Patents Examined by Yubin Hung
  • Patent number: 10372981
    Abstract: Determining if a document is a text page includes partitioning the document into a plurality of cells, scaling each of the cells to a standardized number of pixels to provide a corresponding snippet for each of the cells, using a classifier to examine the snippets to determine which of the cells are classified as text and which of the cells are not classified as text, determining a volume of text for the document based on a total amount of text in the document corresponding to a sum of an amount of text in each of the cells classified as text, and determining that the document is a text page in response to the total amount exceeding a pre-determined threshold. In response to the total amount being less than the pre-determined threshold, cells not classified as text may be examined further. The classifier may be provided by training a neural net.
    Type: Grant
    Filed: September 22, 2016
    Date of Patent: August 6, 2019
    Assignee: EVERNOTE CORPORATION
    Inventors: Alexander Pashintsev, Boris Gorbatov, Eugene Livshitz, Vitaly Glazkov
  • Patent number: 10373308
    Abstract: The invention provides a sliced image processing method including following steps: analyzing a sliced object in a sliced image to determine whether the sliced object has a first contour line segment and a nearest second contour line segment, where the second contour line segment is located within a region encircled by the first contour line segment; determining whether vector directions of the first contour line segment and the second contour line segment are opposite when the sliced object has the first contour line segment and the second contour line segment, and correcting the vector direction of at least one of the first contour line segment and the second contour line segment when the vector directions of the first contour line segment and the second contour line segment are not opposite.
    Type: Grant
    Filed: July 10, 2017
    Date of Patent: August 6, 2019
    Assignees: XYZprinting, Inc., Kinpo Electronics, Inc.
    Inventors: Kuo-Yen Yuan, Ko-Wei Shih
  • Patent number: 10373330
    Abstract: A method for predicting the location of mark is performed for a substrate which includes a plurality of electronic device regions each electronic region includes a mark and a reference indication on a first surface and a sawing indication on a second surface opposite to the first surface. The method includes obtaining first and second image information for the first and second surfaces, extracting a sawing line based on the sawing indication in the second image information, calculating a first spaced distance between the sawing line and the reference indication in the first information, calculating a second spaced distance between the sawing line and the reference indication, and predicting the location of the mark based on whether the first and second spaced distances correspond to a predetermined reference distance. The mark is on each of the electronic device regions separated from each other along the sawing line.
    Type: Grant
    Filed: January 13, 2017
    Date of Patent: August 6, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventor: Tea-Geon Kim
  • Patent number: 10332281
    Abstract: Systems and methods for generating one or more denoised images from a series of noisy images acquired with a medical imaging system are described. In general, the systems and methods described here implement techniques whereby the series of noisy images are formed into a spatial-temporal or spatial-spectral image matrix in which each column represents a different noisy image. The image matrix is then processed to decompose the image matrix into basis images defined by a spatial and a temporal or spectral basis. Low rank solutions are enforced and extracted from the resulting decomposed image matrix as denoised images.
    Type: Grant
    Filed: January 29, 2016
    Date of Patent: June 25, 2019
    Assignee: Wisconsin Alumni Research Foundation
    Inventor: Guang-Hong Chen
  • Patent number: 10311550
    Abstract: Provided is an image processing device by which graininess of a target image is eliminated while outlines in the target image are maintained. The image processing device includes a smoothing unit and a weighted averaging unit. The smoothing unit is configured to generate a smooth image by smoothing the target image. The weighted averaging unit is configured to generate a weighted average image by performing weighted averaging of the target image and a difference image. The difference image is an image that is obtained by subtracting the target image from the smooth image.
    Type: Grant
    Filed: January 20, 2015
    Date of Patent: June 4, 2019
    Assignee: NORITSU PRECISION CO., LTD.
    Inventor: Koji Kita
  • Patent number: 10311579
    Abstract: An apparatus and method for detecting a foreground in an image is provided, and the foreground detecting apparatus includes a context information estimator configured to estimate context information on a scene from an image frame of the image, a background model constructor configured to construct a background model of the image frame using the estimated context information, and a foreground detector configured to detect a foreground from the image frame based on the constructed background model.
    Type: Grant
    Filed: January 13, 2017
    Date of Patent: June 4, 2019
    Assignees: Samsung Electronics Co., Ltd., Seoul National University R&DB Foundation
    Inventors: Ki Min Yun, Jin Young Choi, Jong In Lim
  • Patent number: 10303971
    Abstract: A method of classifying an image is disclosed. The method comprises: applying a computer vision procedure to the image to detect therein candidate image regions suspected as being occupied by a target; presenting to an observer each candidate image region as a visual stimulus, while collecting neurophysiological signals from a brain of the observer; processing the neurophysiological signals to identify a neurophysiological event indicative of a detection of the target by the observer; and determining an existence of the target in the image is based, at least in part, on the identification of the neurophysiological event.
    Type: Grant
    Filed: June 2, 2016
    Date of Patent: May 28, 2019
    Assignee: InnerEye Ltd.
