Template Matching (e.g., Specific Devices That Determine The Best Match) Patents (Class 382/209)
  • Patent number: 10313337
    Abstract: A method in one example implementation includes extracting a plurality of data elements from a record of a data file, tokenizing the data elements into tokens, and storing the tokens in a first tuple of a registration list. The method further includes selecting one of the tokens as a token key for the first tuple, where the token is selected because it occurs less frequently in the registration list than each of the other tokens in the first tuple. In specific embodiments, at least one data element is an expression element having a character pattern matching a predefined expression pattern that represents at least two words and a separator between the words. In other embodiments, at least one data element is a word defined by a character pattern of one or more consecutive essential characters. Other specific embodiments include determining an end of the record by recognizing a predefined delimiter.
    Type: Grant
    Filed: September 11, 2017
    Date of Patent: June 4, 2019
    Assignee: McAfee, LLC
    Inventors: Ratinder Paul Singh Ahuja, William J. Deninger
  • Patent number: 10289375
    Abstract: A system and related operating methods that achieve shared screen verification are presented here. One operating method begins by establishing a desktop sharing session between a publisher device and a viewer device, during which the publisher device renders a publisher display and the viewer device renders a viewer display that corresponds to the publisher display. The method continues by capturing first framebuffer data for a frame of the publisher display, capturing second framebuffer data for the corresponding frame of the viewer display. The method processes the first framebuffer data and/or the second framebuffer data to obtain processed framebuffer data having a consistent display resolution. Thereafter, the method compares the processed second framebuffer data to the processed first framebuffer data to obtain a measure of quality.
    Type: Grant
    Filed: April 20, 2016
    Date of Patent: May 14, 2019
    Assignee: salesforce.com, inc.
    Inventor: Dipak Patil
  • Patent number: 10289894
    Abstract: A method for controlling unlocking includes the following operations. A reference feature point of a finger of a user is acquired when a touch operation on a fingerprint recognition sensor of a terminal is detected. A matching process is executed between the reference feature point set and a first feature point set, the first feature point set includes at least one feature point subset of a second feature point set, the second feature point set includes feature points of the entire or a majority portion of the finger. The terminal is unlocked when the reference feature point set is matched with the first feature point set.
    Type: Grant
    Filed: May 24, 2017
    Date of Patent: May 14, 2019
    Assignee: Guangdong Oppo Mobile Telecommunications Corp., Ltd.
    Inventor: Yibao Zhou
  • Patent number: 10275655
    Abstract: In accordance with one embodiment, an intelligent video thumbnail selection and generation tool may select a relevant and visually stimulating image from a video file and generate a thumbnail including the image. The image may be selected by computing a relevancy metric for an image in the file based on one or more selected relevant features, and comparing that relevancy metric with the metric of at least one other image in the file. In another embodiment, a series of images in a video file may be divided into shots. One of the shots may be selected based on a shot relevancy metric and a key image from the shot may be selected as a thumbnail based on a key image relevancy metric, where the shot relevancy metric and the key image relevancy metrics may be computed based on one or more relevant content features.
    Type: Grant
    Filed: November 27, 2017
    Date of Patent: April 30, 2019
    Assignee: BroadbandTV, Corp.
    Inventors: Shahrzad Rafati, Mehrdad Fatourechi, Lino Evgueni Coria Mendoza
  • Patent number: 10262402
    Abstract: A curved line correction apparatus includes a correction target receiving unit that receives selection of a correction target point when an instruction mark is placed on an arbitrary point on a curved line composed of a plurality of arranged points, a correction target range setting unit that sets a certain range of the curved line, including the correction target point, as a correction target range, and a correction unit that corrects a portion of the curved line within the correction target range by moving the correction target point and a point within the correction target range when movement of the instruction mark is received, in which the correction target range setting unit changes the size of the correction target range when an instruction input to change the range is received with the instruction mark being placed on the correction target point.
    Type: Grant
    Filed: July 21, 2015
    Date of Patent: April 16, 2019
    Assignee: FUJIFILM Corporation
    Inventor: Kenta Yamada
  • Patent number: 10262232
    Abstract: Disclosed herein are methods and systems for generating a fingerprint for verification of a reference object, such as a layer or ply during a composite laminate layup procedure. An exemplary method includes generating a plurality of images of the reference object from a plurality of angles, removing at least one lighting effect from at least one reference image to generate at least one processed image, generating a reference fingerprint for the reference object based on the at least one processed image, generating at least one candidate image of a candidate object, generating a candidate fingerprint for the candidate object based on the at least one candidate image, comparing the candidate fingerprint and the reference fingerprint to determine whether a correlation exists between the candidate fingerprint and the reference fingerprint, and generating an alert based on the comparison of the candidate fingerprint and the reference fingerprint.
