With Pattern Recognition Or Classification Patents (Class 382/170)
  • Patent number: 10387482
    Abstract: The overall architecture and details of a scalable video fingerprinting and identification system that is robust with respect to many classes of video distortions is described. In this system, a fingerprint for a piece of multimedia content is composed of a number of compact signatures, along with traversal hash signatures and associated metadata. Numerical descriptors are generated for features found in a multimedia clip, signatures are generated from these descriptors, and a reference signature database is constructed from these signatures. Query signatures are also generated for a query multimedia clip. These query signatures are searched against the reference database using a fast similarity search procedure, to produce a candidate list of matching signatures. This candidate list is further analyzed to find the most likely reference matches. Signature correlation is performed between the likely reference matches and the query clip to improve detection accuracy.
    Type: Grant
    Filed: April 18, 2019
    Date of Patent: August 20, 2019
    Assignee: Gracenote, Inc.
    Inventors: Prashant Ramanathan, Mihailo M. Stojancic
  • Patent number: 10375947
    Abstract: One example insect sensing system includes a light emitter configured to emit light; a structured light generator positioned to receive the emitted light and configured to generate structured light from the emitted light; a plurality of light sensors arranged in a line, each of the light sensors oriented to receive at least a portion of the structured light and output a sensor signal indicating an amount of light received by the respective light sensor; a processing device configured to: obtain the sensor signals from each of the light sensors, and determine a presence of an insect based a received sensor signal from at least one light sensor, the sensor signal indicating a reduced amount of received light by the at least one light sensor. Another example insect sensing system includes a camera comprising an image sensor and a lens having an aperture of f/2.8 or wider; and a processor configured to obtain an image from the camera and detect an insect in the image.
    Type: Grant
    Filed: October 18, 2017
    Date of Patent: August 13, 2019
    Assignee: VERILY LIFE SCIENCES LLC
    Inventors: Jianyi Liu, Peter Massaro
  • Patent number: 10382373
    Abstract: Systems, devices, methods, media, and instructions for automated image processing and content curation are described. In one embodiment a server computer system receives a content message from a first content source, and analyzes the content message to determine one or more quality scores and one or more content values associated with the content message. The server computer system analyzes the content message with a plurality of content collections of the database to identify a match between at least one of the one or more content values and a topic associated with at least a first content collection of the one or more content collections and automatically adds the content message to the first content collection based at least in part on the match. In various embodiments, different content values, image processing operations, and content selection operations are used to curate content collections.
    Type: Grant
    Filed: August 31, 2016
    Date of Patent: August 13, 2019
    Assignee: Snap Inc.
    Inventors: Jianchao Yang, Yuke Zhu, Ning Xu, Kevin Dechau Tang, Jia Li
  • Patent number: 10380461
    Abstract: Approaches introduce a pre-processing and post-processing framework to a neural network-based approach to identify items represented in an image. For example, a classifier that is trained on several categories can be provided. An image that includes a representation of an item of interest is obtained. Rotated versions of the image are generated and each of a subset of the rotated images is analyzed to determine a probability that a respective image includes an instance of a particular category. The probabilities can be used to determine a probability distribution of output category data, and the data can be analyzed to select an image of the rotated versions of the image. Thereafter, a categorization tree can then be utilized, whereby for the item of interest represented the image, the category of the item can be determined. The determined category can be provided to an item retrieval algorithm to determine primary content for the item of interest.
    Type: Grant
    Filed: October 20, 2017
    Date of Patent: August 13, 2019
    Assignee: A9.COM, INC.
    Inventors: Avinash Aghoram Ravichandran, Matias Omar Gregorio Benitez, Rahul Bhotika, Scott Daniel Helmer, Anshul Kumar Jain, Junxiong Jia, Rakesh Madhavan Nambiar, Oleg Rybakov
  • Patent number: 10373073
    Abstract: A computer implemented method of automatically creating a classification function trained with augmented representation of features extracted from a plurality of sample media objects using one or more hardware processors for executing a code. The code comprises code instructions for extracting a plurality of features from a plurality of sample media objects, generating a plurality of feature samples for each of the plurality of features by augmenting the plurality of features, training a classification function with the plurality of features samples and outputting the classification function for classifying one or more new media objects.
    Type: Grant
    Filed: January 11, 2016
    Date of Patent: August 6, 2019
    Assignee: International Business Machines Corporation
    Inventor: Pavel Kisilev
  • Patent number: 10354143
    Abstract: A method (100) for comparing a first video shot (Vs1) comprising a first set of first images (I1(s)) with a second video shot (Vs2) comprising a second set of second images (I2(t)), at least one between the first and the second set comprising at least two images.
    Type: Grant
    Filed: October 13, 2014
    Date of Patent: July 16, 2019
    Assignee: TELECOM ITALIA S.p.A.