    Inventors: Amir B. Geva, Leon Y. Deouell, Sergey Vaisman, Omri Harish, Ran El Manor, Eitan Netzer, Shani Shalgi
  • Patent number: 10304206
    Abstract: An information processing apparatus: obtains a feature distribution by calculating a distribution of features, existing in an environment, that can be used to measure a position and orientation of a measurement viewpoint; decides on a feature pattern to be laid out and a layout position of the feature pattern in the environment that enable the obtainment of a feature distribution that enhances an accuracy at which the position and orientation of the measurement viewpoint is calculated; and presents the feature pattern and the layout position of the feature pattern that have been decided on.
    Type: Grant
    Filed: January 19, 2017
    Date of Patent: May 28, 2019
    Assignee: CANON KABUSHIKI KAISHA
    Inventors: Yusuke Nakazato, Daisuke Kotake, Akihiro Katayama
  • Patent number: 10297059
    Abstract: An image processor provides a combined image of an object from first and second cameras. The image processor receives a first image from a first camera and a second image from a second camera. The first and second images each include a field of view and metadata associated with the image. The image processor determines whether a combined image of the first and second images will be viewed by a person or a machine. If the combined image is to be processed by a machine, the first and second metadata are included with the combined image and sent to the machine. If the combined image is to be viewed by a person, the combined image includes a subset of the metadata so that the image is not too large or too cluttered.
    Type: Grant
    Filed: December 21, 2016
    Date of Patent: May 21, 2019
    Assignee: MOTOROLA SOLUTIONS, INC.
    Inventors: Karen Suttmann, Stanko Jelavic
  • Patent number: 10290083
    Abstract: A method for deblurring a blurry image (400) includes the steps of: performing a first phase of deconvolution (202) with a first phase regularization spatial mask (300) to reconstruct the main edges and generate a first phase latent sharp image (404) having reconstructed main edges; and performing a second phase of deconvolution (204) with a second phase regularization spatial mask (304) to reconstruct the texture and generate a second phase latent sharp image (406). The second phase regularization spatial mask (304) can be different from the first phase regularization spatial mask (300).
    Type: Grant
    Filed: February 21, 2018
    Date of Patent: May 14, 2019
    Assignee: NIKON CORPORATION
    Inventor: Radka Tezaur
  • Patent number: 10284750
    Abstract: Said method comprises a first cusp-oriented lightness-mapping step and a second lightness-mapping step in which a source color (N) is mapped into a mapped color (N?) having the same hue (H?=H) and the same chroma (C?=C) as the source color, where the second mapping step is defined such as to bring more colors in a target color gamut and more colors closer to the boundary of this target gamut.
    Type: Grant
    Filed: January 14, 2017
    Date of Patent: May 7, 2019
    Assignee: INTERDIGITAL CE PATENT HOLDINGS
    Inventors: Patrick Morvan, Jurgen Stauder, Corinne Poree
  • Patent number: 10274372
    Abstract: A system and method for improving the outcome and consistency of hair coloring is provided. In an example method, an image of hair having a sample color may be received. A color space characteristic associated with the hair sample may be determined. An indication of a target color may be received. A colorant formulation may be identified for changing the hair from the sample color to the target color.
    Type: Grant
    Filed: September 24, 2015
    Date of Patent: April 30, 2019
    Assignee: International Software Development, Inc.
    Inventors: Aaron James Conti, Donald James Conti, Jon F. Maple, Patrick J. McIvor, Jr., Leonard G. Case
  • Patent number: 10262444
    Abstract: Image processing for creating a composite image by using a plurality of input images is performed in the following manner. An ID map is created in which each pixel on a coordinate system of the composite image is assigned an ID value among ID values each of which identifies a corresponding one of the plurality of input images. The composite image is created based on the ID map. The composite image and the ID map are caused to be superimposed and displayed on a display device. User input that is a drag operation performed on the ID map that is superimposed and displayed together with the composite image is obtained. The ID map is changed in accordance with the user input. The composite image is updated in accordance with the change in the ID map.
    Type: Grant
    Filed: December 20, 2016
    Date of Patent: April 16, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Kyohei Kikuta
  • Patent number: 10255486
    Abstract: An image processing apparatus stores, as instance images, a plurality of face images obtained by photographing respective faces of a plurality of persons on a plurality of photographing conditions, while associating the persons with the photographing conditions for each part; obtains the photographing condition of the input face image; approximates the respective parts of the input face images, by a combination of the instance images of the plurality of persons stored in association with the parts and the obtained photographing conditions; decides, for each part of the input face image, a combination corresponding to the combination in the approximation from the instance images of the plurality of persons stored in association with the part and a predetermined photographing condition; and generates an image obtained by photographing the input face image on the predetermined photographing condition, by synthesizing the obtained combination on the whole input face image.
