Patents Examined by Bhavesh M. Mehta
  • Patent number: 10289884
    Abstract: According to an embodiment, an image analyzer includes a set unit, a first calculator, a second calculator, a divider, a third calculator, and a specifier. The set unit sets multiple partial regions in the image. The first calculator calculates an optical flow in a partial region. The second calculator calculates the density of an object included in the partial region. The divider divides the image into the multiple blocks. The third calculator calculates, for a block, a statistical amount that is derived from the density and the moving amount of the object derived from the optical flow for the partial region included in the block. The specifier specifies the block, out of the blocks, as an unsteady block that is in an unsteady state on the basis of the statistical amount.
    Type: Grant
    Filed: August 25, 2016
    Date of Patent: May 14, 2019
    Assignee: Kabushiki Kaisha Toshiba
    Inventors: Quoc Viet Pham, Tomoki Watanabe
  • Patent number: 10281200
    Abstract: Disclosed are various embodiments for determining whether food in a refrigerator has spoiled. An application executing on a computing device receives an image from a refrigerator of a compartment of the refrigerator. The application then analyzes the image to identify a food item in the image. Subsequently, the application analyzes the image to identify a potentially spoiled area of the food item. The application then compares the potentially spoiled area of the food item to a model of a spoiled food item. Afterwards, the application determines that the identified food item has spoiled based at least in part on a comparison of the potentially spoiled area of the identified food item to the model of the spoiled food item.
    Type: Grant
    Filed: March 14, 2016
    Date of Patent: May 7, 2019
    Assignee: Amazon Technologies, Inc.
    Inventor: Simon Kurt Johnston
  • Patent number: 10282627
    Abstract: A method for processing handwriting data is provided. The method includes filtering the handwriting data to remove one or more ineffective data points, acquiring a number of sampling points included in the handwriting data, when the number of the sampling points exceeds a first threshold, screening the handwriting data such that the number of the sampling points included in the screened handwriting data is not greater than the first threshold, acquiring attribute information of the handwriting data and processing the attribute information based on a preset length, and transmitting the screened handwriting data through a network.
    Type: Grant
    Filed: January 19, 2016
    Date of Patent: May 7, 2019
    Assignee: ALIBABA GROUP HOLDING LIMITED
    Inventor: Yuewei Zeng
  • Patent number: 10275886
    Abstract: A medical imaging system (5) includes a workstation (20), a coarse segmenter (30), a fine segmenter (32), and an enclosed tissue identification module (34). The workstation (20) includes at least one input device (22) for receiving a selected location as a seed in a first contrasted tissue type and a display device (26) which displays a diagnostic image delineating a first segmented region of a first tissue type and a second segmented region of a second contrasted tissue type and identified regions which include regions fully enclosed by the first segmented region as a third tissue type. The coarse segmenter (30) grows a coarse segmented region of coarse voxels for each contrasted tissue type from the seed location based on a first growing algorithm and a growing fraction for each contrasted tissue type.
    Type: Grant
    Filed: January 5, 2017
    Date of Patent: April 30, 2019
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Astrid Ruth Franz, Stefanie Remmele, Jochen Keupp
  • Patent number: 10268889
    Abstract: A method of identifying a target material in a spectral image includes acquiring a spectral image of a scene. The method also includes performing image segmentation to partition the spectral image into a plurality of segments. The method includes accessing a database of spectral models of a plurality of materials to determine a material whose spectral model is most similar to the spectral data for the segment, a difference between the spectral model of the material and the spectral data for the segment including measurable reflectance or radiance at characteristic frequencies or wavelengths. The method also includes analyzing a database of spectral data for a plurality of target materials to identify a target material whose spectral data also has measurable reflectance or radiance at the characteristic frequencies or wavelengths. And the method includes outputting an identifier of the target material for display with the spectral image.
