Template Matching (e.g., Specific Devices That Determine The Best Match) Patents (Class 382/209)
  • Patent number: 11227407
    Abstract: The disclosure relates to systems, methods and processor-readable storage mediums, having processor-executable instructions stored thereon, for determining the position of a real-world object in an augmented reality application running on a computing device having a camera. The method includes capturing image information using the camera. Detection of real-world objects is then performed using a computer vision model, and filtering of a received point cloud is performed by way of a virtual frustum constructed using the captured image information. Finally, the position of the object is determined using the filtered points.
    Type: Grant
    Filed: August 26, 2019
    Date of Patent: January 18, 2022
    Assignee: EIDOS INTERACTIVE CORP.
    Inventors: Anthony Reddan, Renaud Bédard
  • Patent number: 11222496
    Abstract: Disclosed is a device and process for marking and detecting labels with spectral band authentication features utilizing a reader that can be affixed to a smart phone and positioned so as to align the lens of the phone's camera with a reader aperture. The reader aperture allows the camera to view an item through a spacer, wherein a UV and IR light source is used to reveal indicia within invisible ink. The light source employs a distinct emission spectrum characterized by narrow peaks and gaps which can illuminate pigment of the invisible ink that is selectively responsive at the wavelengths of specific peaks and/or unresponsive at the gaps in the spectrum. The smart phone captures the indicia revealed and interfaces with a cloud-based database to provide verification of authenticity.
    Type: Grant
    Filed: September 21, 2020
    Date of Patent: January 11, 2022
    Assignee: VerifyMe, Inc.
    Inventor: Keith Goldstein
  • Patent number: 11216835
    Abstract: There is provided an information processing apparatus, an information processing method, and a recording medium which are able to calculate a current price of a product more objectively and accurately, the information processing apparatus including a current price calculation unit calculating a current price of a target product, in which the current price calculation unit dynamically calculates the current price of the target product on the basis of an assessment rank of the target product determined, and supply/demand information regarding a transaction of a product that belongs to an assessment rank that is same as the assessment rank of the target product and has a product type that is same as a product type of the target product.
    Type: Grant
    Filed: May 29, 2018
    Date of Patent: January 4, 2022
    Assignee: SONY CORPORATION
    Inventor: Takao Tajiri
  • Patent number: 11212510
    Abstract: Techniques for generating three-dimensional content from the recordings of multiple independently operated cameras that are not constrained to fixed positions and orientations are disclosed. In some embodiments, data from a plurality of cameras configured to capture a scene is received; a relative pose of each camera with respect to the scene is determined based at least in part on a first estimate and a second estimate, wherein the first estimate is based on image data and the second estimate is based on sensor data; relative poses of cameras with respect to one or more other cameras are determined based on determined relative poses of individual cameras with respect to the scene; and a three-dimensional reconstruction of at least a portion of the scene is generated based on the received data and determined relative poses.
    Type: Grant
    Filed: August 18, 2020
    Date of Patent: December 28, 2021
    Assignee: Outward, Inc.
    Inventor: Clarence Chui
  • Patent number: 11212572
    Abstract: An identifier of query content is accurately determined. A content determining device 100 includes an input unit 2 that inputs query content, a storage unit 1 that stores a plurality of pieces of master content, and a content determining unit 4 that determines a region where feature values of two pieces of master content out of the plurality of pieces of master content do not match each other, calculates a matching feature count which is a count of feature values of the region that match feature values in a corresponding region of the query content, for each of the two pieces of master content, and determines an identifier of the query content on the basis of the matching feature count of each of the pieces of master content.
    Type: Grant
    Filed: February 5, 2019
    Date of Patent: December 28, 2021
    Assignee: NIPPON TELEGRAPH AND TELEPHONE CORPORATION
    Inventors: Takahito Kawanishi, Hidehisa Nagano, Kunio Kashino, Yasunori Oishi, Kaoru Hiramatsu
  • Patent number: 11210800
    Abstract: The present disclosure provides a method for generating a verification template. The verification template includes an infrared template and a depth template. The method includes: obtaining an infrared image of a target object and storing the infrared image into a trusted execution environment as the infrared template; controlling a laser projector to project laser light to the target object; obtaining a laser pattern modulated by the target object; and processing the laser pattern to obtain a depth image and storing the depth image into the trusted execution environment as the depth template.
    Type: Grant
    Filed: April 25, 2019
    Date of Patent: December 28, 2021
    Assignee: SHENZHEN HEYTAP TECHNOLOGY CORP., LTD.