    Inventors: Skjalg Lepsoy, Massimo Balestri, Gianluca Francini
  • Patent number: 10346684
    Abstract: Various embodiments provide a method for computing color descriptors of product images. For example, a number of fine color representatives can be determined to describe color variation in an image as a histogram by assigning a saturation value and a brightness value to a plurality of color hues. For each pixel of the image, the closest color among a defined fine color representative set is computed. In this example, each of the pixels is assigned a color ID corresponding to their closest matching fine color representative and at least one family color ID corresponding one or more pure color families. In this example, a histogram of the color representatives and a histogram for the color families are computed. A single color vector descriptor for the image is then determined by combining the family histogram with the color representative histogram.
    Type: Grant
    Filed: June 9, 2017
    Date of Patent: July 9, 2019
    Assignee: A9.COM, INC.
    Inventors: Arnab Sanat Kumar Dhua, Himanshu Arora, Sunil Ramesh
  • Patent number: 10331970
    Abstract: Techniques are provided that include identifying robust features within a training image. Training features are generated by applying a feature detection algorithm to the training image, each training feature having a training feature location within the training image. At least a portion of the training image is transformed into a transformed image in accordance with a predefined image transformation. Transform features are generated by applying the feature detection algorithm to the transformed image, each transform feature having a transform feature location within the transformed image.
    Type: Grant
    Filed: December 14, 2016
    Date of Patent: June 25, 2019
    Assignee: Nant Holdings IP, LLC
    Inventors: Bing Song, Liwen Lin, Mustafa Jaber
  • Patent number: 10318891
    Abstract: A method includes receiving geometric data to be encoded, generating a signature for the geometric data based on the at least one property associated with the geometric data, enumerating a first set of options, enumerating a second set of options, encoding the geometric data using the first option and the second option, decoding the encoded geometric data, determining a performance associated with encoding the geometric data, determining a performance associated with decoding the encoded geometric data, and training a regressor based on the signature, the enumerated first option, the enumerated second option, the performance associated with encoding the geometric data and the performance associated with decoding the encoded geometric data.
    Type: Grant
    Filed: July 23, 2018
    Date of Patent: June 11, 2019
    Assignee: GOOGLE LLC
    Inventors: Michael Hemmer, Igor Vytyaz, Ameesh Makadia, Leopoldo Taravilse Diez
  • Patent number: 10304002
    Abstract: Human Computer Interfaces (HCI) may allow a user to interact with a computer via a variety of mechanisms, such as hand, head, and body gestures. Various of the disclosed embodiments allow information captured from a depth camera on an HCI system to be used to recognize such gestures. Particularly, the HCI system's depth sensor may capture depth frames of the user's movements over time. To discern gestures from these movements, the system may group portions of the user's anatomy represented by the depth data into classes. “Features” which reflect distinguishing features of the user's anatomy may be used to accomplish this classification. Some embodiments provide improved systems and methods for generating and/or selecting these features. Features prepared by various of the disclosed embodiments may be less susceptible to overfitting training data and may more quickly distinguish portions of the user's anatomy.
    Type: Grant
    Filed: February 8, 2016
    Date of Patent: May 28, 2019
    Assignee: YouSpace, Inc.
    Inventor: Ralph Brunner
  • Patent number: 10264193
    Abstract: Apparatuses, computer readable media, and methods are disclosed for providing composite images and/or videos having a high dynamic range. The apparatus includes a video capture module for capturing video images of a scene at a differing exposure levels. The apparatus further includes a region identification module for identifying regions in the captured video images of the scene that may benefit from being individually optimally-exposed. The apparatus further includes a region adjustment module for updating the positions of the various identified regions within the scene and a region exposure adjustment module for determining optimal exposure settings for the various identified regions of the scene. A video subsystem composites and encodes the various optimally-exposed regions of the scene onto a video image of a static portion of the scene having a high dynamic range that was, e.g., captured at a different moment in time than the various optimally-exposed regions of the scene.
    Type: Grant
    Filed: December 6, 2016
    Date of Patent: April 16, 2019
    Assignee: Polycom, Inc.
    Inventor: Stephen Schaefer
  • Patent number: 10217002
    Abstract: Aspects relate to methods, systems, and devices for monitoring unmanned vehicles. Methods include receiving, by a processor, a captured image of an observed unmanned vehicle, the captured image including measured data, comparing the measured data with an unmanned vehicle database, determining a status of the observed unmanned vehicle, and generating an indicator regarding the status of the observed unmanned vehicle.
