Pattern Recognition Or Classification Using Color Patents (Class 382/165)
  • Patent number: 10970521
    Abstract: An autonomous inventory tracking apparatus includes an image acquisition unit configured to acquire an image, and a processor configured to detect a calibration plate in the image acquired from the image acquisition unit, calculate a color correction value for the image according to a color block of the calibration plate, the color block matching a reference value, correct color in the image using the calculated color correction value to provide a color-corrected image, and perform commodity recognition processing on the color-corrected image so as to identify the commodity in the image acquired from the image acquisition unit.
    Type: Grant
    Filed: December 24, 2019
    Date of Patent: April 6, 2021
    Assignee: TOSHIBA TEC KABUSHIKI KAISHA
    Inventors: Norimasa Ariga, Kazuki Taira, Masaaki Yasunaga
  • Patent number: 10970593
    Abstract: A computer implemented method comprising identifying, by one or more processors, a set of images of an individual and a product purchase history corresponding to the individual, analyzing, by one or more processors, the set of images of an individual, the images being from a defined time window, identifying, by one or more processors, one or more products within the product purchase history that correspond to use within the defined time window, determining, by one or more processors, one or more changes in appearance of the individual based on the analyzed images, determining, by one or more processors, correlations between the determined changes in appearance and the identified products used by the individual, and notifying, by one or more processors, the individual of the determined correlations.
    Type: Grant
    Filed: December 3, 2018
    Date of Patent: April 6, 2021
    Assignee: International Business Machines Corporation
    Inventors: Jenny S. Li, Lisa Seacat DeLuca, Dana L. Price
  • Patent number: 10963685
    Abstract: Introduced here is a machine learning related technique for supplying an observed model additional training data based upon previously received training data. To determine textual content of a character string based on a digital image that includes a handwritten version of the character string a substantial amount of training data is used. The character string can include one or more characters, and the characters can include any of letters, numerals, punctuation marks, symbols, spaces, etc. Disclosed herein is a technique to determine variations between different images of matching known character strings and substitute those variations into the images in order to create more images with the same known character string.
    Type: Grant
    Filed: November 1, 2019
    Date of Patent: March 30, 2021
    Assignee: DST Technologies, Inc.
    Inventor: Ehsan Hosseini Asl
  • Patent number: 10936907
    Abstract: An object detection network can be trained with training images to identify and classify objects in images from a sensor system disposed on a maritime vessel. The objects in the images can be identified, classified, and heat maps can be generated. Instructions can be sent regarding operation of the maritime vessel. For some training images, water conditions, sky conditions, and/or light conditions in the image can be changed to generate a second image.
    Type: Grant
    Filed: August 12, 2019
    Date of Patent: March 2, 2021
    Assignee: Buffalo Automation Group Inc.
    Inventors: Thiru Vikram Suresh, Mohit Arvind Khakharia
  • Patent number: 10931912
    Abstract: A computer-implemented method includes: storing, by a computing device, pixel-based classification rules in a memory of a computing device; storing, by the computing device, video uploading rules that identify a subset of a plurality of cameras implemented within a vehicle for which video should be uploaded in the memory of the computing device; detecting, by the computing device, satisfaction of video upload event criteria based on video or image data from at least one of the plurality of cameras and vehicle information comprising one of vehicle sensor information and vehicle diagnostic information; determining, by the computing device, a subset of the plurality of cameras based on the detecting the satisfaction of the video upload event criteria; and uploading, by the computing device, video captured by only the subset of the plurality of cameras to a video storage server.
    Type: Grant
    Filed: August 27, 2019
    Date of Patent: February 23, 2021
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: James E. Bostick, John M. Ganci, Jr., Martin G. Keen, Sarbajit K. Rakshit
  • Patent number: 10931891
    Abstract: A spectrometer includes a spectrogram, digital camera and signal processing to compensate for limits of system spatial resolution, spatial distortions and lack of precision spatial registration, limited dynamic range, The spectrogram is captured by a digital camera, and the corresponding image is converted to a wavelength and magnitude with mitigation of optical point spread function and potential magnitude clipping due to over-exposure. The clipped portions of the signal are reconstructed using tangential adjacent point spread functions as a reference or adjacent channel ratios as reference. Multichannel camera detectors having unique response magnitude ratios per wavelength are exploited to make associated direct mappings, thereby making improvements in wavelength resolution and accuracy to up to at least one to two orders of magnitude.
    Type: Grant
    Filed: August 12, 2017
    Date of Patent: February 23, 2021
    Assignee: YES WAY INTELLECTUAL HOLDINGS, LLC
    Inventor: Kevin M. Ferguson
  • Patent number: 10931852
    Abstract: An image processing apparatus generates a binary image from a multivalue input image, detects a character region and a non-character region from the binary image, and clips regions surrounding each of characters included in the detected character region as character clipping rectangles. The apparatus determines, on the basis of a black pixel density of the binary image included in the character clipping rectangle, whether or not the character clipping rectangle is a character region and determines, on the basis of a number of pixels included in the character clipping rectangle determined to be a non-character region, whether or not the character clipping rectangle determined to be a non-character region is a character region.
