Pattern Recognition Patents (Class 382/181)
  • Patent number: 10696525
    Abstract: A container crane control system includes: a first camera configured to be mounted to a container crane such that the first camera is rotatable only along a substantially vertical axis, implementing a tilt function of the first camera, the first camera being configured to provide a first video signal; a control device configured to tilt the first camera based on a current height of a load of the crane, to thereby track the load; and an operator terminal, being configured to receive the first video signal, for presentation to an operator and being configured to receive user input for controlling the crane, resulting in a crane control signal for provision to the control device. The control device may further be configured to receive the crane control signal from the operator terminal and to provide a corresponding control signal to control crane operation.
    Type: Grant
    Filed: October 30, 2017
    Date of Patent: June 30, 2020
    Assignee: ABB Schweiz AG
    Inventors: André Ryman, Peter Almhager
  • Patent number: 10681257
    Abstract: A system and method for determining a dimension of a target. The method includes: determining a camera parameter, the camera parameter including at least one of a focal length, a yaw angle, a roll angle, a pitch angle, or a height of one or more cameras; acquiring a first image and a second image of an target captured by the one or more cameras; generating a first corrected image and a second corrected image by correcting the first image and the second image; determining a parallax between a pixel in the first corrected image and a corresponding pixel in the second corrected image; determining an outline of the target; and determining a dimension of the target based at least in part on the camera parameter, the parallax, and the outline of the target.
    Type: Grant
    Filed: August 26, 2016
    Date of Patent: June 9, 2020
    Assignee: ZHEJIANG DAHUA TECHNOLOGY CO., LTD.
    Inventors: Wei Lu, Qiankun Li, Shizhu Pan, Jichao Geng, Xiaohui Sun, Haijiang Pan, Jinting Wang
  • Patent number: 10671795
    Abstract: One embodiment provides a method, including: detecting, in an overlay input application, one or more ink strokes provided to an input field overlay area; and providing, in the overlay input application, a preview area that displays a typeset preview for the one or more ink strokes; wherein the preview area is displayed in a location determined by an area associated with current ink stroke input. Other embodiments are described and claimed.
    Type: Grant
    Filed: December 23, 2014
    Date of Patent: June 2, 2020
    Assignee: Lenovo (Singapore) Pte. Ltd.
    Inventors: Steven Richard Perrin, Jianbang Zhang, Russell Speight VanBlon, Joshua Neil Novak, Aaron Michael Stewart, Jonathan Jen-Wei Yu, Sarah Jane E Cox, Geoffrey Simon Bula, Rajesh Krishna Daivajna
  • Patent number: 10671295
    Abstract: A state machine engine includes a state vector system. The state vector system includes an input buffer configured to receive state vector data from a restore buffer and to provide state vector data to a state machine lattice. The state vector system also includes an output buffer configured to receive state vector data from the state machine lattice and to provide state vector data to a save buffer.
    Type: Grant
    Filed: November 25, 2019
    Date of Patent: June 2, 2020
    Assignee: Micron Technology, Inc.
    Inventors: David R. Brown, Harold B Noyes
  • Patent number: 10657312
    Abstract: Techniques for performing font management on a client allowing the client to dynamically determine operating system support for new technology fonts, and upon an affirmative such determination perform installation and activation of those new technology fonts. At least one stub font and a new technology font test process facilitate activation/installation of selected fonts if the operating system supports them and graceful exception handling if the operating system does not. A stub font can be thought of as a simplified or otherwise light-weight representation of a real font (a stub font is a proxy for a real font). The stub font can be efficiently stored on a client machine, so that a new technology font test can attempt to activate the corresponding stub font in order to test whether a corresponding real font is supported by the operating system.
    Type: Grant
    Filed: November 17, 2017
    Date of Patent: May 19, 2020
    Assignee: Adobe Inc.
    Inventor: Sairus Patel
  • Patent number: 10650268
    Abstract: Provided are an image processing apparatus and an image processing method for improving the accuracy of a recognition result of a current object included in captured images. The image processing apparatus performs recognition processing on the current object on the basis of recognition results of the current object obtained from a plurality of captured images with different output information regarding imaging so that the accuracy of the recognition result of the captured images can be improved. For example, the image processing method can be applied to an electronic device having a function of performing the recognition processing on the current object.
    Type: Grant
    Filed: November 2, 2016
    Date of Patent: May 12, 2020
    Assignee: SONY SEMICONDUCTOR SOLUTIONS CORPORATION
    Inventor: Katsuya Shinozaki
  • Patent number: 10643701
    Abstract: A memory device and a memory system capable of flexibly corresponding to the number of dimensions of reference data and having a compact circuit configuration at searching for data similar to search data are provided. A memory system capable of reducing processing time to search for data similar to search data and reducing a circuit area is provided. A memory device includes a plurality of read circuits, an input search data storing circuit configured to divide search data to output, a plurality of similarity evaluation cells and a plurality of current accumulators. The memory system is configured by including a main core and a branch core thus configured.