    Type: Grant
    Filed: April 30, 2018
    Date of Patent: April 16, 2019
    Assignee: The Boeing Company
    Inventors: Andrew Klimovski, Martin A. Szarski
  • Patent number: 10248625
    Abstract: Methods and systems for Assurance-enabled Linde Buzo Gray (ALBG) data clustering is described herein. In an implementation, a user model data from a database available to the processor is obtained. The user model data comprises data elements or users, each of which corresponds to features and feature values associated with the users. These data elements of the user model data are segmented into clusters using our segmentation approach with an initial accuracy criterion parametric value and the output is captured as segment data. The segment data output is checked for initial pareto validity. If successful, iterative segmentation run with incremental accuracy criterion using parameterized value is performed till the segmented clusters are determined valid against pareto validity check. The last successful pareto valid segmented cluster data is considered as the finalized segment output data.
    Type: Grant
    Filed: February 9, 2016
    Date of Patent: April 2, 2019
    Assignee: Tata Consultancy Services Limited
    Inventors: Sandip Jadhav, Akshay Kumar Singhal, Mohan Raj Velayudhan Kumar, Rahul Ramesh Kelkar, Harrick Mayank Vin
  • Patent number: 10250943
    Abstract: A method and apparatus for managing content, where content received or generated in a device is automatically grouped and managed in real-time, and a computer readable recording medium having recorded thereon a program for executing the method which includes detecting whether content is received or generated by a device, grouping the received or generated content with another received or generated content, and displaying the grouped content on the device, wherein the another content includes at least one content received or generated before the detected received or generated content.
    Type: Grant
    Filed: September 6, 2012
    Date of Patent: April 2, 2019
    Assignee: Samsung Electronics Co., Ltd
    Inventors: Yong-gook Park, Bum-joo Lee, Say Jang, Ji-su Jung, Seung-hwan Hong
  • Patent number: 10235687
    Abstract: The present disclosure extends to methods, systems, and computer program products for generating attribute tables for holding and calculating attributes related to location and distance while a corresponding business plan is in an approval process.
    Type: Grant
    Filed: March 14, 2014
    Date of Patent: March 19, 2019
    Assignee: Walmart Apollo, LLC
    Inventors: Nirup Pothireddy, Bharat Khare, Anand Chinnakannan, Erik Cornelsen
  • Patent number: 10223250
    Abstract: A system for checking data for errors, the system comprising a checking module operable to check tuples of data stored in a target database for errors, the tuples in the target database originating from the output of at least one query transformation module which applies a query transformation to tuples of data from at least one data source an identification module operable to identify a problematic tuple from a data source that produces an error in the target database, the identification module being operable to quantify the contribution of the problematic tuple in producing the error in the target database, and a description generation module operable to generate a descriptive query which represents at least one of errors identified by the checking module in the target database which are produced by the at least one query transformation module, and problematic tuples identified in a data source by the identification module.
    Type: Grant
    Filed: May 27, 2014
    Date of Patent: March 5, 2019
    Assignee: QATAR FOUNDATION
    Inventors: Mourad Ouzzani, Paolo Papotti, Ihab Francis Ilyas Kaldas, Anup Chalmalla
  • Patent number: 10210381
    Abstract: A facial recognition authentication on a device having a camera may operate with multiple enrollment profiles on the device. Multiple enrollment profiles may include separate profiles for different appearances of a user and/or separate profiles for different users authorized to use the device. The enrollment profiles may be generated using an enrollment process where the enrollment process is operated separately to generate each of the different enrollment profiles. During the facial recognition authentication process, a user may unlock the device by having a matching score for image(s) captured of the user that that exceeds an unlock threshold for at least one of the enrollment profiles. The user may have a matching score that exceeds the unlock threshold for multiple enrollment profiles. Each enrollment profile unlocks the device for the user may be updated using a template update process that operates independently for each enrollment profile.
    Type: Grant
    Filed: July 31, 2018
    Date of Patent: February 19, 2019
    Assignee: Apple Inc.
    Inventors: Eslam A. Mostafa, Thorsten Gernoth, Kelsey Y. Ho
  • Patent number: 10192424
    Abstract: Described is a technology by which a mobile device outputs an alert for a reminder based upon a current location of the mobile device with respect to an entity (person, place or thing) associated with the reminder. The reminders may be maintained and provided by a service. Each reminder includes a reference to target-related information. When the device moves to within a threshold proximity of the target, and other criteria (e.g., time of day) is satisfied, an alert is output by the device. A user may gesture with a device towards an entity to set a reminder associated with that entity, or to get any reminder associated with that entity. A device may also get reminders by scanning or image processing, e.g., by reading a barcode associated with a product to get any reminders associated with that product.