    Type: Grant
    Filed: September 18, 2019
    Date of Patent: February 23, 2021
    Assignee: Canon Kabushiki Kaisha
    Inventor: Hiroyuki Sakai
  • Patent number: 10931931
    Abstract: Described herein is a method of generating an image that includes receiving a set of data corresponding to an object. The method also includes generating a three-dimensional representation of the object using the set of data. The method includes generating properties for the object using the set of data. The method also includes associating the properties with the three-dimensional representation of the object, wherein the three-dimensional representation of the object and the properties for the object are used to produce training data for an object recognition algorithm.
    Type: Grant
    Filed: November 21, 2017
    Date of Patent: February 23, 2021
    Assignee: The Boeing Company
    Inventors: Robert J. Klein, John H. Aughey, Zachary L. Langford
  • Patent number: 10896345
    Abstract: A method may include extracting feature-data from an image which includes location data that indicates multiple locations within the image and multiple feature vectors that each correspond to one of the multiple locations. Each feature vector may represent a feature of an object in the image. The method may include determining a feature-data plot based on relative positions of the multiple locations and selecting a grid for the feature-data plot. The method may include generating a first representative feature vector for a first cell of the grid based on a first feature vector set and generating a second representative feature vector for a second cell of the grid based on a second feature vector set. The method may include generating a single feature vector that represents the object in the image based on the first representative feature vector and the second representative feature vector and encrypting the single feature vector.
    Type: Grant
    Filed: June 2, 2017
    Date of Patent: January 19, 2021
    Assignee: FUJITSU LIMITED
    Inventors: Avradip Mandal, Arnab Roy, Hart Montgomery, Nilanjan Datta
  • Patent number: 10885720
    Abstract: A virtual display method, device, electronic apparatus, and computer readable storage medium are provided. The virtual display method includes: obtaining a first image including information on a first target which includes at least one of a shoe, a piece of clothes, and an accessory; extracting the information on the first target from the first image to generate a second image; and photographing a second target with the second image as a foreground to obtain and display a third image including the information on the first target and the information on the second target which includes a human body.
    Type: Grant
    Filed: May 8, 2019
    Date of Patent: January 5, 2021
    Assignee: BOE TECHNOLOGY GROUP CO., LTD.
    Inventor: Ran Wang
  • Patent number: 10885390
    Abstract: A sample selection method and apparatus and a server belong to the field of metric learning technologies. The method includes: selecting n sample pairs from an unlabeled sample set, each sample pair including two samples, and each sample including data in p modalities; calculating a partial similarity between data that is in each modality and that is of one sample included in the sample pair and data that is in each modality and that is of the other sample, to obtain p×p partial similarities; calculating, according to the p×p partial similarities, an overall similarity between the two samples included in the sample pair; obtaining a degree of difference between the p×p partial similarities and the overall similarity; and selecting a sample pair that meets a preset condition and that is in the n sample pairs as a training sample.
    Type: Grant
    Filed: March 14, 2019
    Date of Patent: January 5, 2021
    Assignees: NANJING UNIVERSITY OF AERONAUTICS AND ASTRONAUTICS, TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Shengjun Huang, Nengneng Gao, Kun Yuan, Wei Chen, Di Wang
  • Patent number: 10878550
    Abstract: Systems and methods are disclosed for estimating aesthetic quality of digital images using deep learning. In particular, the disclosed systems and methods describe training a neural network to generate an aesthetic quality score digital images. In particular, the neural network includes a training structure that compares relative rankings of pairs of training images to accurately predict a relative ranking of a digital image. Additionally, in training the neural network, an image rating system can utilize content-aware and user-aware sampling techniques to identify pairs of training images that have similar content and/or that have been rated by the same or different users. Using content-aware and user-aware sampling techniques, the neural network can be trained to accurately predict aesthetic quality ratings that reflect subjective opinions of most users as well as provide aesthetic scores for digital images that represent the wide spectrum of aesthetic preferences of various users.
    Type: Grant
    Filed: October 31, 2019
    Date of Patent: December 29, 2020
    Assignee: ADOBE INC.
    Inventors: Xiaohui Shen, Zhe Lin, Shu Kong, Radomir Mech
  • Patent number: 10878221
    Abstract: An imaging device includes an image pickup device, a video signal processor, and an image recognition unit. The image pickup device outputs an image signal composed of a plurality of frames. The video signal processor performs processing for creating a video signal for display from the image signal. The image recognition unit performs a plurality of pieces of recognition processing for the image signal. The processing of the video signal processor and the processing of the image recognition unit are executed in parallel to each other.