    Type: Grant
    Filed: August 4, 2016
    Date of Patent: February 26, 2019
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Yuk L. Chan, Kyle E. Gilberston, Daniel F. Hogerty, Eileen P. Tedesco
  • Patent number: 10212407
    Abstract: An apparatus for reducing the visibility of disparity estimation errors at edges, and in particular at overlays. The apparatus comprises a receiver (401) for receiving a three dimensional image represented by at least image values (brightness/contrast values) and a disparity value. A subset selector (403) evaluates an image property criterion for the image value for a group of pixels and determines a subset of pixels of the group of pixels for which the image property criterion is met. The criterion may for example reflect whether the pixel belongs to an image object edge. A distribution evaluator (405) generates a frequency distribution for disparity values of the subset of pixels and an analyzer (407) determines a shape property for the frequency distribution (the presence of a peak). An adaptor (409) determining a disparity remapping in response to the shape property and a remapper (411) modifies disparity values of the three dimensional image by applying the disparity remapping. The approach may e.g.
    Type: Grant
    Filed: September 24, 2015
    Date of Patent: February 19, 2019
    Assignee: Koninklijke Philips N.V.
    Inventors: Christiaan Varekamp, Patrick Luc Els Vandewalle
  • Patent number: 10204216
    Abstract: According to various embodiments, a verification method may be provided. The verification method may include: determining a plurality of objects, each object having a property; displaying a representation of each object of the plurality of objects; receiving from a user an input indicating a sequence of the plurality of objects; determining a sequence of the properties of the plurality of objects; and comparing the Determine a plurality of objects, each object having a input with the sequence of the properties of the objects.
    Type: Grant
    Filed: February 24, 2015
    Date of Patent: February 12, 2019
    Assignee: SINGAPORE UNIVERSITY OF TECHNOLOGY AND DESIGN
    Inventors: Hossein Nejati, Ngai-Man Cheung, Dawn C. I. Koh, Ricardo D. Sosa Medina
  • Patent number: 10188791
    Abstract: A system for confirmation of fluid delivery to a patient at the clinical point of use is provided. The system includes a wearable electronic device. The wearable electronic device has a housing; at least one imaging sensor associated with the housing; a data transmission interface; a data reporting accessory for providing data to the user; a microprocessor for managing the at least one imaging sensor, the data transmission interface, and the data reporting accessory; and a program for acquiring and processing images from the at least one imaging sensor. The system further includes a fluid delivery apparatus; and one or more identification tags attached to or integrally formed with the fluid delivery apparatus. The program processes an image captured by the at least one imaging sensor to identify the one or more identification tags and acquires fluid delivery apparatus information from the one or more identification tags.
    Type: Grant
    Filed: January 29, 2015
    Date of Patent: January 29, 2019
    Assignee: Becton, Dickinson and Company
    Inventors: Jonathan Karl Burkholz, Jeff O'Bryan
  • Patent number: 10185877
    Abstract: Processes, systems, and devices for occlusion detection for video-based object tracking (VBOT) are described herein. Embodiments process video frames to compute histogram data and depth level data for the object to detect a subset of video frames for occlusion events and generate output data that identifies each video frame of the subset of video frames for the occlusion events. Threshold measurement values are used to attempt to reduce or eliminate false positives to increase processing efficiency.
    Type: Grant
    Filed: July 8, 2016
    Date of Patent: January 22, 2019
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Reza Pournaghi, Rui Zhang
  • Patent number: 10169570
    Abstract: A method for determining a password strength is provided. The method may include receiving a user-entered password. The method may also include identifying a keyboard layout type associated with a keyboard utilized to enter the received user-entered password. The method may further include mapping each character within a plurality of characters in the received user-entered password to a corresponding location on a grid associated with the identified keyboard layout type. The method may also include determining a coordinate sequence associated with the received user-entered password based on the mapped plurality of characters. The method may further include applying a pattern recognition algorithm to the determined coordinate sequence. The method may also include determining a password strength based on the applied pattern recognition algorithm.
    Type: Grant
    Filed: November 17, 2017
    Date of Patent: January 1, 2019
    Assignee: International Business Machines Corporation
    Inventors: Itzhack Goldberg, Harry R. McGregor, Christopher B. Moore, Shawn P. Mullen, Neil Sondhi
  • Patent number: 10140738
    Abstract: One embodiment provides a system for facilitating visualization of input data classifications. The system obtains, from a remote computer system, output data which includes a classification and a score that a corresponding set of input data belongs to one or more classifications. The system computes an objective function based on the score and the input data, and computes a gradient of the objective function based on the input data. In response to determining that the computed gradient is not greater than a predetermined threshold, the system perturbs the input data in a direction of or opposite to the computed gradient, and transmits the perturbed input data to the remote computer system to obtain new output data. The system displays on a device a visualization of whether the input data belongs more or less strongly to a classification.
