Comparator Patents (Class 382/218)
-
Patent number: 11048946Abstract: A system and method of identifying cognate image sequences is disclosed that examines significant frames of a stream of video images using an array of image indexes. The image index array includes image indexes obtained by at least two different image indexing methods. These are compared to a corresponding array of image indices of significant frames of known image sequences. An image quality indicator is used to determine which set of image index thresholds to use in making the comparison. These thresholds are more stringent for higher quality frames. Two image sequences are considered cognate when a string of sufficiently many sequential frame matches is established. In an alternate embodiment, image blurriness is also, or instead, used to determine the appropriate set of image index thresholds. The sets of image index thresholds are determined using machine learning on a curated set of representative images.Type: GrantFiled: October 16, 2020Date of Patent: June 29, 2021Inventors: Samuel Chenillo, Oran Gilad, Oren Steinfeld
-
Patent number: 11030453Abstract: Systems and methods are described for using optical techniques to authenticate a pre-characterized object according to its latent structural characteristics. For example, an image stack can be generated by aligning enrollment images acquired from an enrollment object according to different optical geometries. Enrollment basis functions can be computed from the stack that describe latent structural characteristics of the enrollment object, and enrollment magnitudes can be extracted from those basis functions. Subsequently, another image stack can be generated by aligning authentication images acquired from an authentication object according to different optical geometries. Authentication basis functions can be computed from the stack to describe latent structural characteristics of the authentication object, and authentication magnitudes can be extracted from those basis functions.Type: GrantFiled: December 16, 2015Date of Patent: June 8, 2021Assignee: ASSA ABLOY ABInventors: Robert K. Rowe, Mark Robinton, Ting Sun
-
Patent number: 10984279Abstract: A method and system for machine translation of text is disclosed. The method includes processing an image comprising a text to generate a pattern associated with the text based on a trained Convolution Neural Network (CNN). The method further includes mapping the pattern to a word in a mapping table and at least one text attribute, based on a classifier network. The method further includes initiating an Optical Character Recognition (OCR) conversion for the pattern, when at least one of the mapping between at least one of the pattern and at least one word in the mapping table and the mapping between the pattern and the at least one text attribute is below a predefined threshold. The method further includes performing incremental learning for the trained CNN and the classifier network based on the OCR conversion.Type: GrantFiled: August 16, 2019Date of Patent: April 20, 2021Assignee: Wipro LimitedInventor: Manjunath Ramachandra Iyer
-
Patent number: 10984512Abstract: Provided is an automotive around view image providing method using a machine learning model. The method includes: receiving, by an image processing device, a plurality of images obtained by a plurality of cameras mounted on a car; inputting, by the image processing device, the plurality of images to a neural network encoder to generate a feature vector for each of the plurality of images; and combining, by the image processing device, feature vectors for the plurality of images into one image form and inputting the one image form to the neural network decoder to generate a matched one image. The neural network decoder includes a filter for performing matching on adjacent images having an overlapping area among the plurality of images based on the feature vector for the plurality of images.Type: GrantFiled: July 2, 2019Date of Patent: April 20, 2021Inventor: Hyun-Min Jang
-
Patent number: 10977511Abstract: Systems and methods for performing OCR of a series of images depicting text symbols. An example method comprises performing OCR a series of images to produce a current symbol sequence and corresponding symbol sequence quadrangle; associating the current symbol sequence with a previous symbol sequence for a previously received image; identifying a median string; determining a median symbol sequence quadrangle; and displaying, using the median symbol sequence quadrangle, a resulting OCR text representing at least a portion of the original document.Type: GrantFiled: December 9, 2019Date of Patent: April 13, 2021Assignee: ABBYY PRODUCTION LLCInventor: Aleksey Ivanovich Kalyuzhny
-
Patent number: 10974152Abstract: System and method for automatic computer aided optical recognition of toys, for example, construction toy elements, recognition of those elements on digital images and associating the elements with existing information is presented. The method and system may recognize toy elements of various sizes invariant of toy element distance from the image acquiring device for example camera, invariant of rotation of the toy element, invariant of angle of the camera, invariant of background, invariant of illumination and without the need of predefined region where a toy element should be placed. The system and method may detect more than one toy element on the image and identify them.Type: GrantFiled: January 28, 2019Date of Patent: April 13, 2021Assignee: LEGO A/SInventors: Marko Velic, Karsten Østergaard Noe, Jesper Mosegaard, Brian Bunch Christensen, Jens Rimestad
-