    Inventors: Xueyong Zhang, Xiangnan Lyu
  • Patent number: 11200859
    Abstract: An electronic device with reduced power consumption is provided. The electronic device has a function of transmitting data. First data and second data are supplied to the electronic device. The electronic device has a function of generating a first hash value from the first data, and transmitting the first data. The electronic device has a function of generating a second hash value from the second data, comparing the first hash value with the second hash value, transmitting the second data when the first hash value is different from the second hash value, and not transmitting the second data when the first hash value is the same as the second hash value.
    Type: Grant
    Filed: January 10, 2018
    Date of Patent: December 14, 2021
    Assignee: Semiconductor Energy Laboratory Co., Ltd.
    Inventors: Takayuki Ikeda, Takahiro Fukutome
  • Patent number: 11189085
    Abstract: Technologies for generating 3D and using models are described. In some embodiments the technologies employ a content creation device to produce a 3D model of an environment based at least in part on depth data and color data, which may be provided by one or more cameras. Contextual information such as location information, orientation information, etc., may also be collected or otherwise determined, and associated with points of the 3D model. Access points to the imaged environments may be identified and labeled as anchor points within the 3D model. Multiple 3D models may then be combined into an aggregate model, wherein anchor points of constituent 3D models in the aggregate model are substantially aligned. Devices, systems, and computer readable media utilizing such technologies are also described.
    Type: Grant
    Filed: May 27, 2016
    Date of Patent: November 30, 2021
    Assignee: INTEL CORPORATION
    Inventors: Shivakumar Doddamani, Jim S. Baca
  • Patent number: 11182903
    Abstract: An electronic device and method for image mask generation using a deep neural network is provided. The electronic device stores an input image that includes an object of interest generates a pilot mask for the input image by application of a trained deep neural network (DNN) on the input image. The electronic device extracts, from the input image, a region of interest that includes the object of interest, based on the generated pilot mask and resizes the extracted region of interest such that a size of the resized region of interest equals a threshold scaling size. The electronic device further generates a final mask by reapplication of the trained DNN on the resized region of interest.
    Type: Grant
    Filed: August 5, 2019
    Date of Patent: November 23, 2021
    Assignee: SONY CORPORATION
    Inventors: Hiroyuki Takeda, Tamaki Kojima, Mohammad Gharavi-Alkhansari
  • Patent number: 11182178
    Abstract: Computerized detection of one or more user interface objects is performed by processing an image file containing one or more user interface objects of a user interface generated by an application program. Sub-control objects are detected in the image file, where each sub-control object forms a portion of a user interface object that receives user input. Extraneous sub-control objects are detected. Sub-control objects that overlap with or that are within a predetermined vicinity of an identified set of sub-control objects are removed. Sub-control objects in the identified set of sub-control objects are correlated to combine one or more of the sub-control objects in the identified set of sub-control objects to generate control objects that correspond to certain of the user interface objects of the user interface generated by the application program.
    Type: Grant
    Filed: May 18, 2020
    Date of Patent: November 23, 2021
    Assignee: Automation Anywhere, Inc.
    Inventors: Sudhir Kumar Singh, Virinchipuram J Anand
  • Patent number: 11164323
    Abstract: The present disclosure provides a method for obtaining image tracking points. The method can be applied to an image tracking point obtaining device, the method includes obtaining, when a current video frame comprises a first image of a target object, a second image of the target object and determining a position of a second feature point on the second image; obtaining, on the first image, a first feature point corresponding to the second feature point; obtaining a first area to which the first feature point belongs in the first image, and obtaining a second area to which the second feature point belongs in the second image; and determining the first feature point as a tracking point of the current video frame when an image similarity between the first area and the second area meets a screening condition.
    Type: Grant
    Filed: November 8, 2019
    Date of Patent: November 2, 2021
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Xiaoming Xiang, Hao Xu, Ting Lu, Chengzhuo Zou
  • Patent number: 11163811
    Abstract: A solution is proposed for ranking a plurality of documents in a computing system, each of the documents comprising a plurality of document terms. A corresponding method comprises receiving a query comprising one or more query terms for selecting the documents, calculating corresponding similarity indexes between the query and the documents, each of the similarity indexes being calculated according to a comparison between the query terms and the document terms of the corresponding document, determining corresponding semantic richness indicators of the documents, adjusting the similarity indexes according to the corresponding semantic richness indicators, and ranking at least part of the documents for selection thereof according to the corresponding similarity indexes being adjusted.