    Type: Grant
    Filed: September 17, 2013
    Date of Patent: January 29, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Vassilii Khachaturov, Lev Novik, Moe Khosravy
  • Patent number: 10182891
    Abstract: The invention relates to a dentel device for the treatment of a dental restoration part, comprising at least one operating program, a storage of the dental device and at least one detection device for at least one object. The detection device can detect data of the object and this data, in particular together with an operating program associated with the object, can be stored in a storage of the dental device or can be compared to the data of objects which have been stored in advance in the storage of the dental device. The dental device, depending on the comparison result of the data of a detected object with the data of objects which have been stored in advance in the storage of the dental device, starts the associated operating program or shows it for selection.
    Type: Grant
    Filed: January 24, 2013
    Date of Patent: January 22, 2019
    Assignee: Ivoclar Vivadent AG
    Inventors: Michael Brotzge, Johannes Lorünser, Robert Grünenfelder, Philipp Kettner
  • Patent number: 10176403
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for shape detection are disclosed. In one aspect, a method includes the actions of generating a shape model that includes a predetermined shape with a predetermined scale and predetermined orientation. The actions further include receiving an image. The actions further include identifying edges that are parallel to the side of the shape model and that are a predetermined distance from the side of the shape model. The actions further include selecting a plurality of edges that likely correspond to edges of a shape that is similar to the shape model. The actions further include determining a fit score between the plurality of edges and each shape of a plurality of shapes that are similar to the shape model. The actions further include identifying a particular shape in the image that most closely fits the shape model.
    Type: Grant
    Filed: May 24, 2017
    Date of Patent: January 8, 2019
    Assignee: MorphoTrust USA, LLC
    Inventor: Brian K. Martin
  • Patent number: 10158911
    Abstract: Systems and methods are disclosed herein for detecting duplicate copies of a media asset and deleting or offloading one of the duplicate copies to different user devices. Specifically, a media guidance application, implemented at user equipment, may be used to record or store media assets from different media sources. The media guidance application may detect a duplicate copy of a previously stored media asset by comparing various attributes of the media asset. After detecting a duplicate copy of a media asset, the media guidance application may determine which of the duplicate copies of the same media asset is to be deleted, or to be transmitted for storage at a different user device.
    Type: Grant
    Filed: December 14, 2017
    Date of Patent: December 18, 2018
    Assignee: Rovi Guides, Inc.
    Inventors: Lopamudra Sengupta, Milan Indu Patel
  • Patent number: 10157332
    Abstract: An image creation and editing tool can use the data produced from training a neural network to add stylized representations of an object to an image. An object classification will correspond to an object representation, and pixel values for the object representation can be added to, or blended with, the pixel values of an image in order to add a visualization of a type of object to the image. Such an approach can be used to add stylized representations of objects to existing images or create new images based on those representations. The visualizations can be used to create patterns and textures as well, as may be used to paint or fill various regions of an image. Such patterns can enable regions to be filled where image data has been deleted, such as to remove an undesired object, in a way that appears natural for the contents of the image.
    Type: Grant
    Filed: June 6, 2016
    Date of Patent: December 18, 2018
    Assignee: A9.com, Inc.
    Inventors: Douglas Ryan Gray, Alexander Li Honda, Edward Hsiao
  • Patent number: 10152637
    Abstract: A method of segmenting a video sequence. A segment score is determined for each of a plurality of fixed length segments of the video sequence. Each of the segment scores provide a score for a plurality of actions associated with a corresponding fixed length segment. A current segment is selected from the segments of the video sequence. The segment score is selected for a further one of the segments, the further segment being disjoint with the current segment and being used to provide information about actions that were classified outside the current segment. A further segment score is determined for the current segment according to the selected segment score. The video is segmented based on the determined further segment score.
    Type: Grant
    Filed: September 14, 2016
    Date of Patent: December 11, 2018
    Assignee: Canon Kabushiki Kaisha
    Inventor: Nagita Mehrseresht
  • Patent number: 10149001
    Abstract: Systems and methods are disclosed herein for detecting duplicate copies of a media asset and deleting or offloading one of the duplicate copies to different user devices. Specifically, a media guidance application, implemented at user equipment, may be used to record or store media assets from different media sources. The media guidance application may detect a duplicate copy of a previously stored media asset by comparing various attributes of the media asset. After detecting a duplicate copy of a media asset, the media guidance application may determine which of the duplicate copies of the same media asset is to be deleted, or to be transmitted for storage at a different user device.
    Type: Grant
    Filed: December 14, 2017
    Date of Patent: December 4, 2018
    Assignee: Rovi Guides, Inc.