    Type: Grant
    Filed: July 20, 2018
    Date of Patent: December 29, 2020
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventor: Masaki Funaki
  • Patent number: 10867206
    Abstract: A method, system, and computer product are provided for efficiently and accurately searching and retrieving trademark images based upon a query image. In one embodiment, a method for content based search and retrieval of trademark images includes extracting color features from a plurality of trademark images by generating, with a processor, a 64-bin color histogram for each trademark image using 6-bit color data for each pixel of the trademark image. The 6-bit color data includes 2 bits from each of a red, green, and blue channel for each pixel of the trademark image. The method further includes extracting shape features from a plurality of trademark images by generating, with the processor, a 9-bin orientation histogram for each trademark image using weighted orientation angle data for each pixel of the trademark image. The method further includes generating, by the processor, a distance similarity measure between the color histograms and the orientation histograms of two trademark images.
    Type: Grant
    Filed: April 14, 2016
    Date of Patent: December 15, 2020
    Assignee: ADER BILGISAYAR HIZMETLERI VE TICARET A.S.
    Inventors: Abdulkadir Albayrak, M. Elif Karsligil, I. Onur Sigirci
  • Patent number: 10867166
    Abstract: Provided are an apparatus and a method for executing a person detection process from an image. A divisional small region setting window is set and an image in the window is determined to be a person based on the number of moving body pixels of each divisional small region, and a first person candidate point is set in the window when the image is determined to be a person. A person determination process is executed based on an image feature quantity in a person determination detection frame, and a second person candidate point is set in the person determination detection frame when it is determined to be a person. A distribution state in a moving body detection frame of the person determination detection frame is analyzed, and an image in the person determination detection frame is determined to be a person based on an analysis result.
    Type: Grant
    Filed: May 30, 2017
    Date of Patent: December 15, 2020
    Assignee: SONY CORPORATION
    Inventors: Kazuhiro Shimauchi, Takashi Kohashi, Masakazu Ebihara, Yuji Ono, Hidetoshi Nagano
  • Patent number: 10853344
    Abstract: The present invention extends to methods, systems, and computer program products for understanding tables for search. Aspects of the invention include identifying a subject tuple (e.g., a subject column) for a table, detecting a tuple header (e.g., a column header) using other tables, and detecting a tuple header (e.g., a column header) using a knowledge base. Implementations can be utilized in a structured data search system (SDSS) that indexes structured information, such as, tables in a relational database or html tables extracted from web pages. The SDSS allows users to search over the structured information (tables) using different mechanisms including keyword search and data finding data.
    Type: Grant
    Filed: July 27, 2017
    Date of Patent: December 1, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Zhongyuan Wang, Kanstantsyn Zoryn, Zhimin Chen, Kaushik Chakrabarti, James P. Finnigan, Vivek R. Narasayya, Surajit Chaudhuri, Kris Ganjam
  • Patent number: 10853704
    Abstract: In some embodiments, reduction of computational resource usage related to image labeling and/or segmentation may be facilitated. In some embodiments, a collection of images may be used to train one or more prediction models. Based on a presentation of an image on a user interface, an indication of a target quantity of superpixels for the image may be obtained. The image may be provided to a first prediction model to cause the prediction model to predict a quantity of superpixels for the image. The target quantity of superpixels may be provided to the first model to update the first model's configurations based on (i) the predicted quantity and (ii) the target quantity. A set of superpixels may be generated for the image based on the target quantity, and segmentation information related to the superpixels set may be provided to a second prediction model to update the second model's configurations.
    Type: Grant
    Filed: December 18, 2018
    Date of Patent: December 1, 2020
    Assignee: Clarifai, Inc.
    Inventors: Yanan Jian, Matthew Zeiler, Marshall Jones
  • Patent number: 10842364
    Abstract: An image processing device includes a processor including hardware, the processor being configured to: acquire an input image; detect an arc curve in the input image; determine a change in a luminance of a pixel in a direction from an inner side toward an outer side of the arc curve; detect, as a representative bubble region, a region including the arc curve involving a change determined to be an increase in the luminance in the direction from the inner side toward the outer side; and extract a bubble region, based on the representative bubble region.
    Type: Grant
    Filed: December 8, 2017
    Date of Patent: November 24, 2020
    Assignee: OLYMPUS CORPORATION
    Inventor: Yoichi Yaguchi
  • Patent number: 10846512
    Abstract: A system for identifying products and tracking inventory in a retail store based on analysis of image data is provided. The system may comprise at least one processor configured to receive image data from a plurality of image sensors mounted in a retail store; analyze the image data to estimate a current inventory of at least one product type in the retail store; receive product supply information associated with the at least one product type in the retail store; determine that an online order from a virtual store made during a first time period will be fulfilled by an employee of the retail store during a second time period; determine a predicted inventory of the at least one product type during the second time period; and provide information to the virtual store regarding the predicted inventory of the at least one product type during the second time period.
    Type: Grant
    Filed: September 23, 2019
    Date of Patent: November 24, 2020
    Assignee: TRAX TECHNOLOGY SOLUTIONS PTE LTD.