    Type: Grant
    Filed: October 30, 2017
    Date of Patent: November 2, 2021
    Assignee: International Business Machines Corporation
    Inventors: Michele Crudele, Antonio Perrone
  • Patent number: 11151371
    Abstract: A method for splitting text line images includes receiving a text line image and identifying that the text line image comprises a plurality of zones, wherein each zone includes text whose font differs from the text of adjacent zones. The method further includes selecting a splitting position between multiple zones and splitting the text line image at the splitting position into a plurality of image segments, wherein each image segment contains at least one zone of the text line image and performing optical character recognition on each image segment to recognize a text segment of the image segment. In certain implementations, the method further includes generating one or more confidence measurements and selecting a splitting position that corresponds to a large gradient in the confidence measurement.
    Type: Grant
    Filed: August 21, 2019
    Date of Patent: October 19, 2021
    Assignee: LEVERTON HOLDING, LLC
    Inventors: Florian Kuhlmann, Michael Kieweg
  • Patent number: 11127128
    Abstract: A method for the non-destructive examination of aeronautical parts utilizing a system for acquiring x-ray images of the aeronautical parts, the method including verifying the system for acquiring x-ray images of the aeronautical parts, the verification including the steps of: acquiring an x-ray image of a known reference part including predefined structures, recognizing the predefined structures of the known reference part in the acquired x-ray image, measuring image quality on the basis of the result of the recognition step, wherein the recognition of the predefined structures of the known reference part in the acquired x-ray image includes the steps of: using information extracted from the acquired image in order to produce first structure information, and combining the first structure information with information representing a priori knowledge of the structures, by modelling using a Markov chain, in order to produce second structure information.
    Type: Grant
    Filed: March 16, 2018
    Date of Patent: September 21, 2021
    Assignee: SAFRAN
    Inventors: Haithem Boussaid, Estelle Parra
  • Patent number: 11113790
    Abstract: During the rendering of an image, specific pixels in the image are identified where antialiasing would be helpful. Antialiasing is then performed on these identified pixels, where anti-aliasing is a technique used to add greater realism to a digital image by smoothing jagged edges. This reduces a cost of performing antialiasing by reducing a number of pixels within an image on which antialiasing is performed.
    Type: Grant
    Filed: March 25, 2019
    Date of Patent: September 7, 2021
    Assignee: NVIDIA CORPORATION
    Inventors: Adam Christopher Marrs, Josef B. Spjut, Holger Heinrich Gruen, Morgan McGuire, Rahul Sathe
  • Patent number: 11107232
    Abstract: This application discloses a method and an apparatus for determining a posture of a target object in an image, a device, and a non-transitory storage medium. In the method, a training model parameter of a convolutional neural network of the target object is obtained from a server. A real-time image of the target object is obtained. At least one first image block from the real-time image is identified. The at least one first image block is a local image of the real-time image. According to the training model parameter, a label image block matching the at least one first image block is determined. The label image block is a local image of a standard image of the target object. Furthermore, the posture of the target object is determined, by processing circuitry of a terminal device, according to the at least one first image block and the determined label image block.
    Type: Grant
    Filed: August 5, 2019
    Date of Patent: August 31, 2021
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventor: Jia Li
  • Patent number: 11080833
    Abstract: A method for manipulating a target image includes generating a query of the target image and keys and values of a first reference image. The method also includes generating matching costs by comparing the query of the target image with each key of the reference image and generating a set of weights from the matching costs. Further, the method includes generating a set of weighted values by applying each weight of the set of weights to a corresponding value of the values of the reference image and generating a weighted patch by adding each weighted value of the set of weighted values together. Additionally, the method includes generating a combined weighted patch by combining the weighted patch with additional weighted patches associated with additional queries of the target image and generating a manipulated image by applying the combined weighted patch to an image processing algorithm.
    Type: Grant
    Filed: November 22, 2019
    Date of Patent: August 3, 2021
    Assignee: Adobe Inc.
    Inventors: Connelly Barnes, Utkarsh Singhal, Elya Shechtman, Michael Gharbi
  • Patent number: 11080869
    Abstract: A search assist system performs search for a subject of search from the images picked up by the on-board cameras. The search assist system includes: a first storage configured to store characteristic information on subjects of identification detected from the images picked up by fixed cameras and information on the fixed cameras; a second storage configured to store location information on vehicles; and one or more first controllers configured to receive characteristic information on the subject of search; determine a search target area based on an installation location of a fixed camera picking up the characteristic information matching the characteristic information on the subject of search; and send, to vehicles within the search target area, search instructions to search for the subject of search by the on-board cameras; and a second controller configured to output an image including the detected characteristic information on the subject of search.