    Type: Grant
    Filed: March 31, 2017
    Date of Patent: April 23, 2019
    Assignee: The Boeing Company
    Inventors: Timothy E. Brown, Robert J. Klein
  • Patent number: 10262206
    Abstract: A method for calibrating crop residue data for a field acquired using a vision-based system may include receiving image data associated with an imaged portion of the field, analyzing the image data using a first residue-estimating technique to determine a first estimated value of a crop residue parameter for the imaged portion of the field, and analyzing the image data using a second residue-estimating technique to determine a second estimated value of the crop residue parameter for the imaged portion of the field. In addition, when a differential exists between the first and second estimated values, the method may also include adjusting at least one of the first estimated value or one or more additional estimated values of the crop residue parameter determined using the first residue-estimating technique based on at least one of the second estimated value or the differential between first and second estimated values.
    Type: Grant
    Filed: May 16, 2017
    Date of Patent: April 16, 2019
    Assignee: CNH Industrial America LLC
    Inventor: John Posselius
  • Patent number: 10262395
    Abstract: An image processing method and apparatus, and an electronic device are provided. The image sensor is controlled to output the compositing image. The merged image and the color-block image can be output respectively under different scenes requiring different imaging effect. Then the preset target region is identified in the merged image. Finally, the processed merged image (i.e. the merged true-color image) corresponding to the preset target region is composited with the processed color-block image (i.e. the simulation true-color image). Therefore, the signal-to-noise ratio, the resolution and distinguishability are improved. The placed location in the simulation true-color image can be manually adjusted, thereby enhancing user experience.
    Type: Grant
    Filed: April 30, 2018
    Date of Patent: April 16, 2019
    Assignee: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP., LTD.
    Inventor: Cheng Tang
  • Patent number: 10262202
    Abstract: A method includes: extracting a first line segment pair including a combination of line segments selected from a plurality of line segments included in an image of a form to be recognized; calculating a first feature amount which represents a relationship between the line segments in the extracted first line segment pair; extracting a candidate for a form identifier of the form to be recognized based at least on the calculated first feature amount and a second feature amount in line segments in a second line segment pair correlated with a form identifier which is registered in advance; extracting corresponding line segment pairs which include a line segment correlated with the candidate for the form identifier and a line segment of the form to be recognized; and specifying the form identifier of the form to be recognized based at least on the degree of overlapping.
    Type: Grant
    Filed: March 24, 2017
    Date of Patent: April 16, 2019
    Assignee: FUJITSU LIMITED
    Inventors: Yutaka Katsuyama, Eigo Segawa
  • Patent number: 10255684
    Abstract: Systems and methods for correcting motion during medical imaging involve using a detector to track annihilation photons produced by one of (i) external emitting sources placed onto a body of a person being imaged or (ii) an object of interest in the body. Motion information is generated based on the tracking. A motion-corrected image is formed from recorded image data, using the motion information.
    Type: Grant
    Filed: June 6, 2016
    Date of Patent: April 9, 2019
    Assignee: UNIVERSITY OF TENNESSEE RESEARCH FOUNDATION
    Inventors: Dustin R. Osborne, Dongming Hu, Sang Hyeb Lee
  • Patent number: 10255496
    Abstract: A method and device for capturing a positionally corrected image of a document is disclosed. The method comprises the steps of: obtaining a two-dimensional image of the document with a mobile terminal apparatus; performing edge detection within the two-dimensional image to identify edges of the document; determining angles between detected edges; calculating, based on the detected edges and the angles determined, a three-dimensional position of the document relative to a position of the mobile terminal apparatus; calculating correction information to correct, by relative movement, the position of the document relative to the position of the mobile terminal apparatus; providing first guidance information derived from the correction information to a user of the mobile terminal apparatus, guiding the user to perform the relative movement; and capturing a positionally corrected image of the document. Thereby, the document can be captured with a quality sufficient to permit Optical Character Recognition (OCR).
