provided of neural network analytic emphasis on parts of the images and text. Other types of media in messages can also be analyzed by a combination of specialized neural networks. | 2017-05-18 |
20170140241 | IMAGE ANALYSIS BASED COLOR SUGGESTIONS - Systems, components, devices, and methods for generating suggestions based on extracting colors from an image are provided. A non-limiting example is a method for generating suggestions for arranging content based on matching colors in an image. The method includes the step of receiving a content file. The content file includes a content region and an image. The method also includes the step of analyzing the image to identify candidate colors in the image. Additionally, the method includes the step of generating a suggestion for the content region. The suggestion includes the image and a suggested design element. The suggested design element matches one of the identified candidate colors. | 2017-05-18 |
20170140242 | USING A PROBABILISTIC MODEL FOR DETECTING AN OBJECT IN VISUAL DATA - A probabilistic model is provided based on an output of a matching procedure that matches a particular object to representations of objects, where the probabilistic model relates a probability of an object being present to a number of matching features. The probabilistic model is used for detecting whether a particular object is present in received visual data. | 2017-05-18 |
20170140243 | Detection of Stent Struts Relative to Side Branches - In part, the disclosure relates to methods of stent strut detection relative to a side branch region using intravascular data. In one embodiment, detecting stent struts relative to jailed side branches is performed using a scan line-based peak analysis. In one embodiment, false positive determinations relating to stent struts are analyzed using a model strut. | 2017-05-18 |
20170140244 | MULTI-SENSOR VISUAL ANALYTICS - This disclosure relates generally to multi-sensor visual analytics, and more particularly to method and system for multi-sensor visual analytics using machine-learning models. In one embodiment, a method for multi-sensor visual analytics includes acquiring sensor data associated with a plurality of sensors for a plurality of days of operation. A plurality of multi-dimensional histograms, having operational profiles of the plurality of sensors are computed from the sensor data. The plurality of multi-dimensional histograms are monitored, and a plurality of multi-sensor patterns are obtained from the plurality of multi-dimensional histograms. The plurality of multi-sensor patterns are indicative of one or more properties of a plurality of sensor-clusters of the plurality of sensors. One or more visual analytical tasks are performed by processing the plurality of multi-sensor patterns using at least one machine-learning model. The one or more visual models are rendered based on the processing of the multi-sensor patterns. | 2017-05-18 |
20170140245 | MOVING VEHICLE DETECTION AND ANALYSIS USING LOW RESOLUTION REMOTE SENSING IMAGERY - Disclosed is a method and system for processing images from an aerial imaging device. A moving vehicle analysis system receives images from an aerial imaging device. The system may perform edge analysis in the images to identify a pairs of edges corresponding to a road. The system may identify pixel blobs in the images including adjacent pixels matching each other based on a pixel attribute. The system uses a machine learning model for generating an output identifying moving vehicles in the images. The system determines a count of the moving vehicles captured by the images, where each moving vehicle is associated with corresponding pixel blobs. | 2017-05-18 |
20170140246 | AUTOMATIC GLANDULAR AND TUBULE DETECTION IN HISTOLOGICAL GRADING OF BREAST CANCER - Methods, systems, and apparatuses for automatically identifying glandular regions and tubule regions in a breast tissue sample are provided. An image of breast tissue is analyzed to detect nuclei and lumen candidates, identify tumor nuclei and true lumen from the candidates, and group tumor nuclei with neighboring tumor nuclei and lumina to define tubule glandular regions and non-tubule glandular regions of the image. Learnt supervised classifiers, such as random forest classifiers, can be applied to identify and classify the tumor nuclei and true lumina. Graph-cut methods can be applied to group the tumor nuclei and lumina and to define the tubule glandular regions and non-tubule glandular regions. The analysis can be applied to whole slide images and can resolve tubule areas with multiple layers of nuclei. | 2017-05-18 |
20170140247 | METHOD AND APPARATUS FOR RECOGNIZING OBJECT, AND METHOD AND APPARATUS FOR TRAINING RECOGNITION MODEL - A method and an apparatus for recognizing an object are disclosed. The apparatus may extract a plurality of features from an input image using a single recognition model and recognize an object in the input image based on the extracted features. The single recognition model may include at least one compression layer configured to compress input information and at least one decompression layer configured to decompress the compressed information to determine the features. | 2017-05-18 |