    Inventors: Yair Adato, Nir Hemed, Yotam Michael, Alon Grubshtein, David M. Gottlieb
  • Patent number: 10839519
    Abstract: Techniques to improve edge detection in images. Some techniques include logic to process image data into patched image data in accordance with a colorspace model where the patched image data includes color data in a plurality of patches and identify an image group corresponding to the patched image data. The logic may be further configured to select, based upon the image group, a colorspace transform mechanism being operative to transform the image data into transformed image data in accordance with another colorspace model, the other colorspace model having a higher likelihood than the colorspace model at edge detection for the image group. The logic may be further configured to apply the colorspace transform mechanism to the image data to generate the transformed image data in accordance with the other colorspace mode and then, apply an edge detection technique to the transformed image data. Other embodiments are described and claimed.
    Type: Grant
    Filed: April 15, 2019
    Date of Patent: November 17, 2020
    Assignee: Capital One Services, LLC
    Inventors: Jeremy Edward Goodsitt, Austin Grant Walters, Fardin Abdi Taghi Abad, Kenneth Taylor, Reza Farivar, Vincent Pham, Anh Truong
  • Patent number: 10839212
    Abstract: A computer-implemented method for identifying clouds in a digital image, comprising pixels, of a scene, the method comprising quantifying pixel-level characteristic/s in each of a multiplicity of pixels within a digital image of a scene; comparing function/s of the pixel-level characteristic/s to threshold/s thereby to generate comparison result/s; and using a controller for generating an output identifying clouds in the digital image, including identifying presence of cloudiness at at least one first pixel in the digital image, at least partly because the at least one comparison result indicates that the first pixel falls below the threshold/s, and identifying absence of cloudiness at at least one second pixel in the digital image, at least partly because the at least one comparison result indicates that the second pixel exceeds the threshold/s.
    Type: Grant
    Filed: January 1, 2017
    Date of Patent: November 17, 2020
    Assignee: ISRAEL AEROSPACE INDUSTRIES LTD.
    Inventor: Tal Feingersh
  • Patent number: 10839495
    Abstract: A method is provided. The method includes receiving at least part of an input image file. The at least part of the input image file includes input image data representing an image and reference tone mapping strength data representing a reference tone mapping strength parameter for deriving an input value representing an amount of spatially-variant tone mapping. The method further includes inputting the input image data and the input value to a tone mapping operation. The tone mapping operation is applied to the input image data to generate output image data representing an output image with the amount of spatially-variant tone mapping applied. A computing device is also provided.
    Type: Grant
    Filed: September 27, 2017
    Date of Patent: November 17, 2020
    Assignee: Apical Limited
    Inventor: Viacheslav Chesnokov
  • Patent number: 10832413
    Abstract: A method for curvilinear object segmentation includes receiving at least one input image comprising curvilinear features. The at least one input image is mapped to segmentation maps of the curvilinear features using a deep network having a representation module and a task module. The mapping includes transforming the input image in the representation module using learnable filters configured to balance recognition of curvilinear geometry with reduction of training error. The segmentation maps are produced using the transformed input image in the task module.
    Type: Grant
    Filed: December 18, 2018
    Date of Patent: November 10, 2020
    Assignee: Palo Alto Research Center Incorporated
    Inventors: Raja Bala, Venkateswararao Cherukuri, Vijay Kumar B G
  • Patent number: 10817744
    Abstract: Image information defining an image may be accessed. The image may include one or more salient objects. A saliency map may be generated based on the image information. The saliency map may include one or more regions corresponding to the one or more salient objects. The one or more regions may be characterized by different levels of intensity than other regions of the saliency map. One or more salient regions around the one or more salient objects may be identified based on the saliency map. A saliency metric for the image may be generated based on one or more of (1) sizes of the one or more salient regions; (2) an amount of the one or more salient regions; and/or (3) histograms within the one or more salient regions.
    Type: Grant
    Filed: August 9, 2019
    Date of Patent: October 27, 2020
    Assignee: GoPro, Inc.
    Inventor: Jerome Piovano
  • Patent number: 10817716
    Abstract: Embodiments provide a process to identify one or more areas containing a hand or hands of one or more subjects in an image. The detection process can start with coarsely locating one or more segments in the image that contain portions of the hand(s) of the subject(s) in the image using a coarse CNN. The detection process can then combine these segments to obtain the one or more areas capturing the hand(s) of the subject(s) in the image. The combined area(s) can then be fed to a grid-based deep neural network finely detect area(s) in the image that contain only the hand(s) of the subject(s) captured.
    Type: Grant
    Filed: December 20, 2018
    Date of Patent: October 27, 2020
    Assignees: MIDEA GROUP CO., LTD., SEETATECH (BEIJING) TECHNOLOGY CO., LTD.