    Type: Grant
    Filed: April 10, 2020
    Date of Patent: August 3, 2021
    Assignee: TOYOTA JIDOSHA KABUSHIKI KAISHA
    Inventor: Kazuma Sato
  • Patent number: 11068702
    Abstract: Disclosed is a process for performance monitoring and feedback for facial recognition systems. A first image for image matching from a camera capture device at a first location is received for purposes of image matching. A highest match confidence score of the first image to a particular stored enrollment image is determined. One or more image or user characteristics associated with the first image or first user is identified. The identified image or user characteristics and highest match confidence score are added to a facial recognition monitoring and feedback model. Subsequently, a particular one of the stored image or user characteristics consistently associated with a below-threshold highest match confidence score is identified, and a notification is displayed or transmitted including an indication of an identified facial recognition low match pattern and identifying the particular one of the stored image characteristics or user characteristics.
    Type: Grant
    Filed: July 29, 2020
    Date of Patent: July 20, 2021
    Assignee: MOTOROLA SOLUTIONS, INC.
    Inventors: Paul D. Steinberg, Peter L. Venetianer
  • Patent number: 11055335
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium determining image relevance responsive to a search query. A method includes, for each resource in a plurality of resources, wherein each resource includes one or more images and text that is separate from each of the one or more images: determining, by a data processing apparatus, and from the text of the resource, resource topics described by the text of the resource. For each of the one or more images, processing the image to determine a set of image topics that describe topics to which content depicted in the image belongs. Determining, by the data process apparatus, one or more topic match scores, wherein each topic match score is a measure of relevance one or more of the image topics of the image to one or more of the resource topics of the resource.
    Type: Grant
    Filed: July 15, 2016
    Date of Patent: July 6, 2021
    Assignee: Google LLC
    Inventors: Wencong Zhang, Jyoti Sood, Kamal Tiwari, Amitabh Saikia, Venkatesh Manickavasagam, Yilin Xiong
  • Patent number: 11037327
    Abstract: A camera control method including performing first detection processing that detects a plurality of predetermined patterns at different positions in real space from one or more images captured by a first camera, acquiring camera characteristic information on the first camera based on one or more first predetermined patterns, included in the plurality of predetermined patterns, successfully detected in the first detection processing, correcting the one or plurality of images based on the acquired camera characteristic information, performing second detection processing to detect one or more second predetermined patterns, included in the plurality of predetermined patterns, that failed to be detected in the first detection processing, the one or more second predetermined patterns being included in the one or more images on which the correcting has been performed, and updating the camera characteristic information based on the detected one or more second predetermined patterns.
    Type: Grant
    Filed: September 19, 2018
    Date of Patent: June 15, 2021
    Assignee: FUJITSU LIMITED
    Inventor: Yukio Hirai
  • Patent number: 11030478
    Abstract: A system and method for determining a correspondence map between a first and second image by determining a set of correspondence vectors for each pixel in the first image and selecting a correspondence vector from the set of correspondence vectors based on a cost value.
    Type: Grant
    Filed: November 25, 2020
    Date of Patent: June 8, 2021
    Assignee: Compound Eye, Inc.
    Inventors: Jason Devitt, Haoyang Wang, Konstantin Azarov
  • Patent number: 11016296
    Abstract: A controller of a terminal device comprises an image capture controlling unit, a creating unit, a storage controlling unit, and a display controlling unit. The image capture controlling unit causes the image capturing unit to perform image capture. The creating unit creates feature information indicating a feature of an environment of the terminal device at a target timing when the image capturing unit performs image capture of a target image. The storage controlling unit stores the captured target image and the created feature information in association with each other in a storage unit. The display controlling unit causes a display unit to display the target image stored in the storage unit in association with the feature information indicating the feature, in a specific case where the feature is detected after the target image and the feature information have been stored in the storage unit.
    Type: Grant
    Filed: May 17, 2017
    Date of Patent: May 25, 2021
    Assignee: Suncorporation
    Inventor: Tatsumi Sumigama
  • Patent number: 11018873
    Abstract: The present specification discloses a computer tangible medium storing instructions for a collision resistant process for signing a digital message with a digital signature using different hash digests derived from the same message data with the same hashing algorithm by hashing the message data in different ways. The collision resistant process protects networks from hacking attacks based different files having the same hash digest, commonly referred to as birthday attacks.
    Type: Grant
    Filed: July 11, 2020
    Date of Patent: May 25, 2021
    Inventor: Tyson York Winarski
  • Patent number: 10984795
    Abstract: An electronic apparatus and an operation method thereof are provided. The method of an electronic apparatus includes obtaining first voice data and second voice data. The method includes allowing a background speaker model that is generated based on voice signals of a plurality of speakers to be trained based on the second voice data. The method includes determining whether the first voice data is voice data corresponding to a first registered speaker associated with the electronic apparatus. The method includes allowing a first registered speaker model that is configured to recognize a voice of the first registered speaker to be trained based on the first voice data and the background speaker model, based on determining that the first voice data is voice data corresponding to the first registered speaker.