20170140248 | LEARNING IMAGE REPRESENTATION BY DISTILLING FROM MULTI-TASK NETWORKS - Embodiments of the present invention relate to learning image representation by distilling from multi-task networks. In implementation, more than one single-task network is trained with heterogeneous labels. In some embodiments, each of the single-task networks is transformed into a Siamese structure with three branches of sub-networks so that a common triplet ranking loss can be applied to each branch. A distilling network is trained that approximates the single-task networks on a common ranking task. In some embodiments, the distilling network is a Siamese network whose ranking function is optimized to approximate an ensemble ranking of each of the single-task networks. The distilling network can be utilized to predict tags to associate with a test image or identify similar images to the test image. | 2017-05-18 |
20170140249 | VISUAL REPRESENTATIONS OF PHOTO ALBUMS - Systems and methods for selecting representative photos for a photo album are described. An example computing device may include a display, a logic device, and a storage device storing instructions executable by the logic device to, for each known individual recognized in one or more photos of the album, determine an affinity score for that known individual indicating a connection of that known individual to a) a user of the computing device and b) a context corresponding to the album. The instructions may be further executable to select one or more known individuals based on the affinity score to be included in a subset of the known individuals recognized in one or more photos of the album, and select a representative photo of each of the subset of the known individuals to be included in one or more of a highlight photoset and a cover photo for the album. | 2017-05-18 |
20170140250 | CONTENT FILE IMAGE ANALYSIS - Systems, components, devices, and methods for understanding the content of an image are provided. A non-limiting example is a method for generating suggestions for arranging content based on understanding the contents of an image. The method includes the step of receiving a content file that includes a content region and an image. The method also includes the steps of generating a statistical analysis of the image and calculating a score based on the statistical analysis. The method also includes the step of classifying the image based on comparing the score to a threshold value. Additionally, the method includes the step of generating a suggestion for arranging the content region based on the classification of the image. | 2017-05-18 |
20170140251 | IMAGE PROCESSING DEVICE - Provided is an image processing device for sorting frames included in one moving image into different channels, the frames included in the moving image being a mixture of frames belonging to the different channels. The image processing device includes an automatic sorting unit and a re-sorting unit. The automatic sorting unit calculates a similarity degree of the plurality of frames included in the moving image by performing image processing on the frames, and sorts the plurality of frames into the plurality of channels based on the similarity degree. The re-sorting unit accepts, from a user, an association operation of individually associating at least one non-sorted frame, which is not automatically sorted by the automatic sorting unit, with any of the plurality of channels, and individually sorts the non-sorted frame to any of the plurality of channels based on content of the association operation. | 2017-05-18 |
20170140252 | COMPUTERIZED, PERSONAL-SCENT ANALYSIS SYTEM - A method and apparatus to automatically generate a customized scent profile receives data corresponding to several physical attributes of a living subject, such as hair, skin and eyes and conducts an analysis uniquely corresponding to each attribute, and may associate each attribute with at least one property such as a color family, a technical identifier, an intensifier, a temperature, a power color, and a saturation designation. Software may identify the color linked to each attribute by, for example, an LAB value, an RGB value, an HTML value, an XYZ value or a CMY value, or a HEX value while an intensifier may be a contrasting color, and saturation may indicate whether the color linked to the attribute is a tone, tint, shade or hue. A scent profile uniquely compatible with the subject may be presented by print media, monitor, printer, cell phone, personal digital assistant, or the like. | 2017-05-18 |
20170140253 | MULTI-LAYER FUSION IN A CONVOLUTIONAL NEURAL NETWORK FOR IMAGE CLASSIFICATION - A method and system for domain adaptation based on multi-layer fusion in a convolutional neural network architecture for feature extraction and a two-step training and fine-tuning scheme. The architecture concatenates features extracted at different depths of the network to form a fully connected layer before the classification step. First, the network is trained with a large set of images from a source domain as a feature extractor. Second, for each new domain (including the source domain), the classification step is fine-tuned with images collected from the corresponding site. The features from different depths are concatenated with and fine-tuned with weights adjusted for a specific task. The architecture is used for classifying high occupancy vehicle images. | 2017-05-18 |