Patent number: 10970599Abstract: Techniques are disclosed for characterizing and defining the location of a copy space in an image. A methodology implementing the techniques according to an embodiment includes applying a regression convolutional neural network (CNN) to an image. The regression CNN is configured to predict properties of the copy space such as size and type (natural or manufactured). The prediction is conditioned on a determination of the presence of the copy space in the image. The method further includes applying a segmentation CNN to the image. The segmentation CNN is configured to generate one or more pixel-level masks to define the location of copy spaces in the image, whether natural or manufactured, or to define the location of a background region of the image. The segmentation CNN may include a first stage comprising convolutional layers and a second stage comprising pairs of boundary refinement layers and bilinear up-sampling layers.Type: GrantFiled: November 15, 2018Date of Patent: April 6, 2021Assignee: ADOBE INC.Inventors: Mingyang Ling, Alex Filipkowski, Zhe Lin, Jianming Zhang, Samarth Gulati
-
Patent number: 10972494Abstract: This invention discloses systems and methods for detecting vulnerabilities in IT assets by utilizing crowdsourcing techniques. A corpus containing vulnerability data of IT assets with known vulnerabilities is established. Vulnerability data in the corpus comprises security aspects or attributes related to the IT assets. The security aspects of an IT asset constitute its attack surface which is represented as a feature vector in a feature space. A determination is made as to how similar/close a target asset whose unknown vulnerabilities are to be detected, is to the rest of the IT assets in the corpus. This determination is made based on a measure of similarity/distance between the respective feature vectors in the feature space. Based on the review of similarity results by a community of researchers/experts, a determination of unknown vulnerabilities in the target system is made.Type: GrantFiled: October 10, 2016Date of Patent: April 6, 2021Assignee: BugCrowd, Inc.Inventors: Jonathan Cran, Michael James O'Kelly, Casey John Ellis
-
Patent number: 10963205Abstract: A method, system and computer program product for generating augmented reality in a state room includes establishing a communicative link with different computing devices disposed within separate state rooms, with each of the state rooms including a display positioned at a ceiling, a display positioned on a wall and a display embedded in a floor. The method further includes, for each of the state rooms, assigning a theme of an exterior environment, directing the retrieval from fixed storage of exterior environmental imagery, and directing display of an atmospheric portion of the exterior environmental imagery on the display positioned at the ceiling, directing display of a horizon portion of the exterior environmental imagery on the display positioned on the wall, and directing display of a surface portion of the exterior environmental imagery on the display embedded in the floor.Type: GrantFiled: October 31, 2018Date of Patent: March 30, 2021Assignee: Royal Caribbean Cruises Ltd.Inventors: Joey Hasty, David Smith, Josh Nakaya
-
Patent number: 10957017Abstract: A method including receiving a first image file in a network server is provided. The method also includes selecting multiple criteria in a test ensemble for the first image file and evaluating a synthetic value for the first image file according to the test ensemble. The method includes storing the first image file and the synthetic value for the first image file in a database, and providing for display the first image file and the synthetic value for the first image file in response to a search query from a user. A system and a non-transitory, computer-readable medium storing instructions to perform the above method are also provided.Type: GrantFiled: April 16, 2019Date of Patent: March 23, 2021Assignee: Shutterstock, Inc.Inventor: Bryan Michael Minor
-
Patent number: 10937180Abstract: A method and an apparatus for depth-map estimation between at least two images respectively captured by at least two cameras are disclosed. Extrinsic and intrinsic parameters of the at least two cameras are obtained. Local spatial structure descriptors for each pixel of the at least two images are obtained by transforming a patch of pixels surrounding each pixel, and depth is obtained for at least one pixel of a first image among the at least two images, among at least two depth candidates, each depth candidate being associated with a corresponding pixel in a second image of the at least two images, said corresponding pixel in the second image being determined according to the obtained extrinsic and intrinsic parameters.Type: GrantFiled: December 27, 2018Date of Patent: March 2, 2021Assignee: INTERDIGITAL CE PATENT HOLDINGSInventors: Frederic Babon, Benoit Vandame, Guillaume Boisson
-
Patent number: 10930076Abstract: Systems and methods for matching content elements to surfaces in a spatially organized 3D environment. The method includes receiving content, identifying one or more elements in the content, determining one or more surfaces, matching the one or more elements to the one or more surfaces, and displaying the one or more elements as virtual content onto the one or more surfaces.Type: GrantFiled: May 1, 2018Date of Patent: February 23, 2021Assignee: Magic Leap, Inc.Inventors: Denys Bastov, Victor Ng-Thow-Hing, Benjamin Zaaron Reinhardt, Leonid Zolotarev, Yannick Pellet, Aleksei Marchenko, Brian Everett Meaney, Marc Coleman Shelton, Megan Ann Geiman, John A. Gotcher, Matthew Schon Bogue, Shivakumar Balasubramanyam, Jeffrey Edward Ruediger, David Charles Lundmark