    Type: Grant
    Filed: May 11, 2017
    Date of Patent: May 5, 2020
    Assignee: TOHOKU UNIVERSITY
    Inventors: Yitao Ma, Tetsuo Endoh
  • Patent number: 10645237
    Abstract: An apparatus includes an imaging device, a display interface, a charging interface and a processer. The imaging device is configured to obtain an image of a user device. The display interface is configured to present selections to a user of the user device and accept instructions from the user. The charging interface configured to charge the user device. The processor is configured to determine an operating system of the user device, to cause the display interface to present a charging option to the user, and to cause the charging interface to charge the user device in response to the user selecting the charging option.
    Type: Grant
    Filed: April 18, 2018
    Date of Patent: May 5, 2020
    Inventor: Cheing L. Winston
  • Patent number: 10640347
    Abstract: An example method may include receiving, from a sensor on a vehicle, an initial plurality of sensor data points representing a position of a face of a pallet. The vehicle may include tines configured to engage the pallet. A baseline geometric representation of the face of the pallet may be determined based on the initial plurality of sensor data points. The vehicle may be caused to reposition the tines relative to the pallet. A subsequent plurality of sensor data points representing the position of the face of the pallet after repositioning the tines may be received from the sensor. An updated geometric representation of the face of the pallet may be determined based on the subsequent sensor data points. It may be determined that the updated geometric representation deviates from the baseline geometric representation by more than a threshold value and, in response, motion of the vehicle may be adjusted.
    Type: Grant
    Filed: December 22, 2017
    Date of Patent: May 5, 2020
    Assignee: X Development LLC
    Inventors: Hemal Shah, Ian Gulliver
  • Patent number: 10638174
    Abstract: A system and method for creating and sharing synchronized video control data for sexual stimulation devices that allows for automated synchronization with any video of sexual activity and allows for comprehensive personalization and customization of the video selection, synchronization, and sharing experience based on the user's preferences and biometric data.
    Type: Grant
    Filed: December 7, 2018
    Date of Patent: April 28, 2020
    Inventor: Brian Sloan
  • Patent number: 10621693
    Abstract: Systems and methods for registering documents. A two-dimensional document image and one or more form images may be obtained. The document image may be projected onto a horizontal axis and a vertical axis to create a horizontal document projection and a vertical document projection. The form images may be projected onto the horizontal axis and the vertical axis to create a horizontal form projection and a vertical form projection. The horizontal document projection may be correlated with the horizontal form projection of the form images and the vertical document projection may be correlated with the vertical form projection of the form images. Correlation scores may be calculated based on the correlations.
    Type: Grant
    Filed: December 28, 2016
    Date of Patent: April 14, 2020
    Assignee: ANCESTRY.COM OPERATIONS INC.
    Inventors: Laryn Brown, Michael Murdock, Jack Reese, Shawn Reid
  • Patent number: 10621788
    Abstract: Virtual reality-based apparatus that includes a memory, a depth sensor and circuitry. The depth sensor captures a plurality of depth data points of a human subject from a single viewpoint. The memory stores a deformed three-dimensional (3D) human body model. The circuitry calculates first distances from the depth data points to a plurality of triangular faces. The circuitry calculates second distances from the depth data points to a plurality of edges. The circuitry further calculates third distances from the depth data points to a plurality of vertices. The circuitry further determines minimum distances, among the calculated first distances, the calculated second distances, and the calculated third distances, as point-to-surface distance to reconstruct a 3D human body model with high accuracy.
    Type: Grant
    Filed: September 25, 2018
    Date of Patent: April 14, 2020
    Assignee: SONY CORPORATION
    Inventors: Jie Ni, Mohammad Gharavi-Alkhansari
  • Patent number: 10606178
    Abstract: Disclosed is a method of measuring a target, and a metrology apparatus. In one arrangement the target comprises a layered structure. The layered structure has a first target structure in a first layer and a second target structure in a second layer. The method comprises illuminating the target with measurement radiation using an illumination profile in the illumination pupil (u) that is offset from an imaginary line (IL) in the illumination pupil passing through the optical axis, to allow propagation to a detection region of the detection pupil of an allowed order (v2, v4) of a predetermined diffraction order while limiting propagation to the detection region of an equal and opposite order (v1?, v3?) of that predetermined diffraction order. Scattered radiation of plural double-diffracted allowed diffraction orders (w2, w4) is detected. A characteristic of the lithographic process is calculated using the detected scattered radiation of the predetermined diffraction orders.