    Inventors: Zixuan Yang, Dahai Yu, Zhuang Liu, Junyang Zhou, Xiujuan Chai, Shiguang Shan, Xilin Chen
  • Patent number: 10817138
    Abstract: An apparatus and a method for processing an input are provided. The apparatus includes a shape identifier configured to identify a first shape corresponding to a user input among shapes, a pattern identifier configured to identify a first pattern corresponding to the user input among patterns, and a determiner configured to determine a first command corresponding to the first shape and the first pattern.
    Type: Grant
    Filed: March 10, 2015
    Date of Patent: October 27, 2020
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Keun Joo Park, Tae Young Ha, So Young Lee, Hyun Surk Ryu
  • Patent number: 10810786
    Abstract: A three-dimensional data creation method includes: creating first three-dimensional data from information detected by a sensor; receiving encoded three-dimensional data that is obtained by encoding second three-dimensional data; decoding the received encoded three-dimensional data to obtain the second three-dimensional data; and merging the first three-dimensional data with the second three-dimensional data to create third three-dimensional data.
    Type: Grant
    Filed: January 9, 2019
    Date of Patent: October 20, 2020
    Assignee: PANASONIC INTELLECTUAL PROPERTY CORPORATION OF AMERICA
    Inventors: Toru Matsunobu, Takahiro Nishi, Tadamasa Toma, Toshiyasu Sugio, Satoshi Yoshikawa, Tatsuya Koyama
  • Patent number: 10803743
    Abstract: In particular embodiments, a computing system may receive ambient light measurements of a scene. The ambient light measurements may be generated by one or more light sensors of a vehicle. The system may receive an image captured by an optical sensor of the vehicle. The image may include color information associated with an object in a scene. The system may process the image to estimate a color associated with the object based on the ambient light measurements and the color information in the image. The system may determine the object based on the estimated color and may provide instructions to activate a safety feature in response to the determined object.
    Type: Grant
    Filed: May 2, 2018
    Date of Patent: October 13, 2020
    Assignee: Lyft, Inc.
    Inventors: Farzad Cyrus Foroughi Abari, Corey Frederick Bangs
  • Patent number: 10783431
    Abstract: Image search techniques and systems involving emotions are described. In one or more implementations, a digital medium environment of a content sharing service is described for image search result configuration and control based on a search request that indicates an emotion. The search request is received that includes one or more keywords and specifies an emotion. Images are located that are available for licensing by matching one or more tags associated with the image with the one or more keywords and as corresponding to the emotion. The emotion of the images is identified using one or more models that are trained using machine learning based at least in part on training images having tagged emotions. Output is controlled of a search result having one or more representations of the images that are selectable to license respective images from the content sharing service.
    Type: Grant
    Filed: November 11, 2015
    Date of Patent: September 22, 2020
    Assignee: Adobe Inc.
    Inventors: Zeke Koch, Gavin Stuart Peter Miller, Jonathan W. Brandt, Nathan A. Carr, Radomir Mech, Walter Wei-Tuh Chang, Scott D. Cohen, Hailin Jin
  • Patent number: 10772765
    Abstract: A computing platform that analyzes a captured video stream to identify a document depicted in the video stream, validates identification information corresponding to the document to display an information address associated with the document, and that initiates a transaction based on the validation of the identification information associated with the document.
    Type: Grant
    Filed: September 18, 2019
    Date of Patent: September 15, 2020
    Assignee: NANT HOLDINGS IP, LLC
    Inventors: Wayne C. Boncyk, Ronald H. Cohen
  • Patent number: 10762669
    Abstract: Systems and techniques are described for colorizing vector images. Color raster images that correspond to the vector images are used to perform a color mapping to colorize the vector images. The vector images are represented using non-overlapping planar arrangements of faces of the vector images, so that the color mapping may be performed with respect to the faces. The faces may be processed in parallel, to further facilitate a speed and scalability of the describes processes and results.
    Type: Grant
    Filed: May 16, 2018
    Date of Patent: September 1, 2020
    Assignee: ADOBE INC.
    Inventors: Vineet Batra, Mridul Kavidayal, Harish Kumar, Ankit Phogat
  • Patent number: 10748245
    Abstract: Firmware interfaces scale a fixed-font utilized by the firmware interfaces to display glyphs of the fixed-font at a native resolution or a preferred resolution of a display. A conversion factor is generated for scaling the glyphs of the font using the native resolution or the preferred resolution. The glyphs may be scaled using the conversion factor. The scaled glyphs may be stored and utilized to display text of the firmware interface in the native resolution or the preferred resolution.