    Type: Grant
    Filed: April 12, 2019
    Date of Patent: April 20, 2021
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventor: Hui Xie
  • Patent number: 10977250
    Abstract: Certain aspects of the present disclosure provide techniques for determining similarities between businesses. One example method generally includes receiving a similarity query and receiving transaction data associated with a plurality of businesses for comparing the plurality of businesses. The method further includes generating a set of vectors representing the plurality of businesses based on the transaction data and generating a set of compact vectors based on the vectors by applying a dimensionality reduction technique. The method further includes generating based on the set of compact vectors, a similarity index and determining a response to the similarity query using the similarity index.
    Type: Grant
    Filed: September 11, 2018
    Date of Patent: April 13, 2021
    Assignee: Intuit, Inc.
    Inventors: Christopher Z. Lesner, Alexander S. Ran, Marko Rukonic, Wei Wang
  • Patent number: 10977845
    Abstract: A control method includes executing, in a case that a change instruction is accepted, at least a process for displaying a first post-change layout image on a display unit with a priority over a second post-change layout image with a higher degree of similarity to the pre-change layout image than the first post-change layout image or a process for displaying the first post-change layout image on the display unit in a more emphasized manner than the second post-change layout image.
    Type: Grant
    Filed: September 28, 2018
    Date of Patent: April 13, 2021
    Assignee: Canon Kabushiki Kaisha
    Inventors: Masaaki Obayashi, Shinjiro Hori, Hiroyasu Kunieda, Mizuki Hayakawa
  • Patent number: 10970704
    Abstract: A method for operating a mobile terminal is disclosed. The method for operating a mobile terminal according to an exemplary embodiment of the present invention comprises the steps of: executing a payment application; and displaying, when the payment application is executed, information on histories of one or more payments performed in the mobile terminal on the basis of an image displayed on the mobile terminal.
    Type: Grant
    Filed: March 29, 2016
    Date of Patent: April 6, 2021
    Assignee: LG ELECTRONICS INC.
    Inventors: Jeonghyun Choi, Hyunjoo Jeon, Sunjung Lee, Yoonshinn Yang
  • Patent number: 10963686
    Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: identifying a candidate key corresponding to an object in a document image with a key in key ontology data, based on that the candidate key is semantically interchangeable with the key. A context, position, and style of each objects of the document image is represented in the document metadata. The candidate key is normalized into a normal form. A key class corresponding to the normal form is determined and a confidence score indicating a likelihood of the key class being representative of the candidate key is assessed. A semantic database is updated with the key class upon verification for enhanced processing of future documents.
    Type: Grant
    Filed: December 1, 2017
    Date of Patent: March 30, 2021
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Kevin Northrup, Craig M. Trim, Terry Hickey, Abisola Adeniran, Kenji Northrup
  • Patent number: 10956355
    Abstract: Disclosed is a system that enables connection of a wide variety of sensors to a smart device and, with the aid of a suitable software application or application processor, allows the sensor acquired information to be displayed on the smart device. Two basic embodiments of the system of the invention are described—an external unit that is connected to the smart device via one of the existing ports and an internal unit that in some cases utilizes some of the existing components of the device.
    Type: Grant
    Filed: March 23, 2017
    Date of Patent: March 23, 2021
    Assignee: PULSENMORE LTD.
    Inventor: Lazar Sonnenschein
  • Patent number: 10959109
    Abstract: Concepts and technologies are disclosed herein for creating and using network coverage models. A request for a predicted coverage model that represents a first signal propagation in a first portion of a network that covers a first area associated with a first geographic location can be received. An aerial image that depicts the first area can be obtained. The aerial image can be provided to an existing coverage model. The existing coverage model can include a neural network, and the existing coverage model can be based on a second signal propagation in a second portion of the network that covers a second area associated with a second location. The predicted coverage model for the first area can be obtained from the existing coverage model.
    Type: Grant
    Filed: February 27, 2020
    Date of Patent: March 23, 2021
    Assignee: AT&T Intellectual Property I, L.P.
    Inventors: Danielle Liu, Arun Jotshi, Gaurav Thakur, Velin Kounev, Fei Wu, Yaron Kanza, Divith Aruni Babu
  • Patent number: 10956732
    Abstract: System and method for detecting the authenticity of products by detecting a unique chaotic signature. Photos of the products are taken at the plant and stored in a database/server. The server processes the images to detect for each authentic product a unique authentic signature which is the result of a manufacturing process, a process of nature etc. To detect whether the product is genuine or not at the store, the user/buyer may take a picture of the product and send it to the server (e.g. using an app installed on a portable device or the like). Upon receipt of the photo, the server may process the receive image in search for a pre-detected and/or pre-stored chaotic signature associated with an authentic product. The server may return a response to the user indicating the result of the search. A feedback mechanism may be included to guide the user to take a picture at a specific location of the product where the chaotic signature may exist.