    Type: Grant
    Filed: May 25, 2017
    Date of Patent: November 27, 2018
    Assignee: PALO ALTO RESEARCH CENTER INCORPORATED
    Inventor: Anurag Ganguli
  • Patent number: 10121072
    Abstract: The present disclosure relates to language agnostic unsupervised removal of text from form images. According to one embodiment, a method comprises generating a spectral domain representation of an image by applying a two dimensional frequency domain transformation, where the image depicts form layout elements and text elements. Applying a first filter to the spectral domain representation to remove a portion of the frequency domain corresponding to the text element, and applying an inverse two dimensional frequency domain transformation to the filtered spectral domain representation of the image to generate a reconstructed image. The text elements are not depicted in the reconstructed image.
    Type: Grant
    Filed: December 30, 2016
    Date of Patent: November 6, 2018
    Assignee: Intuit inc.
    Inventor: Rohan Kekatpure
  • Patent number: 10102347
    Abstract: The invention relates to a system for producing a representation of an object in image data, based on a template coupled to a model of the object, the system comprising a model unit for adapting the model to the object in the image data, and a template unit for adapting the template to the adapted model on the basis of the coupling between the template and the model. The template defines a representation of the object which is simpler to interpret than the model. Because the template of the invention is coupled to the model, the position, orientation and/or shape of the template is determined by the model adapted to the object in the image data. Hence, the template is adapted to the image data. The adapted template is capable of representing the object and its individual characteristics.
    Type: Grant
    Filed: September 17, 2009
    Date of Patent: October 16, 2018
    Assignee: Koninklijke Philips N.V.
    Inventors: Cristian Lorenz, Sebastian Peter Michael Dries, Steffen Renisch, Jens Von Berg
  • Patent number: 10095951
    Abstract: During a description technique, a local descriptor for an object may be generated by computing a 2-dimensional histogram of pairs of angles between pairs of line segments that are aligned with edge pixels associated with the object. The pairs of line segments belong to a subset of k neighboring or proximate line segments. Moreover, this 2D histogram may represent the relative displacement and the relative orientations of the pairs of line segments in the subset as weights in bins or cells defined by angular quantization values, and the 2D histogram may exclude lengths of the line segments. Subsequently, the generated 2D histogram may be compared to predefined sets of descriptors in a model library that are associated with a set of objects, and the object may be identified as one of the set of objects based on a group of match scores determined in the comparisons.
    Type: Grant
    Filed: November 14, 2016
    Date of Patent: October 9, 2018
    Assignee: Datalogic IP Tech S.R.L.
    Inventors: Federico Tombari, Alessandro Franchi, Luigi Di Stefano
  • Patent number: 10095925
    Abstract: A device may receive image data representing a document, the document including: text, and edges. Based on the edges, the device may identify, a segment of interest within the image data and crop the segment of interest to obtain a portion of the image data. In addition, the device may perform optical character recognition on the portion of the image data, the optical character recognition producing recognized text. The device may obtain, based on the recognized text, validation data that includes verification text, and determine whether the recognized text is verified based on the verification text. Based on a result of the determination, the device may perform an action.
    Type: Grant
    Filed: December 18, 2017
    Date of Patent: October 9, 2018
    Assignee: Capital One Services, LLC
    Inventors: Subhashini Tripuraneni, Joseph R. Barco, Jr.
  • Patent number: 10095946
    Abstract: The present disclosure is directed to systems and methods for strike through detection and, more particularly, to systems and methods for detecting a strike through in an address block of a mailpiece. The method is implemented in a computing device and includes: generating edges of lines within a text block identified through optical character recognition processes; locating text lines within the text block; characterizing the edges within the text lines and outside of the text lines; and grouping identified edges of the characterized edges outside of the text lines into co-linear groups.
    Type: Grant
    Filed: July 7, 2016
    Date of Patent: October 9, 2018
    Assignee: LOCKHEED MARTIN CORPORATION
    Inventors: Richard C. Vanhall, Robert S. Lunt, IV
  • Patent number: 10088600
    Abstract: The invention relates to a weather recognition method and device based on image information detection, including: obtaining an image extracting multiple first image features of the image with respect to each preset type of weather using a number of first preset algorithms preset correspondingly for different preset types of weather; inputting the multiple first image features to a preset multi-kernel classifier, the multi-kernel classifier performing classification according to the image features to identify the weather in which the image was taken. The multi-kernel classifier is realized by: selecting a first preset number of image samples for each of the preset types of weather; for the image samples of this type of weather, extracting the first image features of each image sample according to the first preset algorithm corresponding to this preset type of weather; and performing machine learning for the first image features according to a preset multi-kernel learning algorithm.