20170140254 | METHOD AND DEVICE FOR ADDING FONT - The present disclosure provides a method and a device for adding a font. The method includes: acquiring an image; recognizing text in the image as at least one character, each character being a font file corresponding to a single word or a single symbol; and adding a recognized character to a system font library, the system font library including characters used for displaying text on a user interface. | 2017-05-18 |
20170140255 | METHOD FOR PRINTING ON A STATIONARY FLAT MEDIA USING A PORTABLE LARGE FORMAT PRINTER - A method for operating a portable large format inkjet printer includes determining an output image size of an output image to be printed on a stationary flat media; selecting a source image to serve as the output image; displaying a preview of the output image superposed with an output image grid defining a plurality of output image area portions; selecting a serial order of printing each of the output image area portions; selecting a next output image area portion based on the serial order; printing the selected next output image area portion at a media print area of the stationary flat media; and repeating the acts of selecting the next output image area portion and printing, for each of the plurality of output image area portions, until an entirety of the output image area has been printed at the media print area of the stationary flat media. | 2017-05-18 |
20170140256 | IC TAG UNIT FOR INSTRUMENT, AND INSTRUMENT WITH IC TAG - An IC tag unit, for an instrument, which allows an IC tag into and from which instrument information, calibration information, inspection information, and the like can be written and read to be mounted to an instrument without affecting the IC tag by a metal portion of an instrument body, hindering visibility of a scale of the instrument, and further causing degradation due to dust, raindrops, or the like, and an instrument with the IC tag, are provided. An IC tag | 2017-05-18 |
20170140257 | DUAL-INTERFACE IC CARD - The disclosure relates to a dual-interface integrated circuit (IC) card. Embodiments disclosed include a dual-interface card ( | 2017-05-18 |
20170140258 | POST APPLICATION EDITING OF MULTIRESONATOR CHIPLESS RADIO FREQUENCY IDENTIFICATION (RFID) - A method and structure for a radio frequency identification (RFID) system including an RFID tag. The RFID tag can include a dampener configured to dampen a resonation of a resonator. Prior to dampening the resonation of the resonator using the dampener, the RFID tag may be configured to transmit a first response signal from a transmit antenna. Subsequent to dampening of the resonation of the resonator using the dampener, the RFID tag may be configured to transmit a second response signal that is different from the first response signal. The dampener may include a chemical agent or a fusible link. | 2017-05-18 |
20170140259 | SYSTEMS, DEVICES, AND METHODS FOR DISTRIBUTED ARTIFICIAL NEURAL NETWORK COMPUTATION - Robots and robotic systems and methods can employ artificial neural networks (ANNs) to significantly improve performance. The ANNs can operate alternatingly in forward and backward directions in interleaved fashion. The ANNs can employ visible units and hidden units. Various objective functions can be optimized. Robots and robotic systems and methods can execute applications including a plurality of agents in a distributed system, for instance with a number of hosts executing respective agents, at least some of the agents in communications with one another. The hosts can execute agents in response to occurrence of defined events or trigger expressions, and can operate with a maximum latency guarantee and/or data quality guarantee. | 2017-05-18 |
20170140260 | CONTENT FILTERING WITH CONVOLUTIONAL NEURAL NETWORKS - Systems and techniques are provided for content filtering with convolutional neural networks. A spectrogram generated from audio data may be received. A convolution may be applied to the spectrogram to generate a feature map. Values for a hidden layer of a neural network may be determined based on the feature map. A label for the audio data may be determined based on the determined values for the hidden layer of the neural network. The hidden layer may include a vector including the values for the hidden layer. The vector may be stored as a vector representation of the audio data. | 2017-05-18 |
20170140261 | SYSTEMS, METHODS AND COMPUTER PRODUCTS FOR DETERMINING AN ACTIVITY - Media content is recommended based on suitability for a designated activity. A vector engine is trained using a plurality of lists, each of the lists containing metadata associated with a plurality of media objects. The vector engine includes a neural network trained with corpus data including (i) the plurality of lists (ii) a plurality of titles, each one of the titles associated with one of the lists, and (iii) the metadata associated with the plurality of media objects. Training the vector engine involves initializing, using the vector engine, a plurality of feature vectors representing each of the lists, each of the media objects, and each of a plurality of words in the titles of the lists. The training then further involves nudging, using the vector engine, the feature vectors based on a plurality of co-occurrences of the lists, the media objects, the words in the titles of the lists, or a combination thereof. A feature vector corresponding to an activity is identified among the feature vectors. At least one of the media objects, (ii) at least one of lists or (iii) a combination thereof suitable for the activity is selected based on cosine similarities between the feature vector corresponding to the activity and others of the feature vectors. | 2017-05-18 |