    Type: Grant
    Filed: November 23, 2015
    Date of Patent: March 23, 2021
    Inventor: Guy Le Henaff
  • Patent number: 10943111
    Abstract: A method includes identifying one or more objects in one or more images of real-world scenes associated with a user, adding the identified one or more objects to a list of real-world objects associated with the user, assigning each object in the list of real-world objects to an object class based on object recognition, and providing a notification to the user that a content item has been associated with an object class assigned to one of the objects on the list of real-world objects associated with the user. A computer readable storage medium stores one or more computer programs, and an apparatus includes a processor-based device.
    Type: Grant
    Filed: December 9, 2014
    Date of Patent: March 9, 2021
    Assignee: Sony Interactive Entertainment Inc.
    Inventor: Glenn Black
  • Patent number: 10915612
    Abstract: Apparatuses and methods associated with authenticated production are disclosed herein. In embodiments, a digital fingerprint processor may be configured to: identify an activation of at least one of the one or more machines to attempt to produce or manufacture at least one of physical product or physical manufacture; responsive to completion of one or more operations associated with the activation by the one or more machines, acquire digital image data of a portion of a physical object on or inside the one or more machines; analyze the digital image data to form a digital fingerprint of the physical object, wherein the digital fingerprint is responsive to structure of the physical object; and store the digital fingerprint in a database record of the database system. Other embodiments may be disclosed or claimed.
    Type: Grant
    Filed: July 3, 2017
    Date of Patent: February 9, 2021
    Assignee: ALITHEON, INC.
    Inventors: Justin Lynn Withrow, David Justin Ross
  • Patent number: 10909746
    Abstract: Systems and methods for generating a three-dimensional reconstruction from a two-dimensional image of an asset are described. In some aspects, at least one computer hardware processor is used to perform: receiving a two-dimensional input image of an asset; encoding, using a first statistical model, the input image into a latent vector; and generating, using a second statistical model, at least one depth image from the latent vector, wherein pixel values in the at least one depth image correspond to coordinates of a point cloud.
    Type: Grant
    Filed: June 21, 2019
    Date of Patent: February 2, 2021
    Assignee: Imbellus, Inc.
    Inventors: Rebecca Kantar, Richard Wainess, Erica L. Snow, Matthew A. Emery, Jared Lafer, Ramsey Jones
  • Patent number: 10896322
    Abstract: There is provided an information processing device including an image acquiring portion configured to acquire a photographed image obtained by photographing a user wearing a head mounted display, an expression estimating portion configured to estimate an expression of the user from an image of a mouth of the user included in the photographed image, an facial image producing portion configured to produce a facial image responding to the estimated expression of the user, and an output portion configured to output an image including the facial image.
    Type: Grant
    Filed: October 23, 2018
    Date of Patent: January 19, 2021
    Assignees: Sony Interactive Entertainment Inc., Sony Interactive Entertainment LLC
    Inventors: Daisuke Nakata, Jigen Zhou
  • Patent number: 10896284
    Abstract: Concepts and technologies are described herein for transforming data to create layouts. In accordance with the concepts and technologies disclosed herein, a computing device can execute a layout generator. The computing device can be configured to receive or retrieve data that includes visual content such as an image and other content such as text. The computing device can analyze the visual content to identify a salient region and/or an invariant region within the visual content. The computing device can access designs for laying out visual content and other content based upon an identified salient region and/or invariant region. The computing device can evaluate the designs to determine if a design matches the data. The computing device can load the data into the selected design to generate the layout.
    Type: Grant
    Filed: June 25, 2018
    Date of Patent: January 19, 2021
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: David Benjamin Lee, Nathan George Freier, Ilya Tumanov
  • Patent number: 10887862
    Abstract: A communication system that provides wireless service to at least one wireless device is provided. The communication system includes a baseband controller communicatively coupled to a plurality of radio points and at least one image capture device at a site. The baseband controller is configured to determine a signature vector for a wireless device associated with a first user. The communication system also includes a machine learning computing system configured to determine an image-based location of the first user based on image data from the at least one image capture device. The communication system is also configured to determine mapping data that associates the signature vector with the image-based location of the first user.