-
Patent number: 10929988Abstract: A method and a device for processing an image, an electronic device and a computer readable storage medium are provided. The method includes: obtaining an image capturing instruction; capturing an infrared image and an RGB image based on the image capturing instruction, extracting a first feature of the infrared image and extracting a second feature of the RGB image; and performing an alignment operation based on the first feature and the second feature.Type: GrantFiled: July 30, 2019Date of Patent: February 23, 2021Assignee: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP., LTD.Inventors: Ziqing Guo, Haitao Zhou, Kamwing Au
-
Patent number: 10928645Abstract: A three-dimensional (3D) image display apparatus includes a processor configured to determine, from image data of a 3D image to be displayed, a representative depth value based on a current frame of the 3D image and a previous frame of the 3D image, and an imaging optical system configured to generate the 3D image in a predetermined space by modulating light based on the representative depth value.Type: GrantFiled: January 16, 2019Date of Patent: February 23, 2021Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Yuntae Kim, Geeyoung Sung, Changkun Lee, Hongseok Lee
-
Patent number: 10913454Abstract: A system and a method are disclosed for determining intent of a human based on human pose. In some embodiments, a processor obtains a plurality of sequential images from a video feed, and determines respective keypoints corresponding a human in each respective image of the plurality of sequential images. The processor aggregates the respective keypoints for each respective image into a pose of the human and transmits a query to a database to find a template that matches the pose by comparing the pose to a plurality of templates poses that translate candidate poses to intent, each template corresponding to an associated intent. The processor receives a reply message from the database that either indicates an intent of the human based on a matching template, or an inability to locate the matching template, and, in response to the reply message indicating the intent of the human, outputs the intent.Type: GrantFiled: December 13, 2018Date of Patent: February 9, 2021Assignee: Humanising Autonomy LimitedInventors: Maya Audrey Lara Pindeus, Raunaq Bose, Leslie Cees Nooteboom, Adam Joshua Bernstein
-
Patent number: 10909459Abstract: The technology disclosed introduces a concept of training a neural network to create an embedding space. The neural network is trained by providing a set of K+2 training documents, each training document being represented by a training vector x, the set including a target document represented by a vector xt, a favored document represented by a vector xs, and K>1 unfavored documents represented by vectors xiu, each of the vectors including input vector elements, passing the vector representing each document set through the neural network to derive an output vectors yt, ys and yiu, each output vector including output vector elements, the neural network including adjustable parameters which dictate an amount of influence imposed on each input vector element to derive each output vector element, adjusting the parameters of the neural network to reduce a loss, which is an average over all of the output vectors yiu of [D(yt,ys)?D(yt, yiu)].Type: GrantFiled: June 9, 2017Date of Patent: February 2, 2021Assignee: Cognizant Technology Solutions U.S. CorporationInventors: Petr Tsatsin, Philip M. Long, Diego Guy M. Legrand, Nigel Duffy
-
Patent number: 10890916Abstract: A learning method for performing a seamless parameter switch by using a location-specific algorithm selection for an optimized autonomous driving is provided. And the method includes steps of: (a) a learning device instructing a K-th convolutional layer to apply a convolution operation to K-th training images, to thereby generate K-th feature maps; (b) the learning device instructing a K-th output layer to apply a K-th output operation to the K-th feature maps, to thereby generate K-th estimated autonomous driving source information; (c) the learning device instructing a K-th loss layer to generate a K-th loss by using the K-th estimated autonomous driving source information and its corresponding GT, and then to perform backpropagation by using the K-th loss, to thereby learn K-th parameters of the K-th CNN; and (d) the learning device storing the K-th CNN in a database after tagging K-th location information to the K-th CNN.Type: GrantFiled: December 31, 2019Date of Patent: January 12, 2021Assignee: STRADVISION, INC.Inventors: Kye-Hyeon Kim, Yongjoong Kim, Hak-Kyoung Kim, Woonhyun Nam, SukHoon Boo, Myungchul Sung, Dongsoo Shin, Donghun Yeo, Wooju Ryu, Myeong-Chun Lee, Hyungsoo Lee, Taewoong Jang, Kyungjoong Jeong, Hongmo Je, Hojin Cho
-
Patent number: 10878224Abstract: Provided is an image processing method and system. More particularly, provided are an image processing method and system that may map a facial expression of a user, a specific event, etc., to a character in real time by mapping an object such as a face of a user included in an input image to a virtual object such as a face of a specific character, and by applying an event corresponding to a combination of components defined for the object to the virtual object, and a non-transitory computer-readable recording medium that, when executed by a processor, cause the processor to implement the image processing method in conjunction with a computer device.Type: GrantFiled: June 27, 2018Date of Patent: December 29, 2020Assignee: LINE CorporationInventors: Cheol Hyun, Shin Kim, Byoung Cho Park, Byoung Gon Yoo