    Type: Grant
    Filed: August 8, 2018
    Date of Patent: August 18, 2020
    Assignee: American Megatrends International, LLC
    Inventor: Artem Shchygel
  • Patent number: 10733953
    Abstract: A method for adjusting output images and multi-pictures display system are provided. The method includes following steps. A monitor resolution, a multi-pictures display mode and a rotation status of a display device are obtained. A display setting in an operating system (OS) of an image source apparatus is obtained. Whether the display setting in the OS satisfies an optimal display condition is determined according to the monitor resolution, the multi-pictures display mode and the rotation status of the display device. If the display setting does not satisfy the optimal display condition, the display setting in the OS is adjusting according to the optimal display condition. If the display setting satisfies the optimal display condition, a plurality of pixels of a single frame output by the image source device is one-by-one corresponding to a plurality of pixel units of the display device configured for displaying the single frame.
    Type: Grant
    Filed: July 26, 2018
    Date of Patent: August 4, 2020
    Assignee: ViewSonic International Corporation
    Inventors: Bonny Cheng, Chien-Heng Huang, Shr-Jung Jan
  • Patent number: 10716457
    Abstract: A method and system for calculating a volume of resected tissue from a stream of intraoperative images is disclosed. A stream of 2D/2.5D intraoperative images of resected tissue of a patient is received. The 2D/2.5D intraoperative images in the stream are acquired at different angles with respect to the resected tissue. A resected tissue surface is segmented in each of the 2D/2.5D intraoperative images. The segmented resected tissue surfaces are stitched to generate a 3D point cloud representation of the resected tissue surface. A 3D mesh representation of the resected tissue surface is generated from the 3D point cloud representation of the resected tissue surface. The volume of the resected tissue is calculated from the 3D mesh representation of the resected tissue surface.
    Type: Grant
    Filed: October 14, 2015
    Date of Patent: July 21, 2020
    Assignee: Siemens Aktiengesellschaft
    Inventors: Thomas Pheiffer, Stefan Kluckner, Ali Kamen
  • Patent number: 10719735
    Abstract: An information processing method, apparatus and video surveillance system have expandable functionality. The information processing method has an image acquisition step of acquiring an image; a first party feature quantity extracting step of extracting at least one first party feature quantity for describing a first party feature of the image from the acquired image; a third party feature quantity extracting step of invoking a third party algorithm to extract from the image at least one third party feature quantity for describing a third party feature other than the first party feature of the image; and a feature quantity correlation step of using the link information for describing the correlation between each of the first party feature quantities and each of the third party feature quantities of the same image to correlate each of the first party feature quantities of the image and each of the third party feature quantities.
    Type: Grant
    Filed: June 29, 2016
    Date of Patent: July 21, 2020
    Assignee: HITACHI, LTD.
    Inventors: Yulai Xie, Lu Wu, Peng Yang
  • Patent number: 10713780
    Abstract: The present disclosure provides a method and a computer-readable storage medium for color quality assessment of a batch-sample image based on multispectral imaging. The method comprises: selecting an operation area on a reference image and locating a corresponding operation area on a batch-sample image, wherein the reference image is used for color comparison with the batch-sample image to determine whether the batch-sample image satisfies a pass requirement; generating and comparing the color-information items obtained from the reference image and from the batch-sample image respectively and determine whether the batch-sample image satisfies the pass requirement based on one or more thresholds. This method can be applied to automatically and precisely assess the quality of mixed-color fabrics in textile industry, which is more objective, reliable, and cost-effective, as compared to conventional methods for color quality assessment.
    Type: Grant
    Filed: December 11, 2018
    Date of Patent: July 14, 2020
    Assignee: The Hong Kong Research Institute of Textiles and Apparel Limited
    Inventors: John Haozhong Xin, Hui-liang Shen, Quan-geng Ge
  • Patent number: 10681239
    Abstract: An image forming apparatus includes an image forming unit, an image reading unit, an image inspecting unit and a history generating unit. The image forming unit forms an image on a sheet. The image reading unit reads a sheet face on which the image is formed, thereby generating a scan image. The image inspecting unit compares the generated scan image with a normal image to detect an error in the scan image. When the image inspecting unit detects the error, the history generating unit generates detection information on the detected error and embeds the generated detection information in the scan image, thereby generating a history image.
    Type: Grant
    Filed: July 26, 2019
    Date of Patent: June 9, 2020
    Assignee: KONICA MINOLTA, INC.
    Inventor: Makoto Oki
  • Patent number: 10650281
    Abstract: The inventory capture system, method and apparatus (i.e., the inventory capture system) may provide for creating and updating an inventory of clothing for a user. The inventory capture system may use voice and image recognition to capture an inventory of clothing and provide users the ability to enhance the captured details about an inventory of clothing with annotations. Moreover, the inventory capture system may provide a way to facilitate retailers and users to leverage the user's existing inventory of clothing and augment the user's inventory of clothing with shared, purchased and/or rented clothing.