    Type: Grant
    Filed: February 6, 2020
    Date of Patent: January 5, 2021
    Assignee: CommScope Technologies LLC
    Inventor: Balaji B Raghothaman
  • Patent number: 10880472
    Abstract: A first camera captures a first image of a scene, and a second camera captures a second image capturing thermal distribution across the scene. The first image is processed to detect one or more objects of interest in the scene and to identify respective surface characteristics of the objects. The first image is overlaid with the second image to identify regions of interest in the second image corresponding to the objects of interest in the first image. Values of pixels that belong to respective regions of interest in the second image are converted to temperature values using respective conversion functions that reflect respective emissivity values determined by the identified respective surface characteristics of the corresponding objects of interest in the first image. The temperature values are analyzed to monitor thermal conditions of the one or more objects of interest in the scene.
    Type: Grant
    Filed: June 12, 2019
    Date of Patent: December 29, 2020
    Assignee: Air Products and Chemicals, Inc.
    Inventors: Avishek Guha, Erdem Arslan
  • Patent number: 10878299
    Abstract: The techniques described herein relate to methods, apparatus, and computer readable media configured to test a pose of a three-dimensional model. A three-dimensional model is stored, the three dimensional model comprising a set of probes. Three-dimensional data of an object is received, the three-dimensional data comprising a set of data entries. The three-dimensional data is converted into a set of fields, comprising generating a first field comprising a first set of values, where each value of the first set of values is indicative of a first characteristic of an associated one or more data entries from the set of data entries, and generating a second field comprising a second set of values, where each second value of the second set of values is indicative of a second characteristic of an associated one or more data entries from the set of data entries, wherein the second characteristic is different than the first characteristic.
    Type: Grant
    Filed: September 12, 2018
    Date of Patent: December 29, 2020
    Assignee: Cognex Corporation
    Inventors: Andrew Hoelscher, Nathaniel Bogan
  • Patent number: 10880092
    Abstract: Systems and a method for compression and manipulation-resistant fuzzy hashing are provided. In one or more aspects, a system includes a network interface to receive an image object from a network, and a processor to process the image object. The processing includes generating pairs of random numbers using a hash of pixel data of the image object as a seed. The processing further includes identifying a number of coordinate pairs, within image pixels of the image object, such that coordinate values of each coordinate pair of the identified coordinate pairs approximately matches one pair of the random numbers. A number of first entropy values associated with first sub-areas corresponding to the identified coordinate pairs are determined. An anchor point within the image pixels is identified that has coordinate values corresponding to a sub-area that is associated with a highest entropy value among the determined first entropy values.
    Type: Grant
    Filed: February 5, 2018
    Date of Patent: December 29, 2020
    Assignee: Colossio, Inc.
    Inventor: Joseph A. Jaroch
  • Patent number: 10867134
    Abstract: A multicore CPU of a text string data analyzing device: loads a plurality of blocks obtained by dividing a text string dictionary into a memory; executes, in parallel on block groups executable independently of each other, an entry registration process of registering, character by character, unregistered text strings of text string data as new entries in the blocks in order from last characters; and outputs, as BW transformed data of the text string dictionary in which the text string data is already registered, a text string obtained by coupling text strings registered in entries of the blocks in a state in which no unregistered text strings of the blocks exists.
    Type: Grant
    Filed: September 2, 2016
    Date of Patent: December 15, 2020
    Assignee: HITACHI HIGH-TECH CORPORATION
    Inventor: Kouichi Kimura
  • Patent number: 10861137
    Abstract: An apparatus includes a resolving unit configured to resolve input image data into image data for each frequency band, an acquisition unit configured to acquire skewness corresponding to the resolved image data resolved by the resolving unit, wherein the skewness is acquired from a histogram corresponding to each of the resolved image data, and an adjustment unit configured to determine image data to be processed, out of the resolved image data based on the acquired skewness acquired and perform gain adjustment on the determined image data.
    Type: Grant
    Filed: September 5, 2018
    Date of Patent: December 8, 2020
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Reiji Misawa
  • Patent number: 10855936
    Abstract: Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. In particular, a multi-view interactive digital media representation (MVIDMR) of a person can be generated from live images of a person captured from a hand-held camera. Using the image data from the live images, a skeleton of the person and a boundary between the person and a background can be determined from different viewing angles and across multiple images. Using the skeleton and the boundary data, effects can be added to the person, such as wings. The effects can change from image to image to account for the different viewing angles of the person captured in each image.
    Type: Grant
    Filed: September 23, 2019
    Date of Patent: December 1, 2020
    Assignee: Fyusion, Inc.