-
Patent number: 10863935Abstract: Apparatus for optical tissue detection and discrimination between a tissue of a user and non-tissue materials and method of optical tissue detection and discrimination between a tissue of a user and non-tissue materials are provided. The apparatus for optical tissue detection includes one or more of light sources. The apparatus can further include at least one photodetector. A processor can be operable to determine whether the detected light is from a tissue of a user.Type: GrantFiled: September 9, 2016Date of Patent: December 15, 2020Assignee: Happy Health, Inc.Inventors: Paulo E. Xavier Da Silveira, Nithin O. Rajan, Dustin M. Freckleton
-
Patent number: 10867389Abstract: An image processing apparatus detects motion information of an image capturing unit in a time period between capturing of a first image and capturing of a second image by the image capturing unit, and detects a plurality of motion vectors between the first image and the second image. Further, the image processing apparatus determines reliability of the detected motion information, and determines, based on the motion information and the reliability, a motion vector to be used for alignment of the first image and the second image, from the plurality of motion vectors.Type: GrantFiled: June 20, 2018Date of Patent: December 15, 2020Assignee: Canon Kabushiki KaishaInventor: Yoichi Takahashi
-
Patent number: 10861182Abstract: Image recognition device that combines first part candidates and second part candidates to generate a plurality of pairs; that calculates first estimate value for each of the plurality of pairs, this value indicating estimated possibility that these candidates are connected; that executes, for each of the plurality of pairs, correcting first estimate value by using second estimate value as a weight in a state in which a part candidate that is one among a pair of part candidates matching of which has already been performed and that differs from both first part candidate and second part candidate is connected to either first part candidate or second part candidate, second estimate value indicating estimated possibility that the pair of part candidates matching of which has already been performed are connected; and that performs matching of first part candidates and second part candidates using corrected first estimate values.Type: GrantFiled: December 6, 2018Date of Patent: December 8, 2020Assignee: KONICA MINOLTA, INC.Inventor: Taiki Sekii
-
Patent number: 10853971Abstract: A method for determining an exposure, in particular an exposure time, for a recording in a method for determining the 3D coordinates of an object is provided, in which a pattern is projected onto the object and the light reflected by the object is recorded. To improve such a method, a recording of the object is produced with a predetermined exposure, in particular exposure time. A mask image of this recording is produced, in which mask image the regions of the object lying within the measurement volume are depicted. The exposure, in particular the exposure time, for the recording is determined depending on the predetermined exposure, in particular exposure time, depending on the mean greyscale value in the regions, lying within the measurement volume, of the recording with a predetermined exposure and depending on an ideal greyscale value.Type: GrantFiled: February 1, 2018Date of Patent: December 1, 2020Assignee: Carl Zeiss Industrielle Messtechnik GmbHInventors: Christian Schleith, Tom Jaeckel, Alexander Frey, Markus Basel
-
Patent number: 10839525Abstract: An information processing apparatus includes a memory configured to store a recognition result, accuracy and timing of an image captured at a point, and a processor coupled to the memory and the processor configured to specify the image configured to include a designated recognition object, and search for the image having a same recognition result as the recognition object by referring to the memory, based on the point and timing at which the specified image has been captured and movement speed information of the recognition object.Type: GrantFiled: April 12, 2019Date of Patent: November 17, 2020Assignee: FUJITSU LIMITEDInventors: Kenji Iwasaki, Jun Ogawa, Makoto Kubota
-
Patent number: 10831383Abstract: Systems and methods for command line voting are provided. Aspects include obtaining, by an output logic device, a plurality of memory blocks from a plurality of buffers, each of the plurality of memory blocks including two or more output commands generated from a processing circuit based on a sensor data input, generating, by a hash function, a hash value for each of the plurality of memory blocks, comparing the hash value for each of the plurality of memory blocks to determine an output memory block from the plurality of memory blocks, and outputting, to an output hardware, the two more output commands from the output memory block.Type: GrantFiled: November 2, 2018Date of Patent: November 10, 2020Assignee: HAMILTON SUNDSTRAND CORPORATIONInventors: Christopher Brian Noll, Steven A. Avritch
-
Patent number: 10824942Abstract: Embodiments described herein are directed to allowing manipulation of visual attributes of a query image while preserving the visual attributes of a query image. A query image can be received and analyzed using a trained network to determine a set of items whose images demonstrate visual similarity to the query image across a plurality of visual attributes. Visual attributes of the query image may be manipulated to allow a user to search for items that incorporate the desired manipulated visual attributes while preserving the visual attributes of the query image. Content for at least a determined number of highest ranked, or most similar, items related to the modified visual attributes can then be provided.Type: GrantFiled: April 10, 2017Date of Patent: November 3, 2020Assignee: A9.COM, INC.Inventors: Rahul Bhotika, Avinash Aghoram Ravichandran