    Inventors: Lopamudra Sengupta, Milan Indu Patel
  • Patent number: 10145669
    Abstract: A method and system are proposed to obtain a reduced speckle noise image of a subject from optical coherence tomography (OCT) image data of the subject. The cross sectional images each comprise a plurality of scan lines obtained by measuring the time delay of light reflected, in a depth direction, from optical interfaces within the subject. The method comprises two aligning steps. First the cross sectional images are aligned, then image patches of the aligned cross sectional images are aligned to form a set of aligned patches. An image matrix is then formed from the aligned patches; and matrix completion is applied to the image matrix to obtain a reduced speckle noise image of the subject.
    Type: Grant
    Filed: June 16, 2015
    Date of Patent: December 4, 2018
    Assignees: AGENCY FOR SCIENCE, TECHNOLOGY AND RESEARCH, KABUSHIKI KAISHA TOPCON
    Inventors: Jun Cheng, Jiang Liu, Lixin Duan, Yanwu Xu, Wing Kee Damon Wong, Masahiro Akiba
  • Patent number: 10133811
    Abstract: A data arrangement apparatus executes a process request on data stored in a database, calculates similarity of a process in a combination of the process request and the data, divides the data in such a manner as to distribute the similarity and processes a process request accepted for the divided data.
    Type: Grant
    Filed: March 9, 2016
    Date of Patent: November 20, 2018
    Assignee: FUJITSU LIMITED
    Inventors: Yui Noma, Makiko Konoshima
  • Patent number: 10133959
    Abstract: Disclosed are a quantum system-based image pattern recognition computation apparatus and method for machine vision and a quantum system-based machine vision apparatus. The computation apparatus recognizes patterns between images in machine vision by using a quantum system. The computation apparatus includes a modeling unit and an interpretation unit. The modeling unit sets up an objective function based on the similarity between a first pattern derived from the relationships between points of interests of a first image and a second pattern derived from the relationships between points of interests of a second image. The interpretation unit finds an optimum first pattern and an optimum second pattern, in which the similarity between the first pattern and the second pattern is optimized, by interpreting a final quantum state obtained through an adiabatic evolution process of the quantum system in which the objective function is optimized.
    Type: Grant
    Filed: October 14, 2016
    Date of Patent: November 20, 2018
    Assignee: University of Seoul Industry Cooperation Foundation
    Inventor: Do Yeol Ahn
  • Patent number: 10127229
    Abstract: Methods of organizing documents by reclassification and clustering are disclosed. In one embodiment, a method of clustering electronic documents of a document corpus includes comparing, by a computer, each individual electronic document in the document corpus with each other electronic document in the document corpus, thereby forming document pairs. The electronic documents of the document pairs are compared by calculating a similarity value with respect to the electronic documents of a document pair, associating the similarity value with both electronic documents of the document pair, and applying a clustering algorithm to the document corpus using the similarity values to create a plurality of hierarchical clusters. The similarity value is based on a plurality of attributes of the electronic documents in the document corpus.
    Type: Grant
    Filed: April 23, 2014
    Date of Patent: November 13, 2018
    Assignee: Elsevier B.V.
    Inventors: Bob Schijvenaars, Marius Doornenbal
  • Patent number: 10120624
    Abstract: The printing system includes a handwritten character data extraction unit, a sample character data retrieval unit, a determination unit, a character practice worksheet creating unit, and a print control unit. The determination unit determines whether the matching ratio between a handwritten character extracted by the handwritten character data extraction unit and a sample character retrieved by the sample character data retrieval unit is equal to a first ratio or lower. If the determination unit determines that the matching ratio is equal to the first ratio or lower, the character practice worksheet creating unit creates a character practice worksheet containing the sample character that matches the handwritten character and a blank cell for handwriting practice formed next to the sample character. The print control unit controls the printing unit to print the character practice worksheet created by the character practice worksheet creating unit on paper.
    Type: Grant
    Filed: May 31, 2017
    Date of Patent: November 6, 2018
    Assignee: KYOCERA DOCUMENT SOLUTIONS INC.
    Inventor: Takashi Harada
  • Patent number: 10104091
    Abstract: In authentication based on an image region read from a surface of a target object, authentication based on a position corresponding to the image region is executed. An authenticating server 2 receives an image region as an authentication target read from a surface of a target object possessed by a user together with an authentication request from the user, identifies a position corresponding to the image region as the authentication target and one reference image region corresponding to the image region as the authentication target in a plurality of previously stored reference image regions read from respective surfaces of a plurality of target objects, and executes authentication in response to the authentication request based on the identified position.
    Type: Grant
    Filed: May 3, 2016
    Date of Patent: October 16, 2018
    Assignee: FUJI XEROX CO., LTD.