    Type: Grant
    Filed: January 11, 2019
    Date of Patent: March 31, 2020
    Assignee: ASML Netherlands B.V.
    Inventor: Olger Victor Zwier
  • Patent number: 10601866
    Abstract: A method, computer system, and a computer program product for identifying a phishing attack is provided. The present invention may include receiving an alert of a suspicious URL. The present invention may include making an HTTP request to the suspicious URL. The present invention may include downloading and rendering the suspicious URL content. The present invention may include producing a screenshot of the rendered suspicious URL content. The present invention may include making an HTTP request to a domain landing page. The present invention may include downloading and rendering the domain landing page URL content. The present invention may include producing a screenshot of the rendered domain landing page URL content. The present invention may include generating a score based on comparing the produced first screenshot and the produced second screenshot.
    Type: Grant
    Filed: August 23, 2017
    Date of Patent: March 24, 2020
    Assignee: International Business Machines Corporation
    Inventors: Avishay Bartik, Alon Freund, Aviv Ron, Shahaf Stein
  • Patent number: 10600089
    Abstract: A system for analyzing user consumption of content on web pages or determining user engagement with content comprising a data collection script and an content-engagement-inference engine. The data collection script determines one or more content elements to be measured from a web page and collects description data associated with the one or more content elements. The description data describes information about the one or more content elements. The content-engagement-inference engine creates an inference or analytics result based on the description data. The inference or analytics result describes how the one or more content elements have been consumed by users and then provides the inference or analytics result for users to designated entities.
    Type: Grant
    Filed: March 14, 2014
    Date of Patent: March 24, 2020
    Assignee: Oracle America, Inc.
    Inventors: Daniel E. Fichter, Christopher R. Tsoufakis, Nikki K. Gomez, Aniq Rahman, Jonah Goodhart, Michael Garrett Seiler, Suryansh Agarwal, Theodore V. McConnell
  • Patent number: 10592450
    Abstract: A system includes a processor and a hardware accelerator coupled to the processor. The hardware accelerator includes data analysis elements configured to analyze a data stream based on configuration data and to output a result, and an integrated circuit device that includes a DMA engine that writes input data to and read output data from the data analysis elements, one or more preprocessing cores that receive the input data from the DMA engine prior to the DMA engine writing the input data to the one or more data analysis elements and perform custom preprocessing functions on the input data, and one or more post-processing cores that receive the output data from the DMA engine after the output data is read from the data analysis elements but prior to the output data being output to the processor and perform custom post-processing functions on the output data.
    Type: Grant
    Filed: January 18, 2017
    Date of Patent: March 17, 2020
    Assignee: Micron Technology, Inc.
    Inventor: Gavin L. Huggins
  • Patent number: 10579741
    Abstract: In one embodiment, a computer-implemented method for proactively improving machine translation in real time by processing a translation request includes: receiving the translation request from a mobile device; and either generating or retrieving translation information based on a result of either or both of: determining whether the translation request includes image data suitable for generating a machine translation; and determining whether the translation request includes metadata suitable for generating an estimated translation. In another embodiment, a computer-implemented method for proactively improving machine translation in real time by generating and submitting a translation request includes: capturing image data; evaluating one or more conditions corresponding to the captured image data; generating metadata corresponding to the captured image data; and generating and submitting the translation request to a machine translation platform.
    Type: Grant
    Filed: August 17, 2016
    Date of Patent: March 3, 2020
    Assignee: International Business Machines Corporation
    Inventors: Debbie A. Anglin, Jeffrey A. Calcaterra, Su Liu, Cheng Xu
  • Patent number: 10573046
    Abstract: The present invention makes it possible to see an original text string which (i) is contained in a captured image and (ii) has been translated, even after a translation of the original text string is displayed. The text string decoration display control section (12) decorates a part indicating a text string contained in a captured image and causes the decorated part to be displayed. The translation image generating section (13) generates a translation image showing a result of translating the text string into another language. The translation display control section (16) switches between display and non-display of the translation image in accordance with an input carried out by a user.
    Type: Grant
    Filed: June 4, 2018
    Date of Patent: February 25, 2020
    Assignee: SHARP KABUSHIKI KAISHA
    Inventors: Kiyofumi Ohtsuka, Tadao Nagasawa
  • Patent number: 10572759
    Abstract: To quickly specify a region of a character group included in an image, image obtaining means of an image processing device obtains the image data. Expansion means expands and unites a plurality of regions respectively indicating objects included in an image indicated by the image data obtained by the image obtaining means. Character region determining means determines whether all or some of the regions, which are expanded and united by the expansion means, are character regions. Processing performing means performs predetermined processing on a region that is determined by the character region determining means as a character region.
    Type: Grant
    Filed: July 5, 2016
    Date of Patent: February 25, 2020
    Assignee: Rakuten, Inc.