    Type: Grant
    Filed: September 4, 2015
    Date of Patent: October 2, 2018
    Assignee: BEIJING UNIVERSITY OF POSTS AND TELECOMMUNICATIONS
    Inventors: Huadong Ma, Huiyuan Fu, Zheng Zhang
  • Patent number: 10063774
    Abstract: An image processing apparatus detecting a plurality of joint positions between a plurality of input images includes a target image generation unit configured to generate a plurality of target images to be searched in a second input image among the input images from a first input image among the input images; a characteristic amount calculation unit configured to calculate a characteristic amount for each of the target images generated by the target image generation unit; and a joint position determination unit configured to determine the joint position for a target image of interest among the target images having the characteristic amounts calculated by the characteristic amount calculation unit depending on the characteristic amount.
    Type: Grant
    Filed: August 25, 2014
    Date of Patent: August 28, 2018
    Assignee: Ricoh Company, Ltd.
    Inventors: Hirokazu Takenaka, Kazuhiro Yoshida, Keiichi Kawaguchi
  • Patent number: 10021870
    Abstract: A real-time counting insecticidal lamp includes a rainproof cover, a LED lamp body, an insect receiver, and a high-voltage grid; the rainproof cover is arranged above the lamp body, the insect receiver is arranged below the lamp body, and the high-voltage grid is arranged at the periphery of the lamp body; the high-voltage grid includes a high-voltage direct current power supply and N-1 wires, and the N-1 wires are arranged in parallel in each interval to form a circle, wherein, N is no less than 10; top ends of the wires are all connected to the power supply end of the power supply, but one of two adjacent wires is electrically connected to the positive end of the power supply while the other is electrically connected to the negative end; the real-time counting insecticidal lamp also includes a counting unit.
    Type: Grant
    Filed: June 3, 2016
    Date of Patent: July 17, 2018
    Assignee: Nanjing Agricultural University
    Inventors: Xiaochan Wang, Tingting Yan, Guoxiang Sun, Guyue Hu
  • Patent number: 10013758
    Abstract: Systems and methods for processing a segmented volume from magnetic resonance images that corresponds to a nerve are provided. The segmented volume can be processed to generate a report that provides complementary information on the state or condition of tissues contained in the segmented nerve volume. For example, the segmented volume can be processed to identify regions of suspected inflammation, or other pathology such as demyelination, of the nerve tissue contained in the segmented volume. The systems and methods described here provide a user-defined approach to identifying regions of suspected inflammation, or other pathology, in a segmented nerve volume.
    Type: Grant
    Filed: May 27, 2016
    Date of Patent: July 3, 2018
    Assignee: 3D Imaging Partners
    Inventors: Saso Koceski, Filip Shteriev, Domenico Ciambrone, Lionel Lenkinski, Robert Lenkinski
  • Patent number: 10007680
    Abstract: Systems and approaches for searching a content collection corresponding to query content are provided. In particular, false positive match rates between the query content and the content collection may be reduced with a minimum content region test and/or a minimum features per scale test. For example, by correlating content descriptors of a content piece in the content collection with query descriptors of the query content, the content piece can be determined to match the query content when a particular region of the content piece and/or a particular region of a query descriptor have a proportionate size meeting or exceeding a specified minimum. Alternatively, or in addition, the false positive match rate between query content and a content piece can be reduced by comparing content descriptors and query descriptors of features at a plurality of scales. A content piece can be determined to match the query content according to descriptor proportion quotas for the plurality of scales.
    Type: Grant
    Filed: January 26, 2015
    Date of Patent: June 26, 2018
    Assignee: A9.COM, INC.
    Inventors: Arnab Sanat Kumar Dhua, Sunil Ramesh, Max Delgadillo, Raghavan Manmatha
  • Patent number: 9996897
    Abstract: An image display method for a portable display device to be implemented by a processing module includes: controlling the portable display device to display an image in a default position within a display area; estimating a displacement distance of the portable display device during an (X+1)th unit time period, based at least on a number (N) of displacement distances of the portable display device respectively during (N) number of immediately previous unit time periods or on accelerations of the portable display device respectively associated with (X?1)th and (X)th unit time periods; and controlling the portable display device to shift the image with respect to the display area based on the displacement distance estimated thereby.
    Type: Grant
    Filed: June 20, 2016
    Date of Patent: June 12, 2018
    Assignee: Chang Gung University
    Inventors: Jyh-Da Wei, Hsu-Fu Hsiao, Chen-Cheng Tsai, Yi-Xin Liu, Po-I Liu, Jiun-Shian Sung
  • Patent number: 9977995
    Abstract: An image clustering method, an image clustering system, and an image clustering server are provided. The method includes: extracting a GIST feature of a first image and a GIST feature of a second image; obtaining an image fingerprint of the first image based on the GIST feature of the first image, and obtaining an image fingerprint of the second image based on the GIST feature of the second image; calculating a similarity between the first image and the second image, based on the image fingerprint of the first image and the image fingerprint of the second image; and determining whether the similarity between the first image and the second image is larger than a predetermined similarity threshold, and classifying the two image as a same category of image if the similarity between the first image and the second image is larger than the predetermined similarity threshold.