    Type: Grant
    Filed: June 29, 2016
    Date of Patent: May 12, 2020
    Assignee: Intel Corporation
    Inventors: Yuri I. Krimon, David I. Poisner
  • Patent number: 10643359
    Abstract: A transparent display device, a control method thereof and a controller thereof are provided. The transparent display device includes a transparent display, a first sensor set, a second sensor set and a controller. The first sensor set senses user information in a first side. The second sensor set senses scene information in a second side. The controller analyzes and determines a location and a gaze direction of a user according to the user information, calculates a first fixation point in the scene information and a second fixation point on the transparent display according to the location and the gaze direction of the user, determines a target object corresponding to the first fixation point according to the scene information, inquires target object information corresponding to the target object, and presents the target object information according to the second fixation point by the transparent display.
    Type: Grant
    Filed: December 12, 2017
    Date of Patent: May 5, 2020
    Assignees: Industrial Technology Research Institute, Intellectual Property Innovation Corporation
    Inventors: Cheng-Chung Lee, Kuang-Jung Chen, Sheng-Po Wang, Heng-Yin Chen
  • Patent number: 10643299
    Abstract: Embodiments of the present disclosure provide a method for accelerating CDVS extraction process based on a GPGPU platform, wherein for the stages of feature detection and local descriptor computation of the CDVS extraction process, operation logics and parallelism strategies of respective inter-pixel parallelism sub-procedures and respective inter-feature point parallelism sub-procedures are implemented by leveraging an OpenCL general-purpose parallelism programming framework, and acceleration is achieved by leveraging a GPU's parallelism computation capability; including: partitioning computing tasks for a GPU and a CPU; reconstructing an image scale pyramid storage model; assigning parallelism strategies to respective sub-procedures for the GPU; and applying local memory to mitigate the access bottleneck. The technical solution of the present disclosure may accelerate the CDVS extraction process and significantly enhances the extraction performance.
    Type: Grant
    Filed: December 5, 2016
    Date of Patent: May 5, 2020
    Assignee: PEKING UNIVERSITY SHENZHEN GRADUATE SCHOOL
    Inventors: Ronggang Wang, Shen Zhang, Zhenyu Wang, Wen Gao
  • Patent number: 10636160
    Abstract: Methods, systems, and devices for object detection are described. A device may extract features from an image and identify a region within the image for object detection. The device may apply an object model to a first set of features corresponding to positions within the region and one or more channels of the image. The first set of features may be selected so that the object model can detect a first orientation of an object. The device may also apply the object model to a second set of features, from the region, that are different from the first set of features. The second set of features may be selected so that the object model can detect a second orientation of the object (e.g., a flipped or rotated orientation of the object with respect to the first orientation).
    Type: Grant
    Filed: October 3, 2018
    Date of Patent: April 28, 2020
    Assignee: QUALCOMM Incorporated
    Inventors: Rakesh Nattoji Rajaram, Sujith Srinivasan
  • Patent number: 10638060
    Abstract: Techniques are provided for color correction of image frames, received from a hybrid RGBIR sensor, using resolution recovery of the red, green, blue (RGB), and infra-red (IR) channels. The color correction is to compensate for IR contamination of the RGB channels. A methodology implementing the techniques according to an embodiment includes a demosaic operation on the RGBIR image frame to generate full resolution red, green, blue, and IR frames. The demosaic operation includes filtering to extract Chroma and Luma components of the RGBIR image to reconstruct the full resolution images. The method also includes calculating an IR weighting factor for the pixels of each of the full resolution RGB frames, and correcting for IR contamination of those pixels by subtracting a scaled value of the corresponding pixels from the full resolution IR frame. The scaled value is based on the IR weighting factor associated with the pixel to be corrected.
    Type: Grant
    Filed: June 28, 2016
    Date of Patent: April 28, 2020
    Assignee: INTEL CORPORATION
    Inventors: Hsin-I Liu, Yongshen Ni
  • Patent number: 10636172
    Abstract: A robot control system and a method for automatic camera calibration is presented. The robot control system includes a control circuit configured to control a robot arm to move a calibration pattern to at least one location within a camera field of view, and to receive a calibration image from a camera. The control circuit determines a first estimate of a first intrinsic camera parameter based on the calibration image. After the first estimate of the first intrinsic camera parameter is determined, the control circuit determines a first estimate of a second intrinsic camera parameter based on the first estimate of the first intrinsic camera parameter. These estimates are used to determine an estimate of a transformation function that describes a relationship between a camera coordinate system and a world coordinate system. The control circuit controls placement of the robot arm based on the estimate of the transformation function.
    Type: Grant
    Filed: July 8, 2019
    Date of Patent: April 28, 2020
    Assignee: MUJIN, INC.
    Inventors: Russell Islam, Xutao Ye, Rosen Diankov
  • Patent number: 10628965
    Abstract: A method is described. The method includes determining normalized radiance of an image sequence based on a camera response function (CRF). The method also includes determining one or more reliability images of the image sequence based on a reliability function corresponding to the CRF. The method further includes extracting features based on the normalized radiance of the image sequence. The method additionally includes optimizing a model based on the extracted features and the reliability images.