    Inventor: Rong Liu
  • Patent number: 10567844
    Abstract: In one embodiment, a method includes a client device receiving a selection of an emotion capture button. The emotion capture button is associated with an emotion. In response to the receiving the selection of the emotion capture button, the client device captures a video clip designated with a categorization specifying the emotion associated with the selected emotion capture button.
    Type: Grant
    Filed: February 24, 2017
    Date of Patent: February 18, 2020
    Assignee: Facebook, Inc.
    Inventor: Michael Arthur Sayman
  • Patent number: 10552686
    Abstract: An object recognition device according to an embodiment includes a camera that captures an image of an imaging area. A storage device stores, for each of a plurality of registered objects, dictionary feature information for identifying the corresponding object and dictionary boundary information for identifying an actual boundary area of the corresponding object. A processor receives the captured image from the camera, and determines an object area in the captured image. The processor extracts feature information from the object area, and, based on the extracted feature information compared to the dictionary feature information, identifies each object included in the object area. The processor also extracts boundary information corresponding to each identified object included in the object area, and, based on the extracted boundary information compared to the dictionary boundary information with respect to each identified object, determines an overlap state of each identified object in the object area.
    Type: Grant
    Filed: November 17, 2017
    Date of Patent: February 4, 2020
    Assignee: TOSHIBA TEC KABUSHIKI KAISHA
    Inventor: Masaaki Yasunaga
  • Patent number: 10552241
    Abstract: An actuator to execute on a server may be automatically selected based on risk of failure and damage to the server. Requirement specification and environment parameters may be received. A subset of actuators may be selected based on a risk threshold from an actuator catalog database storing actuator information and actuator risk metadata associated with a plurality of actuators. The actuator risk metadata may be augmented with risk information. A ranked list of the subset of actuators may be generated based on the actuator risk metadata associated with each actuator in the subset. An actuator in the ranked list may be executed on the server.
    Type: Grant
    Filed: June 22, 2016
    Date of Patent: February 4, 2020
    Assignee: International Business Machines Corporation
    Inventors: Constantin M. Adam, Anuradha Bhamidipaty, Jayan Nallacherry, Debasisha K. Padhi, Yaoping Ruan, Frederick Y.-F. Wu
  • Patent number: 10552683
    Abstract: The present invention extends to methods, systems, and computer program products for ingesting streaming signals. Signal ingestion modules sample a frame from a raw streaming signal. A preliminary severity or possible event type is computed from the sampled frame. A deeper inspection request is triggered of the raw streaming signal or of another raw streaming signal. Segments of content from the raw streaming signal or the other raw streaming signal are inspected. An actual severity or actual event type is computed from the inspected content. The actual severity or actual event type can be included in a normalized signal.
    Type: Grant
    Filed: July 15, 2019
    Date of Patent: February 4, 2020
    Assignee: Banjo, Inc.
    Inventors: KW Justin Leung, Michael Avner Urbach, Armando Guereca-Pinuelas, Christopher E. Latko, Damien Patton, Rish Mehta
  • Patent number: 10554807
    Abstract: A mobile terminal and a method of operating the mobile terminal are provided. The mobile terminal includes a sensor configured to sense a motion of the mobile terminal, and a communication interface configured to receive, from a wearable device corresponding to the mobile terminal, information of a motion of the wearable device, the motion of the wearable device being sensed during a time period from a start time requested by the mobile terminal. The mobile terminal further includes a controller configured to determine whether the motion of the mobile terminal and the motion of the wearable device have a correlation of a level or greater, and unlock the mobile terminal, in response to the controller determining that the motion of the mobile terminal and the motion of the wearable device have the correlation of the level or greater.
    Type: Grant
    Filed: April 23, 2018
    Date of Patent: February 4, 2020
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventor: Yun-jung Kim
  • Patent number: 10546360
    Abstract: An encoding apparatus partitions a digital image into multiple regions for subsequent encoding. A first encryption code is associated with a first region, a second encryption code is associated with a second region and the first code, and a third code is associated with the first code, the second code and a third region. An authentication apparatus authenticates the digital image in an inverse process.
    Type: Grant
    Filed: June 1, 2016
    Date of Patent: January 28, 2020
    Assignee: SIGNS & WONDERS UNLIMITED, LLC
    Inventors: Nancy Powers, Terrence M. Fortuna, Paul Kocsis
  • Patent number: 10541000
    Abstract: One or more frames of video data may depict content that is determined to likely be of interest to a user. A video segment that includes the one or more frames may be determined. Based at least partly on one or more first summarization parameters associated with the user, a first video summarization may be generated, where the first video summarization includes the first video segment and possibly other video segments associated with the video data. The first video summarization may be provided to the user. Upon receiving data that is representative of user feedback relating to the first video summarization, one or more second summarization parameters may be determined based at least partly on the data. A second video summarization of the video data may be generated based at least partly on the one or more second summarization parameters. The second video summarization may then be provided to the user.