    Type: Grant
    Filed: March 6, 2017
    Date of Patent: April 9, 2019
    Assignee: Open Text SA ULC
    Inventor: Simon Dominic Copsey
  • Patent number: 10255675
    Abstract: In one embodiment, a medical image processing apparatus includes memory circuitry configured to store a program; and processing circuitry configured, by executing the program, to set a region of interest in a medical image, set an analysis region in the region of interest by reducing the region of interest, and calculate feature amount in the analysis region.
    Type: Grant
    Filed: December 12, 2016
    Date of Patent: April 9, 2019
    Assignee: TOSHIBA MEDICAL SYSTEMS CORPORATION
    Inventors: Kousuke Sakaue, Hitoshi Yamagata
  • Patent number: 10242153
    Abstract: A method of computing the risk profile of a neoplastic tissue in a patient is disclosed. The method includes the steps of (a) processing a sample of tumor tissue or cancer cells from the patient in a form suitable for visualization and demarcation of cell nuclei, individually distinguishable centrosomes (iCTRs) and megacentrosomes (mCTRs) in a region of interest (ROI) defined by a plurality of cell nuclei; (b) determining the numbers of iCTRs and mCTRs associated with each cell nucleus in the ROI; (c) determining the volume of each iCTR and mCTR in the ROI; and (d) calculating one or more centrosome amplification scores (CASs) values for the sample based on steps (b) and (c), wherein the one or more CASs indicate the severity of centrosome amplification, the frequency of centrosome amplification, or both, and wherein the one or more scores provide a measure of a level of risk and/or a prognosis associated with the neoplastic tissue.
    Type: Grant
    Filed: January 30, 2017
    Date of Patent: March 26, 2019
    Assignee: NOVAZOI THERANOSTICS
    Inventors: Ritu Aneja, Padmashree C. G. Rida
  • Patent number: 10235770
    Abstract: A system for pothole detection comprises an input interface configured to receive sensor data and a pothole detector configured to determine a pothole based at least in part on the sensor data using a model, wherein the model is used to classify sensor data; and store pothole data associated with the pothole, wherein the pothole data comprises a pothole video.
    Type: Grant
    Filed: March 6, 2017
    Date of Patent: March 19, 2019
    Assignee: Lytx, Inc.
    Inventors: Brett Hoye, Stephen Krotosky
  • Patent number: 10235750
    Abstract: A method is proposed for identifying an anatomical structure within a spatial-temporal image (i.e. a series of frames captured as respective times). A current frame of spatial-temporal medical image is processed using information from one or more previous and/or subsequent temporal frames, to aid in the segmentation of an object or a region of interest (ROI) in a current frame. The invention is applicable to both two- and three-dimensional spatial-temporal images (i.e., 2D+time or 3D+time), and in particular to cardiac magnetic resonance (CMR images). An initialization process for this method segments the left ventricle (LV) in a CMR image by a fuzzy c-means (FCM) clustering algorithm which employs a circular shape function as part of the definition of the dissimilarity measure.
    Type: Grant
    Filed: February 27, 2015
    Date of Patent: March 19, 2019
    Assignees: Agency for Science, Technology and Research, Singapore Health Services Pte Ltd
    Inventors: Xulei Yang, Yi Su, Si Yong Yeo, Liang Zhong, Ru San Tan
  • Patent number: 10229324
    Abstract: An apparatus for video summarization using semantic information is described herein. The apparatus includes a controller, a scoring mechanism, and a summarizer. The controller is to segment an incoming video stream into a plurality of activity segments, wherein each frame is associated with an activity. The scoring mechanism is to calculate a score for each frame of each activity, wherein the score is based on a plurality of objects in each frame. The summarizer is to summarize the activity segments based on the score for each frame.