    Type: Grant
    Filed: May 25, 2018
    Date of Patent: April 21, 2020
    Assignee: QUALCOMM Incorporated
    Inventors: Yan Deng, Michel Adib Sarkis, Yingyong Qi
  • Patent number: 10628890
    Abstract: A system, a computer readable storage medium, and a method for detecting insurance fraud or for comparing references use visual analytics-based techniques. The method can include identifying a scratch and a scratch location on a vehicle in a 3-dimensional rendering in comparison to a base image or in comparison to a stored image in a database, comparing one or more features of the scratch such as color features of the scratch in the scratch location in comparison to the scratch location or comparing one or more texture features of the scratch in the scratch location in comparison to the scratch location in the base image or the stored image. The method can further generate a similarity calculation based on the one or more comparisons for the scratch, the scratch location, the one or more scratch features of the scratch and presents a result in response to the similarity calculation.
    Type: Grant
    Filed: February 23, 2017
    Date of Patent: April 21, 2020
    Assignee: International Business Machines Corporation
    Inventors: Wei Shan Dong, Peng Gao, Chang Sheng Li, Wen Han Luo, Ren Jie Yao, Ting Yuan, Jun Zhu
  • Patent number: 10630891
    Abstract: Provided is a an image processing apparatus including a candidate detection unit configured to detect each of candidate images serving as candidates for a main subject for a plurality of frames of image data, and a main subject determination unit configured to obtain a degree of stable presence of the candidate images detected by the candidate detection unit within the image data spanning the plurality of frames and to determine a main subject among the candidate images using the degree of stable presence.
    Type: Grant
    Filed: June 7, 2017
    Date of Patent: April 21, 2020
    Assignee: Sony Corporation
    Inventor: Masaya Kinoshita
  • Patent number: 10609372
    Abstract: Input minimal noise levels of are computed over input codeword bins based on image content in input images of an input bit depth. The minimal noise levels are adjusted to generate approximated minimal noise levels of a higher bit depth. The approximated minimal noise levels are used to generate per-bin bit depths over the input codeword bins. The input codeword bins are classified into first codeword bins that have relatively high risks of banding artifacts and some other input codeword bins that have relatively low or zero risks of banding artifacts based on the per-bin bit depths. Portions of bit depths from the other input codeword bins are moved to the first input codeword bins to generate modified per-bin bit depths. A forward reshaping function constructed from the modified per-bin bit depths is used to reshape the input images into reshaped images used to generate output images.
    Type: Grant
    Filed: September 24, 2018
    Date of Patent: March 31, 2020
    Assignee: Dolby Laboratories Licensing Corporation
    Inventors: Guan-Ming Su, Amin Kheradmand, Navaneeth Kamballur Kottayil
  • Patent number: 10607340
    Abstract: A remote image transmission system, a display apparatus, and a guide displaying method of a display apparatus are provided. The remote image transmission system includes: an image capturing apparatus including a plurality of image pickup devices that are spaced from each other, the image capturing apparatus being configured to transmit, to a display apparatus, a plurality of images which are captured by the plurality of image pickup devices; and a display apparatus configured to generate a guide object indicating physical information of a captured object by using the plurality of received images, and to display the generated guide object and at least one of the plurality of images.
    Type: Grant
    Filed: January 11, 2017
    Date of Patent: March 31, 2020
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Min-soeng Kim, Joo-yoo Kim, Yong Kim, Soo-wan Kim, Eung-sun Kim, Jae-geol Cho, Tae-hwa Hong
  • Patent number: 10599914
    Abstract: The present disclosure discloses a method and apparatus for human face image processing. A specific embodiment of the method comprises: locating facial feature points in a human face image, extracting an image of a human face region according to a range defined by the facial feature points, transforming a facial image of the source image according to a face shape of the target image, transforming the facial image of the source image according to a complexion distribution of a facial region of the target image, and obtaining a new human face by combining the facial image of the source image and a facial image of the target image. The embodiment achieves a facial image processing with higher similarity to the user in the image, of simple steps, small calculation and high real-time performance.
    Type: Grant
    Filed: November 27, 2015
    Date of Patent: March 24, 2020
    Assignee: Baidu Online Network Technology (Beijing) Co., Ltd.
    Inventors: Guang Li, Jiawei Gu, Shasha Yan, Jianping Hao, Jiabin He, Li Xu, Jingtuo Liu, Fuguo Zhu, Zhengping Wei
  • Patent number: 10592759
    Abstract: An object recognition apparatus is disclosed. The present apparatus includes a storage unit for obtaining an initial image of a preset object and storing the initial image as a reference image; and a control unit for obtaining a first additional image of the preset object, determining whether the size of the first additional image relative to the initial image meets a first preset condition and additionally storing the first additional image as a reference image if the first additional image meets the preset condition.
    Type: Grant
    Filed: March 9, 2015
    Date of Patent: March 17, 2020
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Byoung-hyun Kim, Sang-yoon Kim, Kyoung-jae Park, Ki-jun Jeong, Eun-heui Jo