-
Patent number: 10819934Abstract: The present invention relates to an image sensor system. The invention further relates to an X-ray imaging system comprising such an image sensor system. More in particular, the present invention is related to image sensor systems that use a relatively small pixel width. According to the present invention, the conversion unit comprises, for each column of pixels, a load that comprises a toggling unit configured for toggling a predefined number of bits in response to the clock signal. Furthermore, the load and binary counter are operable in a counting mode, in which mode the binary counter increases the binary count value in dependence of the clock signal and the load does not toggle, and in a non-counting mode, in which mode the binary counter has stopped counting and the load toggles said predefined number of bits in dependence of the clock signal.Type: GrantFiled: July 19, 2019Date of Patent: October 27, 2020Assignee: TELEDYNE DALSA B.V.Inventors: Laurens Korthout, Vincent Arkesteijn
-
Patent number: 10798428Abstract: A method to improve convenience for providing a coupon with the use of a spatial or temporal modulation component added to light that can be captured while a service is being used. Provided is a method for providing a coupon by using a terminal device and at least one server configured to provide a service to the terminal device, the method includes capturing light while the service is being used, transmitting key information based on a spatial or temporal modulation component of the light to the server, and receiving coupon information related to the service transmitted from the server by using the terminal device; and receiving the key information from the terminal device and issuing the coupon information in accordance with the key information by using the server.Type: GrantFiled: September 18, 2015Date of Patent: October 6, 2020Assignee: SONY CORPORATIONInventors: Tomoo Mitsunaga, Kensei Jo, Hiroaki Takahashi, Takeyuki Fujii, Junichi Kosaka
-
Patent number: 10796459Abstract: An information processing apparatus includes a controller configured to control a mode of display of each piece of information in such a manner that a part or whole of each piece of information included in a plurality of pieces of information related to a specific position is displayed on a display unit.Type: GrantFiled: July 5, 2018Date of Patent: October 6, 2020Assignee: FUJI XEROX CO., LTD.Inventor: Kengo Tokuchi
-
Patent number: 10776816Abstract: A system for building a targeted audience for a present online advertising campaign is disclosed. The system comprises a database for storing data related to each of the plurality of products with each product associated with a previous online advertising campaign and a processor in communication with the database and configured to execute computer-readable instructions causing the processor to utilize the data to identify at least one previous online advertising campaign as being similar to the present online advertising campaign, learn from the identified previous online advertising campaign(s) to predict a probability of conversion of each of a plurality of customers when exposed to an impression of the present online advertising campaign, and build the targeted audience for the present online advertising campaign based on the predicted probability of conversion. A method for building a targeted audience for a present online advertising campaign is also disclosed.Type: GrantFiled: January 30, 2015Date of Patent: September 15, 2020Assignee: WALMART APOLLO, LLCInventors: Abhimanyu Mitra, Patrick Lloyd Harrington, Jr., Nikhil Raj, Somnath Banerjee, Gary Tang, Zachary Poley, Yun Zhang, Galana Gebisa, Robert Bartoszynski, Chung-Wei Yen
-
Patent number: 10769666Abstract: An intelligent marketing and advertising platform which provides an innovative merchandising solution for retailers by effectively transforming the glass surface of retail product containers (such as cooler doors) into a non-transparent display of planograms. The merchandising solution provides for digital planograms and pricing management, real time promotional updates and sales data, etc. This is accomplished by converting/transforming the simple glass surface of a retail product container (such as cooler/freezer doors) into digital “smart” screens that provide for innovative advertising solutions. The cooler/freezer doors are configured to use at least one camera to capture images when the doors are opened, in order to effectively take inventory of what is inside the cooler/freezer.Type: GrantFiled: December 17, 2018Date of Patent: September 8, 2020Assignee: Cooler Screens Inc.Inventor: Arsen Avakian
-
Patent number: 10769430Abstract: A method and fabrication correction system for correcting fabrication in a document receives an input document from a user and identifies a reference document based on one of a plurality of categories of the input document from reference document database. The fabrication correction system detects fabrication in input document based on a predefined machine learning technique, by comparing one or more parameters associated with the input document with corresponding one or more parameters of the reference document and determines fabricated regions in the input document and a type of the fabrication in each of the one or more fabricated regions, based on one or more predefined techniques. Thereafter, one or more actions is performed in each of the one or more fabricated regions based on the type of the fabrication and the reference document, upon receiving a user input, for correcting the one or more fabricated regions.Type: GrantFiled: July 30, 2018Date of Patent: September 8, 2020Assignee: Wipro LimitedInventors: Aayush Kumar, Manmohan Kumar, Janki Rao Upada