20170140262 | SYSTEMS AND METHODS FOR PROVIDING RECOMMENDATIONS BASED ON COLLABORATIVE AND/OR CONTENT-BASED NODAL INTERRELATIONSHIPS - In selected embodiments a recommendation generator builds a network of interrelationships between venues, reviewers and users based on attributes and reviewer and user reviews of the venues. Each interrelationship or link may be positive or negative and may accumulate with other links (or anti-links) to provide nodal links the strength of which are based on commonality of attributes among the linked nodes and/or common preferences that one node, such as a reviewer, expresses for other nodes, such as venues. The links may be first order (based on a direct relationship between, for instance, a reviewer and a venue) or higher order (based on, for instance, the fact that two venue are both liked by a given reviewer). The recommendation engine in certain embodiments determines recommended venues based on user attributes and venue preferences by aggregating the link matrices and determining the venues which are most strongly coupled to the user. | 2017-05-18 |
20170140263 | CONVOLUTIONAL GATED RECURRENT NEURAL NETWORKS - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing a convolutional gated recurrent neural network (CGRN). In one of the systems, the CGRN is configured to maintain a state that is a tensor having dimensions x by y by m, wherein x, y, and m are each greater than one, and for each of a plurality of time steps, update a currently maintained state by processing the currently maintained state through a plurality of convolutional gates. | 2017-05-18 |
20170140264 | NEURAL RANDOM ACCESS MACHINE - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a system output from a system input. In one aspect, a neural network system includes a memory storing a set of register vectors and data defining modules, wherein each module is a respective function that takes as input one or more first vectors and outputs a second vector. The system also includes a controller neural network configured to receive a neural network input for each time step and process the neural network input to generate a neural network output. The system further includes a subsystem configured to determine inputs to each of the modules, process the input to the module to generate a respective module output, determine updated values for the register vectors, and generate a neural network input for the next time step from the updated values of the register vectors. | 2017-05-18 |
20170140265 | NEURAL NETWORK PROGRAMMER - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing operations using data from a data source. In one aspect, a method includes a neural network system including a controller neural network configured to: receive a controller input for a time step and process the controller input and a representation of a system input to generate: an operation score distribution that assigns a respective operation score to an operation and a data score distribution that assigns a respective data score in the data source. The neural network system can also include an operation subsystem configured to: perform operations to generate operation outputs, wherein at least one of the operations is performed on data in the data source, and combine the operation outputs in accordance with the operation score distribution and the data score distribution to generate a time step output for the time step. | 2017-05-18 |
20170140266 | DUELING DEEP NEURAL NETWORKS - Systems, methods, and apparatus, including computer programs encoded on a computer storage medium, for selecting an actions from a set of actions to be performed by an agent interacting with an environment. In one aspect, the system includes a dueling deep neural network. The dueling deep neural network includes a value subnetwork, an advantage subnetwork, and a combining layer. The value subnetwork processes a representation of an observation to generate a value estimate. The advantage subnetwork processes the representation of the observation to generate an advantage estimate for each action in the set of actions. The combining layer combines the value estimate and the respective advantage estimate for each action to generate a respective Q value for the action. The system selects an action to be performed by the agent in response to the observation using the respective Q values for the actions in the set of actions. | 2017-05-18 |
20170140267 | STRUCTURAL DESCRIPTIONS FOR NEUROSYNAPTIC NETWORKS - Embodiments of the invention provide a method comprising creating a structural description for at least one neurosynaptic core circuit. Each core circuit comprises an interconnect network including plural electronic synapses for interconnecting one or more electronic neurons with one or more electronic axons. The structural description defines a desired neuronal activity for the core circuits. The desired neuronal activity is simulated by programming the core circuits with the structural description. The structural description controls routing of neuronal firing events for the core circuits. | 2017-05-18 |