    Inventors: Tetsuya Kimura, Kensuke Ito
  • Patent number: 10095677
    Abstract: Disclosed are techniques and systems to detect a layout of a source document. A process may include receiving content from a first page and a second page of the source document, designating sections in each page along a first direction of the page, and assigning similar sections to a group. For the group, the process may proceed by dividing sections for each page into discrete portions associated with 2D coordinate areas, and identifying sets of 2D coordinate areas for the discrete portions that contain content. The number of times each portion contains some content may be compared to a threshold to determine a layout of the group of sections.
    Type: Grant
    Filed: June 26, 2014
    Date of Patent: October 9, 2018
    Assignee: Amazon Technologies, Inc.
    Inventors: Vasant Manohar, Eric Allen Menninga, Ashley Alonzo Ricardo Karl Mitchell, Joseph King, Mugunthan Govindaraju
  • Patent number: 10083366
    Abstract: Edge-based recognition systems and methods are presented. Edges of the object are identified from the image data based on co-circularity of edgels, and edge-based descriptors are constructed based on the identified edges. The edge-based descriptors along with additional perception metrics are used to obtain a list of candidate objects matched with the edge-based descriptors. Through various filtering processes and verification processes, false positive candidate objects are further removed from the list to determine the final candidate object.
    Type: Grant
    Filed: April 14, 2017
    Date of Patent: September 25, 2018
    Assignee: Nant Holdings IP, LLC
    Inventors: Bing Song, Matheen Siddiqui
  • Patent number: 10003934
    Abstract: A method for providing messaging-related information to a mobile device is discussed. The method includes receiving from the mobile device a request for messaging-related information, using the request to identify a device-type indication for the mobile device, identifying one or more presentation parameters for presenting the messaging-related content properly on the mobile device, and transmitting the messaging-related content to the mobile device in a format corresponding to the one or more parameters.
    Type: Grant
    Filed: June 20, 2014
    Date of Patent: June 19, 2018
    Assignee: Google LLC
    Inventors: Abhijit Kalamkar, Elad Gil, Keith J. Coleman, Mark Slee, Zhanna Shamis
  • Patent number: 9998763
    Abstract: A system and method for transmitting compressed image data includes an encoder, responsive to received image data representing an image, for minimizing a space-spatial frequency of the image data by applying a predetermined orthogonal function thereto to generate a mathematical representation of the image data and extracting coefficients of the mathematical representation of the image data. A transmitter transmits the coefficients of the image data from a first location to a second location. A receiver receives the transmitted coefficients of the image data at the second location from the first location. A decoder recreates the mathematical representation of the image data at the second location responsive to the received coefficients and the predetermined orthogonal function and generates the image data from the recreated mathematical representation of the image data.
    Type: Grant
    Filed: March 31, 2016
    Date of Patent: June 12, 2018
    Assignee: NxGen Partners IP, LLC
    Inventors: Solyman Ashrafi, Roger D. Linquist
  • Patent number: 9984453
    Abstract: The present invention provides a measurement apparatus for measuring a position of a mark formed on a substrate, the apparatus including a detector configured to detect the mark to generate a detection signal, and a processor configured to process the generated detection signal to obtain a position of the mark, wherein the processor is configured to limit a range of the detection signal to be processed to obtain the position of the mark based on a statistic representing dispersion of a plurality of the position obtained with respect to a plurality of the mark.
    Type: Grant
    Filed: October 27, 2015
    Date of Patent: May 29, 2018
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Toru Sugiyama
  • Patent number: 9974466
    Abstract: A system for early warning of health status decline includes at least one energy emitter configured to emit energy onto a field-of-view that contains an individual, and at least one energy sensor configured to capture reflected energy from within the field-of-view. A spatial measurement module calculates spatial measurements of a surface portion of the body of the individual when the individual is either stationary or moving about in real-time, based on data from the energy sensor. A comparator module detects deviations in measurements from baseline values indicative of a deterioration in health status of the individual.
    Type: Grant
    Filed: October 3, 2012
    Date of Patent: May 22, 2018
    Assignee: Atlas5D, Inc.
    Inventor: Zebadiah M. Kimmel
  • Patent number: 9965700
    Abstract: Disclosed herein are methods and systems for generating a fingerprint for verification of a reference object, such as a layer or ply during a composite laminate layup procedure. An exemplary method includes generating a plurality of images of the reference object from a plurality of angles, removing at least one lighting effect from at least one reference image to generate at least one processed image, generating a reference fingerprint for the reference object based on the at least one processed image, generating at least one candidate image of a candidate object, generating a candidate fingerprint for the candidate object based on the at least one candidate image, comparing the candidate fingerprint and the reference fingerprint to determine whether a correlation exists between the candidate fingerprint and the reference fingerprint, and generating an alert based on the comparison of the candidate fingerprint and the reference fingerprint.