-
Patent number: 10757101Abstract: Embodiments are directed to using a hash signature of a rendered DOM object of a website to find similar content and behavior on other websites. Embodiments break a DOM into a large number of data portions (i.e., “shingles”), apply a hashing algorithm to the shingles, select a predetermined number of hashes from the hashed shingles according to a selection criteria to create a hash signature, and compare the hash signature to that of a reference page to determine similarity of website DOM object content. Embodiments can be used to identify phishing websites, defaced websites, spam websites, significant changes in the content of a webpage, copyright infringement, and any other suitable purposes related to the similarity between website DOM object content.Type: GrantFiled: September 25, 2018Date of Patent: August 25, 2020Assignee: RiskIQ, Inc.Inventors: Adam Hunt, David Pon, Chris Kiernan, Ben Adams, Jonas Edgeworth, Elias Manousos, Joseph Linn
-
Patent number: 10750166Abstract: An abnormality detection apparatus for detecting an abnormality of a camera to be mounted on a mobile body includes a processor and associated memory configured to perform a determination process of determining a presence or absence of the abnormality of the camera based on a temporal change of a position of a feature point that is extracted from a frame image photographed by the camera and suppress a gain change in an Automatic Gain Control (“AGC”) circuit of the camera when the determination process is performed.Type: GrantFiled: August 30, 2019Date of Patent: August 18, 2020Assignee: DENSO TEN LimitedInventors: Naoshi Kakita, Kohji Ohnishi, Takayuki Ozasa, Teruhiko Kamibayashi
-
Patent number: 10740598Abstract: A multi-modal emotion recognition system is disclosed. The system includes a data input unit for receiving video data and voice data of a user, a data pre-processing unit including a voice pre-processing unit for generating voice feature data from the voice data and a video pre-processing unit for generating one or more face feature data from the video data, a preliminary inference unit for generating situation determination data as to whether or not the user's situation changes according to a temporal sequence based on the video data. The system further comprises a main inference unit for generating at least one sub feature map based on the voice feature data or the face feature data, and inferring the user's emotion state based on the sub feature map and the situation determination data.Type: GrantFiled: November 26, 2018Date of Patent: August 11, 2020Assignee: GENESIS LAB, INC.Inventors: Dae-Hun Yoo, Young-Bok Lee
-
Patent number: 10726339Abstract: Systems and methods for recognizing an analogous case from a knowledge base including a plurality of candidate cases are disclosed. The system may include a data receiver to receive a representation of a target case, and a microprocessor coupled to the data receiver to generate a plurality of target attributes from the representation of the target case. The microprocessor may query the knowledge base to recognize the analogous case similar to the target case in information content using the target attributes and a plurality of attribute memories each including first and second attributes and an inter-attribute contextual representation of interactions between the first and second attributes in a context of the plurality of candidate cases. The system may include an output circuit to output the recognized analogous case to a user or a process.Type: GrantFiled: July 1, 2016Date of Patent: July 28, 2020Assignee: Intel CorporationInventor: Ali Ashrafi
-
Patent number: 10726294Abstract: Techniques are disclosed for generating logical sensors for an image driver. The image driver monitors values corresponding to at least a first feature in one or more regions of a first image in a stream of images received by a first sensor. The image driver identifies at least a first correlation between at least a first and second value of the monitored values. The image driver generates a logical sensor based on the identified correlations. The logical sensor samples one or more features corresponding to the identified correlation from a second image in the stream of images.Type: GrantFiled: July 5, 2018Date of Patent: July 28, 2020Assignee: Intellective Ai, Inc.Inventors: Kishor Adinath Saitwal, Lon W. Risinger, Wesley Kenneth Cobb
-
Patent number: 10719519Abstract: A method of operation of a navigation system includes: determining a search context with a control unit for identifying the search context where a search request is made; determining a result pattern including a word complete over an autosuggestion based on the search context; and generating a search result including a suggestive component based on the result pattern for displaying on a device.Type: GrantFiled: November 9, 2015Date of Patent: July 21, 2020Assignee: Telenav, Inc.Inventor: Eric Wood
-