    Type: Grant
    Filed: May 11, 2016
    Date of Patent: May 22, 2018
    Assignee: Tencent Technology (Shenzhen) Company Limited
    Inventor: Pipei Huang
  • Patent number: 9959473
    Abstract: In a symbol recognition device, each histogram computation module receives an image of each partial region of a recognition target region in a binarized image and computes a frequency distribution of pixels of a given color in each line or column in the partial region; each run length determination module receives an image of each partial region of the recognition target region and determines whether or not a line or column of pixels of the given color having a certain length is present in the partial region; a control module feeds pixel information of the partial regions, read by scanning the binarized image stored in the image memory, into the histogram computation modules and the run length determination modules; a determination module determines a symbol included in the binarized image based on computation results of the histogram computation modules and determination results of the run length determination modules.
    Type: Grant
    Filed: March 29, 2016
    Date of Patent: May 1, 2018
    Assignee: HIROSHIMA UNIVERSITY
    Inventors: Tetsushi Koide, Hoang Anh Tuan, Masaharu Yamamoto, Tsubasa Mishima
  • Patent number: 9928642
    Abstract: A system and method uses the capabilities of a geometry shader unit within the multi-threaded graphics processor to implement algorithms with variable input and output.
    Type: Grant
    Filed: January 3, 2017
    Date of Patent: March 27, 2018
    Assignee: NVIDIA CORPORATION
    Inventor: Franck Diard
  • Patent number: 9922270
    Abstract: Systems and methods of generating a compact visual vocabulary are provided. Descriptor sets related to digital representations of objects are obtained, clustered and partitioned into cells of a descriptor space, and a representative descriptor and index are associated with each cell. Generated visual vocabularies could be stored in client-side devices and used to obtain content information related to objects of interest that are captured.
    Type: Grant
    Filed: February 13, 2015
    Date of Patent: March 20, 2018
    Assignee: Nant Holdings IP, LLC
    Inventors: Bing Song, David McKinnon
  • Patent number: 9922241
    Abstract: The invention concerns a gesture recognition method for gesture-based interaction at an apparatus. The method comprises receiving one or more images of an object; creating feature images for the received one or more images; determining binary values for pixels in corresponding locations of said feature images and concatenating the binary values to form a binary string for said pixel; repeating the previous step for each corresponding pixel of said feature image to form a feature map and forming a histogram representation of the feature map. The invention also concerns an apparatus and a computer program.
    Type: Grant
    Filed: December 1, 2011
    Date of Patent: March 20, 2018
    Assignee: Nokia Technologies Oy
    Inventors: Jiangwei Li, Kongqiao Wang, Lei Xu
  • Patent number: 9910939
    Abstract: Methods of characterizing or classifying graphical representation of numerical simulation results are disclosed. A training database is created in a computer system by including a plurality of graphical representations of respective results obtained from a plurality of numerical simulations. Each graphical representation is associated with a textual description of a pertinent feature related to the numerical simulations by user. A quality index with respect to the associated textual description is calculated for each graphical representation by application module using an autocorrelation technique of correlating all graphical representations with one another in the training database. A new graphical representation obtained from another numerical simulation can then be characterized with one of the textual descriptions and a corresponding confidence score by comparing the new graphical representation with all graphical representations in the training database.
    Type: Grant
    Filed: September 25, 2014
    Date of Patent: March 6, 2018
    Assignee: Livermore Software Technology Corp.
    Inventor: Suri Bala
  • Patent number: 9899061
    Abstract: A representative frame selecting system includes: an importance obtaining unit that obtains importance of each frame from calculating on the basis of a length of a similar frame interval formed of consecutive frames each of which has a value according to a similarity between each of the frames included in video information that is equal to or more than a standard; an evaluation value obtaining unit that obtains an evaluation value of each frame from calculating on the basis of an evaluation standard from frames adjacent to each frame; and a representative frame selecting unit that selects at least one representative frame among the frames included in the video information, on the basis of the importance and the evaluation value of each frame.
    Type: Grant
    Filed: July 15, 2014
    Date of Patent: February 20, 2018
    Assignee: FUJI XEROX CO., LTD.
    Inventor: Shingo Uchihashi
  • Patent number: 9881374
    Abstract: Disclosed is a method for establishing a prediction model based on a multidimensional texture of brain nuclear magnetic resonance images. Images are segmented using a region growing method, a contourlet transform method is used to extract an edge texture feature parameter of ROIs, a multidimensional database is established, and a prediction model is established using various data mining methods, comprising a Gaussian process, a support vector machine, a random forest, a Lasso regression and a semi-supervised support vector machine. The ROIs comprise a hippocampus region and an entorhinal cortex region.