    Type: Grant
    Filed: April 18, 2017
    Date of Patent: May 8, 2018
    Assignee: The Boeing Company
    Inventors: Andrew Klimovski, Martin A. Szarski
  • Patent number: 9959481
    Abstract: An image processing apparatus for processing an image acquired by imaging a living body includes: a blood vessel candidate region extraction unit configured to extract a plurality of blood vessel candidate regions from the image; an identical blood vessel candidate region extraction unit configured to extract, from among the plurality of blood vessel candidate regions, a blood vessel candidate region group estimated to form a line shape when integrated, as an identical blood vessel candidate region; an evaluation value calculation unit configured to calculate one or more kinds of evaluation values for evaluating a likelihood that the identical blood vessel candidate region corresponds to an identical blood vessel; and a blood vessel region discrimination unit configured to discriminate whether or not the identical blood vessel candidate region forms an identical blood vessel region, based on the evaluation values.
    Type: Grant
    Filed: August 20, 2015
    Date of Patent: May 1, 2018
    Assignee: OLYMPUS CORPORATION
    Inventors: Makoto Kitamura, Yamato Kanda, Toshiya Kamiyama
  • Patent number: 9942543
    Abstract: The present application provides a user configurable test system for set-top boxes (STB) and other consumer devices providing video output. In particular, it provides for a method of improving an Optical Character Recognition (OCR) process in such test systems.
    Type: Grant
    Filed: October 31, 2016
    Date of Patent: April 10, 2018
    Assignee: Accenture Global Solutions Limited
    Inventor: Liam Friel
  • Patent number: 9928284
    Abstract: In various embodiments, a system and method for recognizing and integrating datasets disclosed. The system comprises a processor and a memory unit. A training dataset is developed that forms the basis to measure similarities between and among the datasets. Incoming datasets are examined for features and a measurement is made to determine similarity with datasets in the training dataset. An estimate can be made of the probability that an incoming dataset contains specified attributes. The incoming dataset can be assigned an attribute based on the probability estimate.
    Type: Grant
    Filed: December 31, 2014
    Date of Patent: March 27, 2018
    Assignee: ZEPHYR HEALTH, INC.
    Inventor: Funmi Fapohunda
  • Patent number: 9916832
    Abstract: Techniques for leveraging a combination of audio-based and vision-based cues for voice command-and-control are provided. In one embodiment, an electronic device can identify one or more audio-based cues in a received audio signal that pertain to a possible utterance of a predefined trigger phrase, and identify one or more vision-based cues in a received video signal that pertain to a possible utterance of the predefined trigger phrase. The electronic device can further determine a degree of synchronization or correspondence between the one or more audio-based cues and the one or more vision-based cues. The electronic device can then conclude, based on the one or more audio-based cues, the one or more vision-based cues, and the degree of synchronization or correspondence, whether the predefined trigger phrase was actually spoken.
    Type: Grant
    Filed: February 18, 2016
    Date of Patent: March 13, 2018
    Assignee: Sensory, Incorporated
    Inventor: Todd F. Mozer
  • Patent number: 9898176
    Abstract: A system for creating an application for a portable electronic device includes: a template selector to select an application template from a repository of application templates; a step-by-step creator module to receive user input, and to insert the user input at one or more placeholders in said application; a button inserter to insert into said application code that causes said portable electronic device to contact a third party, via a pre-defined communication method, upon user selection of a displayed button.
    Type: Grant
    Filed: October 15, 2014
    Date of Patent: February 20, 2018
    Assignee: One Smart Star Ltd.
    Inventors: Hemy Tzubary, Yakov Shulman
  • Patent number: 9892114
    Abstract: The current document is directed to methods and systems for identifying symbols corresponding to symbol images in a scanned-document image or other text-containing image, with the symbols corresponding to Chinese or Japanese characters, to Korean morpho-syllabic blocks, or to symbols of other languages that use a large number of symbols for writing and printing. In one implementation, the methods and systems to which the current document is directed carry out an initial processing step on one or more scanned images to identify a subset of the total number of symbols frequently used in the scanned document image or images. One or more lists of graphemes for the language of the text are then ordered in most-likely-occurring to least-likely-occurring order to facilitate a second optical-character-recognition step in which symbol images extracted from the one or more scanned-document images are associated with one or more graphemes most likely to correspond to the scanned symbol image.