Patent number: 10706581Abstract: An image processing apparatus estimates obverse and reverse pairs as obverse and reverse images of a plurality of cards even if positions of obverse and reverse images of respective cards shift when a user turns cards upside down to scan reverse images when scanning obverse and reverse images of cards and associating obverse and reverse images of cards with each other as obverse and reverse pairs, and presents estimated pairs to the user. A first image and second image are acquired to extract first and second rectangular images and central coordinate values thereof from acquired first and second images. When the central coordinate value extracted from the acquired second image is located within a predetermined distance from the central coordinate value extracted from the acquired first image, it is discriminated that the first rectangular image and second rectangular image as a combination serving as an obverse and reverse pair.Type: GrantFiled: November 21, 2017Date of Patent: July 7, 2020Assignee: CANON KABUSHIKI KAISHAInventor: Takashi Miyauchi
-
Patent number: 10699507Abstract: A method of verifying an authenticity of a printed item includes: photographing the printed item to obtain a photographic image of the printed item, retrieving reference data of the printed item, the reference data including a reference image of the printed item, determining a test noise parameter from the photographic image of the printed item, determining a reference noise parameter from the reference image, comparing the test noise parameter of the photographic image of the printed item to the reference noise parameter of the reference image, and determining an authenticity of the printed item from a result of the comparing. The determining the authenticity of the printed item from the result of the comparing may include establishing from the reference noise parameter of the reference image and the test noise parameter of the printed item.Type: GrantFiled: April 11, 2016Date of Patent: June 30, 2020Assignee: FILIGRADE B.V.Inventor: Johannes Bernardus Kerver
-
Patent number: 10679047Abstract: An object recognition system includes a parameter generator for generating a parameter that indicates whether an object depicted in an image pair is the same or different object, and a pose difference for the image pair and a parameter refiner for refining the parameter, and an applicator for applying the refined parameter to object recognition.Type: GrantFiled: December 29, 2017Date of Patent: June 9, 2020Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Rogerio Schmidt Feris, Minkyong Kim, Clifford A. Pickover
-
Patent number: 10664695Abstract: A system, method and computer program product for managing typesetting of digital ink structured content on computing devices. Each computing device has a processor and at least one system application for recognizing handwriting input under control of the processor. The system application determines dimensional information of at least digital ink text elements of structured content, calculates a first font size for each typeset ink text element respectively corresponding to the digital ink text elements based on at least part of the dimensional information, categorizes the typeset ink text elements into one or more categories of the structured content, determines a second font size for each typeset ink text element based on the first font size of each typeset ink text element of the respective category, and display, on a display associated with the computing device, the typeset ink text elements at the respective determined second font sizes.Type: GrantFiled: March 22, 2017Date of Patent: May 26, 2020Assignee: MYSCRIPTInventors: Fabien Ric, Robin Melinand, Romain Bednarowicz
-
Patent number: 10650646Abstract: This disclosure relates to method of enhancing the three-dimensional detection range of a vision-based, single camera intrusion detection system within a tensile test machine or other materials testing machine. Illumination sources are offset from the camera and provide a cones of illumination which intersect with the conical viewing zone of the camera thereby defining a detection zone. When objects intrude into these conical regions, a shadow is cast. The shadow is detected by the camera. The detection of the intrusion is typically used as a safety function to deactivate at least part of the function of the materials testing machine.Type: GrantFiled: December 5, 2018Date of Patent: May 12, 2020Assignee: ILLINOIS TOOL WORKS INC.Inventors: Roy Allen, Stephen McMahon, Zachary Harvey
-
Patent number: 10650041Abstract: Systems and methods of verifying the results of an initial image recognition process are presented. A verification engine can receive a set of candidate images corresponding to the results of an image recognition process performed on a captured query image. The verification engine can determine an appropriate verification technique to apply to the images of the candidate set, and classify, re-rank or otherwise re-organize the candidate set such that the best match from the candidate set is confirmed as a proper match.Type: GrantFiled: May 20, 2019Date of Patent: May 12, 2020Assignee: Nant Holdings IP, LLCInventors: Mustafa Jaber, Bing Song, Jeremi Sudol
-
Patent number: 10607326Abstract: An automated system and method for retaining images in a smart phone are disclosed. The system may then determine a no-reference quality score of the image using a PIQUE module. The PIQUE module utilizes block level features of the image to determine the no-reference quality score. The system may present the image and the no-reference quality score to the user and accept a feedback towards quality of the image. The system may utilize a supervised learning model for continually learning a user's perception of quality of the image, the no-reference quality score determined by the PIQUE module, and the user feedback. Based on the learning, the supervised learning model may adapt the no-reference quality score and successively the image may either be retained or isolated for deletion, based on the adapted quality score and a predefined threshold range.Type: GrantFiled: October 5, 2017Date of Patent: March 31, 2020Assignee: Uurmi Systems PVT LTDInventors: Shanti Swarup Medasani, Sumohana S Channappayya, Venkatanath Neeluri, Maruthi Chandrasekhar Bhatlapenumarti