20170140268 | TRAINING NEURAL NETWORKS USING NORMALIZED TARGET OUTPUTS - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using normalized target outputs. One of the methods includes updating current values of the normalization parameters to account for the target output for the training item; determining a normalized target output for the training item by normalizing the target output for the training item in accordance with the updated normalization parameter values; processing the training item using the neural network to generate a normalized output for the training item in accordance with current values of main parameters of the neural network; determining an error for the training item using the normalized target output and the normalized output; and using the error to adjust the current values of the main parameters of the neural network. | 2017-05-18 |
20170140269 | TRAINING NEURAL NETWORKS USING A PRIORITIZED EXPERIENCE MEMORY - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network used to select actions performed by a reinforcement learning agent interacting with an environment. In one aspect, a method includes maintaining a replay memory, where the replay memory stores pieces of experience data generated as a result of the reinforcement learning agent interacting with the environment. Each piece of experience data is associated with a respective expected learning progress measure that is a measure of an expected amount of progress made in the training of the neural network if the neural network is trained on the piece of experience data. The method further includes selecting a piece of experience data from the replay memory by prioritizing for selection pieces of experience data having relatively higher expected learning progress measures and training the neural network on the selected piece of experience data. | 2017-05-18 |
20170140270 | ASYNCHRONOUS DEEP REINFORCEMENT LEARNING - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for asynchronous deep reinforcement learning. One of the systems includes a plurality of workers, wherein each worker is configured to operate independently of each other worker, and wherein each worker is associated with a respective actor that interacts with a respective replica of the environment during the training of the deep neural network. | 2017-05-18 |
20170140271 | NEURAL PROGRAMMING - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural programming. One of the methods includes processing a current neural network input using a core recurrent neural network to generate a neural network output; determining, from the neural network output, whether or not to end a currently invoked program and to return to a calling program from the set of programs; determining, from the neural network output, a next program to be called; determining, from the neural network output, contents of arguments to the next program to be called; receiving a representation of a current state of the environment; and generating a next neural network input from an embedding for the next program to be called and the representation of the current state of the environment. | 2017-05-18 |
20170140272 | GENERATING LARGER NEURAL NETWORKS - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a larger neural network from a smaller neural network. In one aspect, a method includes obtaining data specifying an original neural network; generating a larger neural network from the original neural network, wherein the larger neural network has a larger neural network structure including the plurality of original neural network units and a plurality of additional neural network units not in the original neural network structure; initializing values of the parameters of the original neural network units and the additional neural network units so that the larger neural network generates the same outputs from the same inputs as the original neural network; and training the larger neural network to determine trained values of the parameters of the original neural network units and the additional neural network units from the initialized values. | 2017-05-18 |
20170140273 | SYSTEM AND METHOD FOR AUTOMATIC SELECTION OF DEEP LEARNING ARCHITECTURE - A system and method of determining a neural network configuration may include receiving at least one neural network configuration, altering the received configuration for at least two iterations, calculating a first parameter of an altered configuration, calculating a second parameter of a consecutive altered configuration of the at least two iterations, comparing values of the calculated first parameter and second parameter, and determining a configuration having largest value of the calculated parameters. | 2017-05-18 |