    Type: Grant
    Filed: June 26, 2015
    Date of Patent: January 21, 2020
    Assignee: Amazon Technologies, Inc.
    Inventors: Kenneth Mark Karakotsios, Deon Poncini, Matthew Alan Townsend
  • Patent number: 10528808
    Abstract: Disclosed is a document processing system that can be used to automatically detect and process an invoice for a business entity. The system receives a document and determines the structural information from the document. The structural information includes a template object and its location on the document. The system further retrieves structural information of documents stored in the database and compares the structural information of retrieved documents to the received document based on matching criteria such as a template object name and its location. If a match is found within a predefined threshold range, the data is extracted from the received document and the structural information is extracted from the matching document and the received document is processed by applying the extracted data to the corresponding extracted structural information. The processed document is transmitted for a user review or for processing by an accounting or bookkeeping software application.
    Type: Grant
    Filed: April 20, 2016
    Date of Patent: January 7, 2020
    Assignee: Orbiion, Inc.
    Inventors: Miguel A. Galarza Lozano, Jose Luis Medellin Garibay
  • Patent number: 10530922
    Abstract: A mobile terminal and a method of operating the mobile terminal are provided. The mobile terminal includes a sensor configured to sense a motion of the mobile terminal, and a communication interface configured to receive, from a wearable device corresponding to the mobile terminal, information of a motion of the wearable device, the motion of the wearable device being sensed during a time period from a start time requested by the mobile terminal. The mobile terminal further includes a controller configured to determine whether the motion of the mobile terminal and the motion of the wearable device have a correlation of a level or greater, and unlock the mobile terminal, in response to the controller determining that the motion of the mobile terminal and the motion of the wearable device have the correlation of the level or greater.
    Type: Grant
    Filed: April 23, 2018
    Date of Patent: January 7, 2020
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventor: Yun-jung Kim
  • Patent number: 10529203
    Abstract: Embodiments of the present application provide a regional surveillance and alarming system and an alarming method. In the embodiment of the present application, each security region is provided with a control device having stored thereon an association table in which associated objects of a security region where the control device is located when this security region is taken as the first target object are recorded, and the associated objects may be a detection device or other target objects. When a change of the state of the detection device or the target object satisfies the alarm output triggering condition, the control device may issue an alarm. As such, a real-time surveillance and alarming of illegal events may be allowed.
    Type: Grant
    Filed: October 27, 2016
    Date of Patent: January 7, 2020
    Assignee: HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD.
    Inventor: Yanguo Lin
  • Patent number: 10528649
    Abstract: Font recognition and similarity determination techniques and systems are described. For example, a computing device receives an image including a font and extracts font features corresponding to the font. The computing device computes font feature distances between the font and fonts from a set of training fonts. The computing device calculates, based on the font feature distances, similarity scores for the font and the training fonts used for calculating features distances. The computing device determines, based on the similarity scores, final similarity scores for the font relative to the training fonts.
    Type: Grant
    Filed: September 29, 2016
    Date of Patent: January 7, 2020
    Assignee: Adobe Inc.
    Inventors: Zhaowen Wang, Hailin Jin
  • Patent number: 10521889
    Abstract: Enhanced vectorization of raster images is described. An image vectorization module converts a raster image with bitmapped data to a vector image with vector elements based on mathematical formulas. In some embodiments, spatially-localized control of a vectorization operation is provided to a user. First, the user can adjust an intensity of a denoising operation differently at different areas of the raster image. Second, the user can adjust an automated segmentation by causing one segment to be split into two segments along a zone marked with an indicator tool, such as a brush. Third, the user can adjust an automated segmentation by causing two segments to be merged into a combined segment. The computation of the vector elements is based on the adjusted segmentation. In other embodiments, semantic information gleaned from the raster image is incorporated into the vector image to facilitate manipulation, such as joint selection of multiple vector elements.
    Type: Grant
    Filed: April 12, 2018
    Date of Patent: December 31, 2019
    Assignee: Adobe Inc.
    Inventors: Holger Winnemoeller, Wilmot Wei-Mau Li, Stephen N. Schiller, Jun Xie
  • Patent number: 10509943
    Abstract: A method for processing fingerprint information includes dividing an input image that corresponds to at least a portion of a user fingerprint into a plurality of first regions; dividing a registered image that had previously been stored into a plurality of second regions; selecting a first matching region from among the plurality of first regions, and selecting a second matching region from among the plurality of second regions, by comparing the plurality of first regions with the plurality of second regions; and matching the registered image with the input image by comparing the first matching region with the second matching region.