    Type: Grant
    Filed: October 7, 2014
    Date of Patent: February 13, 2018
    Assignee: ABBYY DEVELOPMENT LLC
    Inventor: Yuri Chulinin
  • Patent number: 9888147
    Abstract: An image processing apparatus includes: a text area extractor that extracts multiple text areas from image data including texts; a font size calculator that calculates the font sizes of characters in each text area; a complexity calculator that calculates the complexities of characters in each text; a necessary resolution calculator that calculates a necessary resolution for the each text area with reference to the font sizes and the complexities; a resolution determination portion that merges text areas into a layer if a difference in the necessary resolution between the text areas is equal to or less than a specified value and that determines a necessary resolution for the layer with reference to the necessary resolutions for the text areas constituting the layer; and a resolution adjustment portion that adjusts the necessary resolutions for the text areas constituting the layer to a value identical to the necessary resolution for the layer.
    Type: Grant
    Filed: August 23, 2016
    Date of Patent: February 6, 2018
    Assignee: KONICA MINOLTA, INC.
    Inventor: Takahiro Tsutsumi
  • Patent number: 9886629
    Abstract: Disclosed are various embodiments for digitally restoring content from a torn document. A computing device obtains an image of a document that has a tear. The computing device identifies portions of the image separated by a gap region representing the tear in the document. Content in the portions of the image adjacent to the gap region is then identified. The position of a portion of the image is incrementally adjusted to reduce the gap region without overlapping the portions. The position of the portion is adjusted to align the content along a boundary between the portions of the image.
    Type: Grant
    Filed: April 26, 2016
    Date of Patent: February 6, 2018
    Assignee: Adobe Systems Incorporated
    Inventors: Ajay Jain, Ram Bhushan Agrawal
  • Patent number: 9864912
    Abstract: A video camera is provided for video-based anomaly detection that includes at least one imaging sensor configured to capture video sequences in a workplace environment having a plurality of machines therein. The video camera further includes a processor. The processor is configured to generate one or more predictions of an impending anomaly affecting at least one item selected from the group consisting of (i) at least one of the plurality of machines and (ii) at least one operator of the at least one of the plurality of machines, using a Deep High-Order Convolutional Neural Network (DHOCNN)-based model applied to the video sequences. The DHOCNN-based model has a one-class SVM as a loss layer of the model. The processor is further configured to generate a signal for initiating an action to the at least one of the plurality of machines to mitigate expected harm to the at least one item.
    Type: Grant
    Filed: December 15, 2016
    Date of Patent: January 9, 2018
    Assignee: NEC Corporation
    Inventors: Renqiang Min, Dongjin Song, Eric Cosatto
  • Patent number: 9860400
    Abstract: A learning support device includes a storage portion which stores the images of model characters, an image reading portion which reads a practice sheet to generate image data, a determination portion which extracts, as an image of a determination target character, an image of a handwritten character present within the image data on the practice sheet, which acquires, from the storage portion, the image of the model character and which compares the image of the model character with the image of the determination target character so as to perform a pass/fail determination, a generation portion which generates image data on a report that includes result information indicating the result of the pass/fail determination and an output portion which outputs the report including the result information.
    Type: Grant
    Filed: April 12, 2016
    Date of Patent: January 2, 2018
    Assignee: KYOCERA Document Solutions Inc.
    Inventors: Sachiko Yoshimura, Hidehiko Akuta, Toshihide Higashimori, Yumi Nakagoshi
  • Patent number: 9858330
    Abstract: Representative implementations of devices and techniques provide a system for categorizing electronically stored information without the need for user input, direction, or guidance. In an implementation, the system determines meanings of input textual data items and groups of textual data items, identifies equivalent meanings between textual data items and between groups of textual data items, and outputs user-selected information that is categorized, indexed, and searchable.
    Type: Grant
    Filed: October 20, 2014
    Date of Patent: January 2, 2018
    Inventor: Joel E Henry
  • Patent number: 9846825
    Abstract: A method of generating a region-based representation of a document is disclosed. A global compositing sequence is generated based on a predetermined rule, using fill data and at least one compositing operation associated with a plurality of objects of the document, to form an object-based representation of the document. The region-based representation of the document is generated based on a further compositing sequence determined for regions formed using the object-based representation. The method also determines whether at least one of the regions satisfies the predetermined rule using a relative arrangement of the objects in the object-based representation. Where the region satisfies the predetermined rule, a reference to the global compositing sequence is created. Where the region does not satisfy the predetermined rule, a local compositing sequence is generated using fill data and compositing operations associated with the objects contributing to the region.
    Type: Grant
    Filed: December 16, 2014
    Date of Patent: December 19, 2017
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Krzysztof Adam Koziarz
  • Patent number: 9842275
    Abstract: An image processing device includes a processor including hardware, the processor being configured to calculate comparison result information through a comparison process performed on the results of a census transform process performed on a first image and the results of the census transform process performed on a second image, set weight information, calculate a cost using the comparison result information and the weight information, calculate the amount of disparity using the cost, set a first weight having as low degree of contribution to the cost on a neighboring pixel which is determined to be affected by noise to a large extent among a plurality of neighboring pixels, and set a second weight having a high degree of contribution to the cost on a neighboring pixel which is determined to be affected by noise to a small extent among the plurality of neighboring pixels.