    Type: Grant
    Filed: June 10, 2016
    Date of Patent: January 30, 2018
    Assignee: CAPITAL MEDICAL UNIVERSITY
    Inventors: Xiuhua Guo, Ni Gao, Jingjing Wang, Yanxia Luo, Jin Guo
  • Patent number: 9836655
    Abstract: An information processing apparatus including a memory storing instructions, and at least one processor configured to process the instructions to obtain an orientation, size, and position of a first subject in a first image, and an orientation, size, and position of a second subject in a second image, generate an estimated position of the first subject in the second image based on the orientation, size, and position of the first subject in the first image and the orientation and size of the second subject in the second image, calculate a distance between the estimated position of the first subject in the second image and the position of the second subject in the second image; and determine whether or not the first subject is the second subject based on the distance.
    Type: Grant
    Filed: June 23, 2015
    Date of Patent: December 5, 2017
    Assignee: NEC CORPORATION
    Inventor: Jia Hao
  • Patent number: 9830533
    Abstract: Embodiments focus on the real-time processing and analysis of event-related images posts on social media. By computing the most posted images and grouping them in accordance to their similarity, these images can be organized in a visual interface to provide the users an image-driven social media topic detection system. The groups of images with the highest frequency represent the most prominent topics. By keeping track of the temporal occurrence of the images, it is possible to visualize the temporal evolution of the topics.
    Type: Grant
    Filed: December 30, 2015
    Date of Patent: November 28, 2017
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Paulo Rodrigo Cavalin, Maira Athanazio de Cerqueira Gatti, Carlos Mendes, Luis Gregorio Moyano, Claudio Santos Pinhanez
  • Patent number: 9785825
    Abstract: Provided is a method for estimating a disparity search range to which multi-level disparity image partition is applied, and a stereo image matching device using the same in that a disparity histogram of a previous disparity image is analyzed at the time of stereo matching of a continuous image, the disparity image is divided into various sizes of image blocks, and a disparity search range is estimated on the basis of a disparity value having the number of pixels equal to or more than a predetermined threshold value for each image block, thereby decreasing a calculation amount while improving a stereo matching rate of the next frame.
    Type: Grant
    Filed: January 7, 2016
    Date of Patent: October 10, 2017
    Assignee: KYUNGPOOK NATIONAL UNIVERSITY INDUSTRY—ACADEMIC COOPERATION FOUNDATION
    Inventors: Byungin Moon, Taewoong Ahn, Kyeongryeol Bae
  • Patent number: 9703658
    Abstract: Systems and techniques for identifying failure mechanisms based on a population of scan diagnostic reports is described. Given a population of scan diagnostic reports, a mixed membership model can be used for computing a topic distribution for each portion of each scan diagnostic report and a feature distribution for each topic. The failure mechanisms can be identified based on the topic distributions for the portions of the scan diagnostic reports and the feature distributions for the topics.
    Type: Grant
    Filed: October 30, 2015
    Date of Patent: July 11, 2017
    Assignee: SYNOPSYS, INC.
    Inventors: Christopher W. Schuermyer, Karen Movsisyan
  • Patent number: 9704271
    Abstract: Provided are a method and apparatus for giving a blurring effect of various levels to a given image. In the blur image processing method, the apparatus obtains an original image and blur-related information for generating a blur image. The apparatus generates a diagonal image with regard to each pixel, based on the original image, and generates the blur image from the diagonal image by using the blur-related information.
    Type: Grant
    Filed: December 2, 2015
    Date of Patent: July 11, 2017
    Assignee: Samsung Electronics Co., Ltd
    Inventors: Uison Yoon, Jisoo Yeh, Seokyoung Jeong
  • Patent number: 9697439
    Abstract: An object detection method includes for each of a set of patches of an image, encoding features of the patch with a non-linear mapping function, and computing per-patch statistics based on the encoded features for approximating a window-level non-linear operation by a patch-level operation. Then, windows are extracted from the image, each window comprising a sub-set of the set of patches. Each of the windows is scored based on the computed patch statistics of the respective sub-set of patches. Objects, if any, can then be detected in the image, based on the window scores. The method and system allow the non-linear operations to be performed only at the patch level, reducing the computation time of the method, since there are generally many more windows than patches, while not impacting performance unduly, as compared to a system which performs non-linear operations at the window level.
    Type: Grant
    Filed: October 2, 2014
    Date of Patent: July 4, 2017
    Assignee: XEROX CORPORATION
    Inventors: Adrien Gaidon, Diane Larlus-Larrondo, Florent C. Perronnin
  • Patent number: 9671354
    Abstract: A method is provided for analysing electron backscatter diffraction data generated from a sample material. An image data set representative of an image of electron backscatter diffraction bands is obtained from the sample material. A set of estimated first diffraction parameters is then generated, these defining individual electron backscatter diffraction bands in the image data set. A candidate phase is then selected together with a respective orientation for the material, based upon the generated set of estimated parameters thereby identifying diffraction bands in the image data set. Second diffraction parameters of the identified diffraction bands are simulated for the candidate phase according to the respective orientation. These second diffraction parameters are then adjusted for the identified simulated bands so as to fit the simulated bands to the bands in the image data.