-
Patent number: 10592774Abstract: A system for identifying in an image an object that is commonly found in a collection of images and for identifying a portion of an image that represents an object based on a consensus analysis of segmentations of the image. The system collects images of containers that contain objects for generating a collection of common objects within the containers. To process the images, the system generates a segmentation of each image. The image analysis system may also generate multiple segmentations for each image by introducing variations in the selection of voxels to be merged into a segment. The system then generates clusters of the segments based on similarity among the segments. Each cluster represents a common object found in the containers. Once the clustering is complete, the system may be used to identify common objects in images of new containers based on similarity between segments of images and the clusters.Type: GrantFiled: August 11, 2017Date of Patent: March 17, 2020Assignee: Lawrence Livermore National Security, LLCInventors: Peer-Timo Bremer, Hyojin Kim, Jayaraman J. Thiagarajan
-
Patent number: 10593425Abstract: A device obtains prescription information relating to a medication in a container. The device causes a camera device of the device to obtain image data relating to the medication and a weighing device of the device to obtain weight data relating the medication. The device sends the prescription information, the image data, and the weight data to a different device to cause the different device to verify the medication using a machine learning model. The device receives information concerning the medication and automatically generates, based on the information concerning the medication, a message concerning the medication, wherein the message includes instructions on how much of the medication a user of the device is to take. The device causes the device or an additional device to present the message.Type: GrantFiled: February 14, 2019Date of Patent: March 17, 2020Assignee: Accenture Global Solutions LimitedInventors: Andrew J. Truscott, Ethan Bischoff, Christopher Donnelly, Jean M. Becker
-
Patent number: 10593057Abstract: With the inventive technology, wound measurement is performed, but without the patient wound, or the skin near the patient wound, needing to have an object physically placed thereon. The patient wound and patient skin near the wound are spared contact with a ruler, marker, grid, and spared the wound and area near the wound being directly physically worked-on.Type: GrantFiled: December 21, 2017Date of Patent: March 17, 2020Assignee: DERMAGENESIS, LLCInventors: Tianning Xu, Ran Cohen, Alexander Steinberg
-
Patent number: 10586334Abstract: A method and system for segmenting a plurality of images. The method comprises the steps of segmenting the image through a novel clustering technique that is, generating a composite depth map including temporally stable segments of the image as well as segments in subsequent images that have changed. These changes may be determined by determining one or more differences between the temporally stable depth map and segments included in one or more subsequent frames. Thereafter, the portions of the one or more subsequent frames that include segments including changes from their corresponding segments in the temporally stable depth map are processed and are combined with the segments from the temporally stable depth map to compute their associated disparities in one or more subsequent frames. The images may include a pair of stereo images acquired through a stereo camera system at a substantially similar time.Type: GrantFiled: January 7, 2014Date of Patent: March 10, 2020Assignee: Edge 3 Technologies, Inc.Inventors: Tarek El Dokor, Joshua King, Jordan Cluster, James Edward Holmes
-
Patent number: 10579896Abstract: A mark detection system and method is provided. The system includes a memory having computer-readable instructions stored therein. The system further includes an image processor configured to execute the computer-readable instructions to access an image of a document and process the image to generate a binarized image. The image processor is further configured to extract components of the binarized image using a connected-component labelling algorithm. Furthermore, the image processor is configured to analyze features of the extracted components to detect one or more marks in the document.Type: GrantFiled: January 12, 2018Date of Patent: March 3, 2020Assignee: NEWGEN SOFTWARE TECHNOLOGIES LIMITEDInventors: Jindal Abhishek, Lal Puja
-
Patent number: 10580101Abstract: A method and an apparatus are provided for screenshot processing. The method includes: receiving a screenshot instruction; capturing a target image according to the screenshot instruction; acquiring interface jump information of a display interface displaying the target image, wherein the interface jump information enables the terminal to jump back to the display interface or an application containing the display interface; and storing the target image and the interface jump information correspondingly.Type: GrantFiled: March 19, 2018Date of Patent: March 3, 2020Assignee: Beijing Xiaomi Mobile Software Co., Ltd.Inventors: Mingze Sun, Yifei Pei