20170140274 | SPECULATIVE ASYNCHRONOUS SUB-POPULATION EVOLUTIONARY COMPUTING - A tool computes fitness values for a first generation of a first sub-population of a plurality of sub-populations. A population of candidate solutions for an optimization problem was previously divided into the plurality of sub-populations. The population of candidate solutions was created for an iterative computing process in accordance with an evolutionary algorithm to identify a most fit candidate solution for the optimization problem. The tool determines a speculative ranking of the first generation of the first sub-population prior to the fitness values being computed for all candidate solutions in the first generation of the first sub-population. The tool generates a next generation of the first sub-population based, at least in part, on the speculative ranking prior to completion of computation of the fitness values for the first generation of the first sub-population. | 2017-05-18 |
20170140275 | System for Refining Cognitive Insights Using Cognitive Graph Vectors - A method, system and computer-usable medium for using cognitive graph vectors to refine cognitive insights comprising storing data from a plurality of data sources within a cognitive graph via a cognitive inference and learning system; associating a first set of the data within the cognitive graph with a first cognitive graph vector of a plurality of cognitive graph vectors via the cognitive inference and learning system; associating a second set of the data within the cognitive graph with a second cognitive graph vector of the plurality of cognitive graph vectors via the cognitive inference and learning system; processing the data from the plurality of data sources to provide cognitive insights via the cognitive inference and learning system; and refining the cognitive insights based upon a limitation relating to one of the plurality of cognitive graph vectors via the cognitive inference and learning system. | 2017-05-18 |
20170140276 | SYSTEM, METHOD, AND RECORDING MEDIUM FOR MODELING A CORRELATION AND A CAUSATION LINK OF HIDDEN EVIDENCE - A method, system, and non-transitory compute readable medium for hidden evidence correlation and causation linking including computing a correlation link based on hidden evidence found in relation to a user input in hidden cycle measurements, forecasting the hidden evidence into future forecasted cycle measurements, and computing a causation link based on the future forecasted cycle measurements. | 2017-05-18 |
20170140277 | COMPUTER-IMPLEMENTED COGNITIVE SYSTEM FOR ASSESSING SUBJECTIVE QUESTION-ANSWERS - A cognitive system that automatically assesses subjective answers may be provided. A cognitive engine executing on one or more processors may determine whether a statement parsed from a subjective answer by natural language processing technique is accurate or inaccurate, for each of the plurality of statements based on matching the statement with information associated with a domain of a question from a plurality of data sources, according to an accuracy threshold. An overall assessment of the answer may be automatically determined based on a number of statements determined to be accurate, a number of statements determined to be inaccurate, a number of duplicate statements in the answer relative to a total number of statements in the answer. A visual graphics representing accurate and inaccurate statements may be presented or displayed, allowing a user to interact with the visual graphics to modify the assessment. | 2017-05-18 |
20170140278 | USING MACHINE LEARNING TO PREDICT BIG DATA ENVIRONMENT PERFORMANCE - A method includes performing operations as follows on a processor: receiving a big data dataset comprising new active data, receiving a request to predict a level of performance with respect to a performance parameter of a data processing system in analyzing the new active data, selecting a machine learning algorithm from a plurality of machine learning algorithms based on the performance parameter to obtain a selected machine learning algorithm, selecting a group of historical metadata from a plurality of groups of historical metadata of datasets that have previously been analyzed using the data processing system to provide a selected group of historical metadata, applying the selected machine learning algorithm to the selected group of historical metadata to generate a model of the selected group of historical metadata, obtaining metadata of the new active data, applying the model to the metadata of the new active data to generate a prediction of the level of performance with respect to the performance parameter; and configuring the data processing system for analyzing the new active data based on the prediction. | 2017-05-18 |
20170140279 | SYSTEM, DEVICE, AND METHOD OF DETECTING USER IDENTITY BASED ON MOTOR-CONTROL LOOP MODEL - Device, system, and method of detecting identity of a user based on motor-control loop model. A method includes: during a first session of a user who utilizes a pointing device for interacting with a computerized service, monitoring the pointing device dynamics and gestures of the user; based on the monitored dynamics and gestures, estimating parameters that characterize a sensorimotor control loop model of the user; storing in a database a record indicating that the user is associated with the parameters that characterize the sensorimotor control loop model of the user. | 2017-05-18 |