    Type: Grant
    Filed: February 14, 2014
    Date of Patent: June 6, 2017
    Assignee: Oxford Instruments Nanotechnology Tools Limited
    Inventors: Charles Penman, Niels-Henrik Schmidt, Knud Thomsen
  • Patent number: 9667879
    Abstract: Blur metrics may be calculated for each of the image pixels of a digital image of a scene captured using an imaging device. The blur metrics may be indicative of the level of blur expressed in the digital image, and a blur image representative of the blur metrics may be generated. Subsequently, when another digital image is to be captured using the imaging device, pixel sensors corresponding to high blur metrics may be digitized at a high level of priority, or at a high rate, compared to pixel sensors corresponding to low blur metrics, which may be digitized at a low level of priority, or at a low rate. The blur images may be updated based on changes in blur observed in subsequent images, and different pixel sensors may be digitized at higher or lower levels of priority, or at higher or lower rates, based on the changes in blur.
    Type: Grant
    Filed: December 2, 2016
    Date of Patent: May 30, 2017
    Assignee: Amazon Technologies, Inc.
    Inventors: Dushyant Goyal, Pragyana K. Mishra
  • Patent number: 9633265
    Abstract: A method for tracking objects across a number of image frames includes tracking objects in the frames based on appearance models of each foreground region corresponding to each of the objects and determining if a plurality of the tracked objects overlap. Where a plurality of the tracked objects overlap, the method creates compensated appearance models for each of the plurality of overlapping objects by attenuating common appearance features among the corresponding appearance models; and tracks the plurality of overlapping objects based on the created compensated appearance models.
    Type: Grant
    Filed: October 7, 2014
    Date of Patent: April 25, 2017
    Assignee: Canon Kabushiki Kaisha
    Inventor: Andrew John Shellshear
  • Patent number: 9633049
    Abstract: A searching apparatus comprising: a storage unit that stores therein indexes for searching for an object included in an image and cooperative information indicating a function of cooperating with the object in association with each other; a receiving unit that receives a captured image; an extracting unit that extracts an object included in the captured image; a calculating unit that calculates a degree of similarity between the object searched for by an index stored in the storage unit and the object extracted from the captured image by the extracting unit; a searching unit that searches for one or more objects based on the degree of similarity from the storage unit; and a presenting unit that presents the cooperative information associated with the index corresponding to the object as a search result of the searching unit to a source of the captured image.
    Type: Grant
    Filed: June 5, 2013
    Date of Patent: April 25, 2017
    Assignee: Ricoh Company, Limited
    Inventors: Hidenobu Kishi, Takayuki Kunieda, Tetsuya Ikeda
  • Patent number: 9626766
    Abstract: A method of sensing depth using an RGB camera. In an example method, a color image of a scene is received from an RGB camera. The color image is applied to a trained machine learning component which uses features of the image elements to assign all or some of the image elements a depth value which represents the distance between the surface depicted by the image element and the RGB camera. In various examples, the machine learning component comprises one or more entangled geodesic random decision forests.
    Type: Grant
    Filed: February 28, 2014
    Date of Patent: April 18, 2017
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Antonio Criminisi, Duncan Paul Robertson, Peter Kontschieder, Pushmeet Kohli, Henrik Turbell, Adriana Dumitras, Indeera Munasinghe, Jamie Daniel Joseph Shotton
  • Patent number: 9626601
    Abstract: Systems and methods for identifying transformations to be applied to at least part of a document image for improving the OCR quality. An example method comprises: constructing, by a computer system, an ordered list of transformations to be applied to an image comprising a character string, each transformation corresponding to a hypothesis asserted with respect to one or more characteristics of the image; applying, to the image, a leading transformation on the list to produce a transformed image; evaluating a quality of the transformed image to produce a quality estimate; and updating the list in view of the quality estimate.
    Type: Grant
    Filed: December 16, 2014
    Date of Patent: April 18, 2017
    Assignee: ABBYY Development LLC
    Inventor: Sergey Kuznetsov
  • Patent number: 9626738
    Abstract: An image processing apparatus includes a detection unit that detects segments from a first image; a selection unit that selects pairs of segments formed of a predetermined number of segments counted from a higher priority in an order of length among the detected segments and segments in a second image, the second image being a model of the first image; and a calculation unit that calculates distortion of the first image with respect to the second image by using the pairs of segments.
    Type: Grant
    Filed: September 10, 2014
    Date of Patent: April 18, 2017
    Assignee: FUJI XEROX CO., LTD.
    Inventor: Eiichi Tanaka