    Type: Grant
    Filed: December 24, 2015
    Date of Patent: March 12, 2019
    Assignee: Intel Corporation
    Inventors: Myung Hwangbo, Krishna Kumar Singh, Teahyung Lee, Omesh Tickoo
  • Patent number: 10223581
    Abstract: A system and method are presented for video analysis. In an embodiment, video analysis may be applied in a contact center environment to aid contact center agents in improving the effectiveness of interactions. Feedback may be provided in real time to an agent on their interaction. Body mechanics may be examined and rated. In an embodiment, body mechanics may be combined with indicators which inform an agent on their performance. Tips may also be provided to an agent on how to improve performance in the form of audio overlay, video overlay, reports, or any combination of these. Feedback may also be used to improve the routing of communications within the contact center. Static and dynamic visual characteristics may also be used to improve routing decisions.
    Type: Grant
    Filed: December 27, 2015
    Date of Patent: March 5, 2019
    Inventors: Richard J. Walsh, David Allan Ertel, II
  • Patent number: 10206646
    Abstract: A method and apparatus for extracting centerline representations of vascular structures in medical images is disclosed. A vessel orientation tensor for each of a plurality of voxels associated with the target vessel, such as a coronary artery, in a medical image, such as a coronary tomography angiography (CTA) image, using a trained vessel orientation tensor classifier. A flow field is estimated for the plurality of voxels associated with the target vessel in the medical image based on the vessel orientation tensor estimated for each of the plurality of voxels. A centerline of the target vessel is extracted based on the estimated flow field for the plurality of vessels associated with the target vessel in the medical image by detecting a path that carries maximum flow.
    Type: Grant
    Filed: March 8, 2017
    Date of Patent: February 19, 2019
    Assignee: Siemens Healthcare GmbH
    Inventors: Mehmet Akif Gulsun, Yefeng Zheng, Saikiran Rapaka, Viorel Mihalef, Puneet Sharma, Gareth Funka-Lea
  • Patent number: 10198842
    Abstract: The methods and systems described herein comprise: receiving a first image and a second image, a first timestamp and a second timestamp, the first image and the second image depicting a common object; determining an actual position of first common object pixels and second common object pixels; computing a common object motion information based on the actual position of the first common object pixels and the second common object pixels, the first and the second timestamp; receiving a third image and a third timestamp, the third image depicting the common object; determining an actual position of third common object pixels; computing an estimated position of the third common object pixels based on the common object motion information, the third timestamp and the third pixels; if the actual position of the third common object pixels and the estimated position of the third common object pixels don't match, generating the synthetic image.
    Type: Grant
    Filed: March 15, 2017
    Date of Patent: February 5, 2019
    Assignee: YANDEX EUROPE AG
    Inventor: Anton Vasilyevich Korzunov
  • Patent number: 10198654
    Abstract: In various example embodiments, a system and method are provided for automated estimation of a saliency map for an image based on a graph structure comprising nodes corresponding to respective superpixels on the image, the graph structure including boundary-connecting nodes that connects each non-boundary node to one or more boundary regions. Each non-boundary node is in some embodiments connected to all boundary nodes by respective boundary-connecting edges forming part of the graph. Edge weights are calculated to generate a weighted graph. Saliency map estimation comprises bringing respective nodes for similarity to a background query. The edge weights of at least some of the edges are in some embodiments calculated as a function of a geodesic distance or shortest path between the corresponding nodes.
    Type: Grant
    Filed: June 24, 2016
    Date of Patent: February 5, 2019
    Assignee: eBay Inc.
    Inventors: Qiaosong Wang, Wen Zheng, Robinson Piramuthu
  • Patent number: 10188321
    Abstract: A method of measuring animal health, such as rodent health, such as a degree of arthritis, is described. Steps include capturing video frames, then using optical flow to compute vector fields for each frame, then taking a maximum vector value over a first time period, then selecting a set of maximum vector values over a second time period, then clipping those values to a maximum, then computing an average of those values. This is an animal health metric. Metrics may be organized into a plot over time and may then be compared against known plots to compute an overall animal health and measure efficacy of treatments or other animal characteristics or behavior, including predictive.
    Type: Grant
    Filed: May 31, 2016
    Date of Patent: January 29, 2019
    Assignee: Vium, Inc.
    Inventors: Daniel J. Ford, Jonathan Betts-Lacroix