20170140280 | PREDICTIVE CUSTOMER SERVICE ENVIRONMENT - A mechanism for facilitating customer interactions within a customer service environment provides prompt and accurate answers to customer questions. A smart chat facility for use in a customer service environment to predict a customer problem examines a customer chat transcript to identify customer statements that set forth a customer issue and, responsive to this, can route the customer to an agent, an appropriate FAQ, or can implement a problem specific widget in the customer UI. Customer queries are matched with most correct responses and accumulated knowledge is used to predict a best response to future customer queries. The iterative system thus learns from each customer interaction and can adapt to customer responses over time to improve the accuracy of problem prediction. | 2017-05-18 |
20170140281 | IDENTIFYING, FOR A SET OF DECISION RULES, ONE OR MORE DECISION RULES MISSING FROM THE SET OF DECISION RULES - Aspects include identifying, for a set of decision rules, one or more decision rules missing from the set of decision rules, the one or more missing decision rules satisfying a set of limitations. A decision rule determines whether a decision is made for a case, and a limitation determines the cases for which a decision should be made. A constraint graph that represents the cases for which no rule of the set of rules makes a decision, and for which all limitations of the set of limitations are satisfied, is built. A missing case represented by the constraint graph is created, and a family description is created from the missing case. The family description is a set of cases for which no rule of the set of rules makes a decision. The one or more missing decision rules are then constructed from the family description. | 2017-05-18 |
20170140282 | Very Short-Term Air Pollution Forecasting - A mechanism is provided for forecasting air pollution. One or more air-pollution monitoring stations correlated to a forecasting point from a plurality of air-pollution monitoring stations are identified. For the one or more air-pollution monitoring stations that correlate to the forecasting point, one or more patterns of the forecasting point, historical patterns of the forecasting point relating to the one or more patterns of the forecasting point, and one or more patterns of the air-pollution monitoring stations that relate to the one or more patterns of the forecasting point are identified. Based on the one or more patterns of the forecasting point, the historical patterns of the forecasting point relating to the one or more patterns of the forecasting point, and the one or more patterns of the air-pollution monitoring stations that relate to the one or more patterns of the forecasting point, a pollution forecast is provided. | 2017-05-18 |
20170140283 | LOOKALIKE EVALUATION - Lookalike models can select users that are predicted to share characteristics with a specified set of seed users. The processing requirements for lookalike models can be decreased by identifying features that have low impact on model accuracy, and therefore can be excluded from creating models. Also, by identifying preferred seed sources and training parameters, accurate lookalike models can be created with less overhead and in less time. The features and training parameters can be identified by obtaining a sample seed set, extracting seeds with a defined set of features, and using the remaining training seeds to train a model. Performance of this model can be compared to a standard model to see if the model performs well. If so, features excluded from the features used to create the model, a seed source, or training parameters used to create the model can be selected. | 2017-05-18 |
20170140284 | COMPUTER-IMPLEMENTED SYSTEMS UTILIZING SENSOR NETWORKS FOR SENSING TEMPERATURE AND MOTION ENVIRONMENTAL PARAMETERS; AND METHODS OF USE THEREOF - Computer-implemented systems utilizing sensor networks for sensing temperature and motion environmental parameters, and performing at least operations of electronically establishing, based on pattern recognition criteria, correspondence of a plurality of representative features a plurality of characteristics of an occurrence, where a first instance of the occurrence occurred within a first time period of a plurality of time periods; electronically discovering, based on the correspondence, a second instance of the occurrence in an environment during a second time period of the plurality of time periods; and electronically causing, based on the discovery of the second instance of the occurrence, a change in the environment via an electronically-controlled device. | 2017-05-18 |
20170140285 | Enhanced Computer Experience From Activity Prediction - A user activity pattern may be ascertained using signal data from a set of computing devices. The activity pattern may be used to infer user intent with regards to a user interaction with a computing device or to predict a likely future action by the user. In one implementation, a set of computing devices is monitored to detect user activities using sensors associated with the computing devices. Activity features associated with the detected user activities are determined and used to identify an activity pattern based on a plurality of user activities having similar features. Examples of user activity patterns may include patterns based on time, location, content, or other context. The inferred user intent or predicted future actions may be used to provide improved user experiences, such as personalization, modifying functionality of user devices, or providing more efficient consumption of bandwidth or power. | 2017-05-18 |