    Type: Grant
    Filed: September 27, 2017
    Date of Patent: December 17, 2019
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Geun Tae Bae, Sung Hoon Son, Woong Hee Lee, Ho Jae Lee, Do Ha Hwang
  • Patent number: 10504507
    Abstract: Provided herein is an integrated circuit including, in some embodiments, a special-purpose host processor, a neuromorphic co-processor, and a communications interface between the host processor and the co-processor configured to transmit information therebetween. The special-purpose host processor is operable as a stand-alone host processor. The neuromorphic co-processor includes an artificial neural network. The co-processor is configured to enhance special-purpose processing of the host processor through the artificial neural network. In such embodiments, the host processor is a keyword identifier processor configured to transmit one or more detected words to the co-processor over the communications interface. The co-processor is configured to transmit recognized words, or other sounds, to the host processor.
    Type: Grant
    Filed: December 28, 2018
    Date of Patent: December 10, 2019
    Assignee: SYNTIANT
    Inventors: Kurt F. Busch, Jeremiah H. Holleman, III, Pieter Vorenkamp, Stephen W. Bailey
  • Patent number: 10498851
    Abstract: Techniques are disclosed herein for normalizing heterogeneous information provided in labels processed by Internet of Things (IoT) devices. A label transform assistant service receives a request from an IoT device to translate content associated with a label of an item to a format readable by the device. The content includes attributes describing the item. The request specifies a target language and target encoding. A source language and a source encoding associated with the attributes are determined. Each of the attributes are normalized based on a configuration of the network service. Each of the normalized attributes is translated to the target language and the target encoding.
    Type: Grant
    Filed: January 10, 2017
    Date of Patent: December 3, 2019
    Assignee: International Business Machines Corporation
    Inventors: Debbie A. Anglin, Su Liu, Andrew Ly, Shunguo Yan
  • Patent number: 10497173
    Abstract: A system and method for adaptive hierarchical tessellation. For example, one embodiment of a method comprises: a tessellation queue to store portions of a first image frame to be tessellated; motion vector analysis circuitry to group a plurality of sub-tiles within each of a plurality of tiles at multiple levels of granularity, wherein the sub-tiles of a first level comprise pixels and the sub-tiles of each successive level comprise tiles from a previous level, the motion vector analysis circuitry to iteratively analyze motion vectors of each group of sub-tiles at each level of granularity to determine whether the motion vectors are similar in accordance with a defined threshold, the motion vector analysis circuitry to queue tiles having sub-tiles which are determined to be dissimilar to the tessellation queue.
    Type: Grant
    Filed: May 7, 2018
    Date of Patent: December 3, 2019
    Assignee: Intel Corporation
    Inventors: Valentin Fuetterling, Gabor Liktor, Karthik Vaidyanathan
  • Patent number: 10496801
    Abstract: An authentication engine for an information handling system includes an event engine that receives authentication information from a plurality of input devices of the information handling system and classifies the authentication information from each input device into a plurality of events, and provides confidence score metadata based upon the authentication information, a confidence module that generates a confidence score based upon the events, and a threshold table that receives the confidence score and determines an authentication state of the information handling system based upon the confidence score.
    Type: Grant
    Filed: January 13, 2016
    Date of Patent: December 3, 2019
    Assignee: Dell Products, LP
    Inventors: Daniel Hamlin, Charles D. Robison, Jr., Carrie Elaine Gates
  • Patent number: 10496366
    Abstract: Systems and methods are described for recognizing and responding to vocal commands in a virtual or physical environment. A system may receive voice data from a user and determine an intended command. In a virtual environment, the system may then determine a position and viewpoint orientation of the user to be able to determine one or more digital assets in a field of view of the user. The system may then apply the command to at least a first digital asset of these digital assets. In a physical environment, the system may determine one or more devices in the environment that the command may be applied to and output a unique sensory pattern to each device such that the sensory pattern may be used to distinguish one device from another device. The system may receive one of these output sensory patterns and determine the sensory pattern is unique to a first device of the one or more devices, indicating the first device is the device the user wishes to command.
    Type: Grant
    Filed: April 18, 2018
    Date of Patent: December 3, 2019
    Assignee: Comcast Cable Communications, LLC
    Inventor: Mark David Francisco
  • Patent number: 10491660
    Abstract: Systems and methods are provided for sharing a screen from a mobile device. For example, a method includes receiving, at a second mobile device, an image of a screen captured from a first mobile device and determining whether to trigger an automated action. The method may also include displaying, responsive to not triggering the automated action, annotation data generated for the image with the image on a display of the second mobile device, the annotation data including at least one visual cue corresponding to content in the image relevant to a user of the second mobile device. The method may further include, responsive to triggering the automated action, determining that a mobile application associated with the image is installed on the second mobile device and replaying user input actions received with the image on the second mobile device starting from a reference screen associated with the mobile application.