    Inventors: Stefan Johannes Josef Holzer, Radu Bogdan Rusu, Stephen David Miller, Pantelis Kalogiros, Matteo Munaro, Alexander Jay Bruen Trevor, Nico Gregor Sebastian Blodow, Luo Yi Tan, Mike Penz, Martin Markus Hubert Wawro, Matthias Reso, Chris Beall, Yusuke Tomoto, Krunal Ketan Chande
  • Patent number: 10853407
    Abstract: A machine may be configured to execute a machine-learning process for identifying and understanding fine properties of various items of various types by using images and associated corresponding annotations, such as titles, captions, tags, keywords, or other textual information applied to these images. By use of a machine-learning process, the machine may perform property identification accurately and without human intervention. These item properties may be used as annotations for other images that have similar features. Accordingly, the machine may answer user-submitted questions, such as “What do rustic items look like?,” and items or images depicting items that are deemed to be rustic can be readily identified, classified, ranked, or any suitable combination thereof.
    Type: Grant
    Filed: May 29, 2014
    Date of Patent: December 1, 2020
    Assignee: eBay, Inc.
    Inventors: Anurag Bhardwaj, Robinson Piramuthu, Vicente Ordonez-Roman, Vignesh Jagadeesh, Wei Di
  • Patent number: 10846596
    Abstract: This document presents methods by which system parameters are tracked online. For adjusting the values of the system parameters, the presented methods take advantage of the data that become available during the system's operation. The values of the parameters can be used for estimating the system state and controlling the system. This document includes methods comprising constructing a cost function based on the data collected during the system operation as a function system parameters and running a memetic algorithm that reduces the cost function value. A memetic algorithm combines an evolutionary or a population-based algorithm with a procedure for local improvement (local search, refinements) of candidate solutions. This document includes methods by which the rotor speed, the rotor flux, and the stator currents of the induction motor can be estimated from electrical measurements while covariance matrices of noise are adjusted online.
    Type: Grant
    Filed: November 23, 2016
    Date of Patent: November 24, 2020
    Inventor: Daniel Chonghwan Lee
  • Patent number: 10803616
    Abstract: A system generates a user hand shape model from a single depth camera. The system includes the single depth camera and a hand tracking unit. The single depth camera generates single depth image data of a user's hand. The hand tracking unit applies the single depth image data to a neural network model to generate heat maps indicating locations of hand features. The locations of hand features are used to generate a user hand shape model customized to the size and shape of the user's hand. The user hand shape model is defined by a set of principle component hand shapes defining a hand shape variation space. The limited number of principle component hand shape models reduces determination of user hand shape to a smaller number of variables, and thus provides for a fast calibration of the user hand shape model.
    Type: Grant
    Filed: April 13, 2017
    Date of Patent: October 13, 2020
    Assignee: Facebook Technologies, LLC
    Inventors: Christopher David Twigg, Robert Y. Wang, Yuting Ye
  • Patent number: 10789257
    Abstract: An industrial process analysis system is disclosed The system comprises a process data connection device for the acquisition of process data from process data source, an input system for receiving at least one search instruction, an indexing system for indexing the process data to create a set of indexed process data a data processing device for processing the at least one search instruction to create a search parameter set and comparing distances of members of the search parameter set with corresponding members of the indexed process data to obtain a similarity value; and an output device to display results based on the similarity value.
    Type: Grant
    Filed: December 22, 2014
    Date of Patent: September 29, 2020
    Assignee: D SQUARE N.V.
    Inventors: Thomas Dhollander, Bert Baeck, Stijn Meganck
  • Patent number: 10785452
    Abstract: Systems and methods identify consumer products in images. Known consumer products are captured as grayscale or color images. They are converted to binary at varying thresholds. Connected components in the binary images identify image features according to pixels of a predetermined size, shape, solidity, aspect ratio, and the like. The image features are stored and searched for amongst image features similarly extracted from unknown images of consumer products. Identifying correspondence between the features of the images lends itself to identifying or not known consumer products.
    Type: Grant
    Filed: November 19, 2018
    Date of Patent: September 22, 2020
    Assignee: LEXMARK INTERNATIONAL, INC.
    Inventor: Robert Reed Booth
  • Patent number: 10783734
    Abstract: Disclosed is a device and process for marking and detecting labels with spectral band authentication features utilizing a reader that can be affixed to a smart phone and positioned so as to align the lens of the phone's camera with a reader aperture. The reader aperture allows the camera to view an item through a spacer, wherein a UV and IR light source is used to reveal indicia within invisible ink. The light source employs a distinct emission spectrum characterized by narrow peaks and gaps which can illuminate pigment of the invisible ink that is selectively responsive at the wavelengths of specific peaks and/or unresponsive at the gaps in the spectrum. The smart phone captures the indicia revealed and interfaces with a cloud-based database to provide verification of authenticity.
    Type: Grant
    Filed: March 25, 2019
    Date of Patent: September 22, 2020
    Assignee: VerifyMe, Inc.
    Inventor: Keith Goldstein