    Type: Grant
    Filed: August 26, 2016
    Date of Patent: December 12, 2017
    Assignee: OLYMPUS CORPORATION
    Inventor: Asako Seki
  • Patent number: 9824683
    Abstract: A method of augmenting training data includes converting a feature sequence of a source speaker determined from a plurality of utterances within a transcript to a feature sequence of a target speaker under the same transcript, training a speaker-dependent acoustic model for the target speaker for corresponding speaker-specific acoustic characteristics, estimating a mapping function between the feature sequence of the source speaker and the speaker-dependent acoustic model of the target speaker, and mapping each utterance from each speaker in a training set using the mapping function to multiple selected target speakers in the training set.
    Type: Grant
    Filed: December 22, 2015
    Date of Patent: November 21, 2017
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Xiaodong Cui, Vaibhava Goel, Brian E. D. Kingsbury
  • Patent number: 9811735
    Abstract: Systems and methods are disclosed for computer vision and object detection by extracting tracks of moving objects on a set of video sequences; selecting a subset of tracks for training; rendering a composite of each selected track into a single image; labeling tracks using the rendered images; training a track classifier by supervised machine learning using the labeled tracks; applying the trained track classifier to the remainder of the tracks; and selecting tracks classified with a low confidence by the classifier.
    Type: Grant
    Filed: April 1, 2016
    Date of Patent: November 7, 2017
    Assignee: NEC Corporation
    Inventor: Eric Cosatto
  • Patent number: 9811916
    Abstract: The location of a user's head, for purposes such as head tracking or motion input, can be determined using a two-step process. In a first step, at least one image is captured including a representation of at least a portion of the user, with distance information also being obtained. The distance information can be used to segment the at least one image into a foreground portion, which then can be analyzed to recognize a head and shoulder signature of a user. In a second step, a contour of the foreground portion can be determined, and a center point of that contour determined. The distances from the center point to locations along the contour can be used to locate transition points associated with the head and shoulders. A center point of the portion of the contour between the transition points gives an approximation of the relative head position.
    Type: Grant
    Filed: September 25, 2013
    Date of Patent: November 7, 2017
    Assignee: Amazon Technologies, Inc.
    Inventor: Dmitri Yurievich Khokhlov
  • Patent number: 9813762
    Abstract: A computer implemented method for hashing an image is provided that includes: receiving a reference image frame; deriving an array of reference hash values to represent the reference image frame, wherein the array of reference hash values includes a first reference hash value, a second reference hash value, and a third reference hash value; receiving an test image frame; deriving an array of hash values to represent the test image frame, wherein the array of hash values includes a first test hash value, a second test hash value, and a third test hash value; subtracting the array of test hash values representing the test image frame from the array of reference hash values representing the reference image frame to produce a delta array, wherein the delta array is indicative of an area where the test image frame differs from the reference image frame.
    Type: Grant
    Filed: February 23, 2016
    Date of Patent: November 7, 2017
    Assignee: ARRIS Enterprises LLC
    Inventors: Gautam Babbar, Olga Malysheva, Pierre Brice, Dan Hillegass
  • Patent number: 9805266
    Abstract: A method and system for performing video content analysis based on two-dimensional image data and depth data are disclosed. Video content analysis may be performed on the two-dimensional image data, and then the depth data may be used along with the results of the video content analysis of the two-dimensional data for tracking and event detection.
    Type: Grant
    Filed: January 26, 2016
    Date of Patent: October 31, 2017
    Assignee: AVIGILON FORTRESS CORPORATION
    Inventors: Zhong Zhang, Gary W. Myers, Peter L. Venetianer
  • Patent number: 9799119
    Abstract: Embodiments of the present application relate to a method, apparatus, and system for detecting a specified image identifier. The method includes retrieving a target image to be detected from a predetermined area, binarizing the target image to be detected to obtain a target binary image to be detected, calibrating connected domains of the target binary image to be detected, successively retrieving image features of candidate connected domains, and comparing the image features corresponding to the candidate connected domains to image features of a standard specified identifier image, wherein the candidate connected domains are determined based at least in part on the calibration of the connected domains, and determining a candidate connected domain as the location of the specified identifier image based at least in part on the comparison of the image features corresponding to the candidate connected domains to image features of the standard specified identifier image.
    Type: Grant
    Filed: July 28, 2015
    Date of Patent: October 24, 2017
    Assignee: Alibaba Group Holding Limited
    Inventors: Gang Cheng, Rufeng Chu, Lun Zhang