    Type: Grant
    Filed: August 18, 2017
    Date of Patent: November 26, 2019
    Assignee: GOOGLE LLC
    Inventors: Matthew Sharifi, David Petrou
  • Patent number: 10489062
    Abstract: A state machine engine includes a state vector system. The state vector system includes an input buffer configured to receive state vector data from a restore buffer and to provide state vector data to a state machine lattice. The state vector system also includes an output buffer configured to receive state vector data from the state machine lattice and to provide state vector data to a save buffer.
    Type: Grant
    Filed: April 5, 2019
    Date of Patent: November 26, 2019
    Assignee: Micron Technology, Inc.
    Inventors: David R. Brown, Harold B Noyes
  • Patent number: 10489683
    Abstract: Disclosed are systems and methods for generating large data sets for training deep learning networks for 3D measurements extraction from images taken using a mobile device camera. The method includes the steps of receiving at least one 3D model; generating a first type of augmentation data, such as but not limited to skin color, face contour, hair style, virtual clothing, and/or lighting conditions; augmenting the 3D model with the first type of augmentation data; generating at least one image from the augmented 3D model; receiving a second type of augmentation data, such as a plurality of background images representing a variety of backgrounds; augmenting the at least one image with the second type of augmentation data to generate a plurality of augmented images; extracting spatial features from the 3D model; and providing the plurality of augmented images and the spatial features to train a deep learning network for 3D measurement determination.
    Type: Grant
    Filed: July 19, 2019
    Date of Patent: November 26, 2019
    Assignee: Bodygram, Inc.
    Inventors: Chong Jin Koh, Kyohei Kamiyama
  • Patent number: 10473429
    Abstract: A projectile detection technique is disclosed. The technique helps improve the self-defense capabilities of strategic platforms such as naval ships against asymmetric threats such as anti-ship missiles (ASMs). These threats can be particularly challenging in a highly cluttered maritime environment, where the threats can be too close for radar to accurately detect. In one example, the projectile detection technique automatically detects ASMs flying above the horizon by using mid-wavelength infrared (MWIR) and visible/near-infrared (VNIR) camera systems, and locating the horizon line and segmenting the imagery into different regions. Projectiles are detected in the near-horizon segment using a Fourier phase-only transform and convolution matched filters to enhance exceedances, then applying multi-frame processing to measure persistence and scintillation (e.g., flicker from missile exhaust) to help filter out background clutter objects.
    Type: Grant
    Filed: August 21, 2018
    Date of Patent: November 12, 2019
    Assignee: BAE Systems lnformation and Electronic Systems Integration Inc.
    Inventor: Eric M. Louchard
  • Patent number: 10474932
    Abstract: Disclosed herein are systems, devices, and methods for detecting anomalies in multivariate data received from an asset-related data source, such as signal data and/or other data from an asset. According to an example, a platform may receive multivariate data from an asset in an original coordinate space and transform the data in the original coordinate space to a transformed coordinate space having a relatively fewer number of dimensions. Additionally, the platform may standardize the data in the transformed coordinate space and modify the standardized data based on a comparison between the standardized data and a set of threshold values previously defined via training data reflective of normal asset operation. Thereafter, the platform may inversely transform the modified data back to the original coordinate space and perform an analysis to detect anomalies.
    Type: Grant
    Filed: December 1, 2016
    Date of Patent: November 12, 2019
    Assignee: Uptake Technologies, Inc.
    Inventors: Frank Fineis, Michael Horrell, Tuo Li, James Herzog
  • Patent number: 10460431
    Abstract: According to one embodiment, a method of identifying a part of a conveyance system is provided. The method comprising: capturing an image of a part of a conveyance system using a camera; classifying the part of the conveyance system using supervised learning; and displaying a classification of the part of the part on a mobile computing device.
    Type: Grant
    Filed: January 15, 2018
    Date of Patent: October 29, 2019
    Assignee: OTIS ELEVATOR COMPANY
    Inventors: Luca F. Bertuccelli, Kishore K. Reddy, Kin Gwn Lore
  • Patent number: 10452781
    Abstract: An electronic artifact is accessed which includes content of a particular type of media. Text is determined corresponding to the content and natural language processing is performed on the text to identify at least a subset of words in a statement within the text and determine meanings of each word in the subset of words. A context image is generated for the electronic artifact based on the natural language processing, where the context image includes a graph including nodes corresponding to the subset of words and the context image defines relationships between the subset of words.
    Type: Grant
    Filed: May 24, 2017
    Date of Patent: October 22, 2019
    Assignee: CA, Inc.