    Type: Grant
    Filed: March 3, 2016
    Date of Patent: April 9, 2019
    Assignee: CANON KABUSHIKI KAISHA
    Inventors: Shunsuke Nakano, Hiroshi Sato, Yuji Kaneda, Atsuo Nomoto
  • Patent number: 10242243
    Abstract: A fingerprint sensor includes a first conductive pattern formed on one side of a core, a second conductive pattern formed on the first conductive pattern, an insulating layer formed between the first conductive pattern and the second conductive pattern, a dielectric layer configured to cover the second conductive pattern, and a protective layer covering the dielectric layer, wherein the protective layer includes a photosetting resin.
    Type: Grant
    Filed: August 2, 2016
    Date of Patent: March 26, 2019
    Assignee: Samsung Electro-Mechanics Co., Ltd.
    Inventors: Woon-Chun Kim, Ga-Young Yoo, Hyung-Mi Jung, Hyun-Chul Jung, Jeong-Bok Kwak, Ji-Hye Shim
  • Patent number: 10244146
    Abstract: A computer-implemented method for color correction includes obtaining a noise evaluation image by adding noise to a noise-free image, color correcting the noise evaluation image using a plurality of color correction parameters, color correcting the noise-free image using the plurality of color correction parameters, determining a noise amplification metric at least by comparing the corrected noise evaluation image with the corrected noise-free image, and adjusting the plurality of color correction parameters based on the noise amplification metric.
    Type: Grant
    Filed: May 11, 2018
    Date of Patent: March 26, 2019
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventors: Wei Chen, Zisheng Cao
  • Patent number: 10235602
    Abstract: An artificial intelligence system for identifying attributes in an image. The system may include a processor in communication with a client device; and a storage medium. The storage medium may store instructions that, when executed, configure the processor to perform operations including: extracting first features; categorizing the first images in a first group or a second group; modifying first metadata associated with each image in the first images to include a binary label; calculating a classification function; classifying a second plurality of images using the classification function; extracting second features from the second images classified in the first group; categorizing the second images in the first group by attribute; calculating an attribute identification function that identifies attributes of the second images; and identifying at least one attribute associated with a client image using the attribute identification function, the client image being received from the client device.
    Type: Grant
    Filed: April 9, 2018
    Date of Patent: March 19, 2019
    Assignee: CAPITAL ONE SERVICES, LLC
    Inventors: Sunil Subrahmanyam Vasisht, Geoffrey Dagley, Qiaochu Tang, Sean Reddy, Jason Richard Hoover, Stephen Michael Wylie, Micah Price
  • Patent number: 10217243
    Abstract: A method of modifying a scene model for a sequence of input images includes receiving, selecting, determining, and modifying. Scene modes associated with the sequence are received. For each image pixel in an input image of the sequence, two scene modes are selected from the received scene modes based on distances between the image pixel color value and the scene modes color values at a corresponding pixel location. It is determined if the image pixel color value matches the color value of any of the selected scene modes. It is determined if the image pixel color value is a mixture of the color values of the selected scene modes. The color value of a closest selected scene mode is modified or is maintained depending on whether there is one matched mode and the image pixel color value is not a mixture of the color values of the selected scene modes.
    Type: Grant
    Filed: December 20, 2016
    Date of Patent: February 26, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Quang Tuan Pham
  • Patent number: 10216972
    Abstract: Embodiments herein describe an input device that includes a rectangular array of sensor electrodes connected to sensor modules that measure capacitive sensing signals corresponding to the electrodes. During a charge stage, the input device applies a charging voltage to neighboring sensor electrodes in the array. The input device then drives the neighboring sensor electrodes to a reference voltage and measures the amount of charge accumulated on at least one of the sensor electrodes. Because of the parasitic capacitance between the neighboring electrodes, driving these electrodes (even the ones not being measured) to the same charging and reference voltages reduces the effect of the parasitic capacitance on the capacitive sensing measurement. Thus, during the read stage, the measured charge is affected primarily by the capacitance between the sensor electrodes and an input object (e.g., a finger).
    Type: Grant
    Filed: January 13, 2017
    Date of Patent: February 26, 2019
    Assignee: SYNAPTICS INCORPORATED
    Inventors: Arash Akhavan Fomani, Kirk Hargreaves, Patrick Smith
  • Patent number: 10204421
    Abstract: A digital magazine server presents content, which may include images, retrieved from various sources to a user. To improve presentation of images while allowing modification of images, the digital magazine server identifies feature points in an image and identifies regions of the image including the feature points. Groups of regions are generated based at least on the number of feature points in each region and the location of each region. Based on information associated with the groups, such as the location of various groups and the aspect ratio of various groups, one or more groups are selected and associated with the image. The selected groups may identify regions of the image including an object or not including an object, providing information for modifying the image without obscuring objects in the image.
    Type: Grant
    Filed: June 16, 2017
    Date of Patent: February 12, 2019
    Assignee: Flipboard, Inc.
    Inventors: Meng Guo, Filipe Fortes