    Inventor: Vineet Verma
  • Patent number: 10445415
    Abstract: A computer program product includes a computer readable storage medium with computer readable program code. The computer readable program code may be configured to store a plurality of classifiers. The computer readable program code may be configured to store a document with one or more first portions of text associated with a first classifier. The computer readable program code also may be configured to display the document. The computer readable program code may be configured to change a feature of the first portions of text displayed in the document to indicate that the first portions of text are associated with the first classifier.
    Type: Grant
    Filed: March 14, 2013
    Date of Patent: October 15, 2019
    Assignee: CA, Inc.
    Inventors: Peter C. Spellward, Howard C. Snart Woodhouse
  • Patent number: 10445587
    Abstract: The present invention discloses a device and method for automatic monitoring and autonomic response. The device comprises: a video capture unit, used for capturing and transmitting video in real time; an audio capture unit, used for capturing and transmitting audio in real time; a processing device, used for responding to received video and audio; a processing device, used for responding to the received video and audio, recognizing contents of the video and audio, and issuing instruction; and, a responder, used for receiving the instruction and responding according to the instruction. Compared with the prior art, the present invention allows a camera monitoring system to process automatically and respond autonomically when a certain scenario is monitored, while obviating the need for human intervention.
    Type: Grant
    Filed: September 15, 2014
    Date of Patent: October 15, 2019
    Assignee: AINEMO INC.
    Inventor: Chenfeng Song
  • Patent number: 10430948
    Abstract: The current document is directed to methods and systems that straighten in the text lines of text-containing digital images. Initial processing of a text-containing image identifies the outline of a text-containing page. Next, aggregations of symbols, including words and word fragments, are identified within the outlined page image. The centroids and inclination angles of the symbol aggregations are determined, allowing each symbol aggregation to be circumscribed by a closest-fitting rectangle oriented in conformance with the inclination angle determined for the circumscribed symbol aggregation. A model is constructed for the text-line curvature within the text image based on the circumscribed symbol aggregations and is refined using additional information extracted from the text image. The model, essentially an inclination-angle map, allows for assigning local displacements to pixels within the page image which are then used to straighten the text lines in the text image.
    Type: Grant
    Filed: August 16, 2016
    Date of Patent: October 1, 2019
    Assignee: ABBYY PRODUCTION LLC
    Inventors: Olga Arnoldovna Kacher, Ivan Germanovich Zagaynov, Vladimir Rybkin
  • Patent number: 10425556
    Abstract: Provided is an information processing apparatus including: a marking extraction circuit that extracts, from a script image including a plurality of markings respectively superimposed on a plurality of character strings, the plurality of markings; a same-character-string identification circuit that identifies the same character string out of the plurality of character strings on which the markings are respectively superimposed; and a symbol determination circuit that allocates the same symbol to the same character string and allocates different symbols to different character strings.
    Type: Grant
    Filed: February 21, 2017
    Date of Patent: September 24, 2019
    Assignee: KYOCERA DOCUMENT SOLUTIONS INC.
    Inventor: Tomohiro Miura
  • Patent number: 10401825
    Abstract: According to an example, a method for area occupancy information extraction may include receiving a signal from a sensor, and determining a number of occupants moving within a first area based on the signal. The method may further include determining when an occupant is moving and a direction of motion of the occupant based on the signal, and determining a most likely trajectory based on the direction of motion of the occupant. The method may also include controlling, by a processor, a service in the first area based on the determination of the number of occupants, the determination of when the occupant is moving and the direction of motion of the occupant, and/or the determination of the most likely trajectory.
    Type: Grant
    Filed: January 31, 2013
    Date of Patent: September 3, 2019
    Assignee: Hewlett Packard Enterprise Development LP
    Inventors: Alan A. McReynolds, Cullen E. Bash, Niru Kumari, Geoff M. Lyon, Amip J. Shah, Zhikui Wang, Rongliang Zhou
  • Patent number: 10387521
    Abstract: The process of rendering web pages can be significantly improved with a content delivery system that pre-renders web content for a client device. A web page “program” can be pre-executed and the result delivered to a requesting client device, rather than or before sending a traditional set of web page components, such as a markup language document, cascading style sheets, embedded objects. This pre-execution can relieve the client device of the burden of rendering the web page, saving resources and decreasing latency before the web page is ready, and can reduce the number of network requests that the client device must make before being able to display the page. Disclosed herein are methods, systems, and devices for creating and delivering pre-rendered web pages for accelerated browsing.
    Type: Grant
    Filed: January 10, 2017
    Date of Patent: August 20, 2019
    Assignee: Akamai Technologies Inc.
    Inventors: Moritz M. Steiner, Martin T. Flack, Stephen L. Ludin, Ketan Bhardwaj