Patents Examined by Kathleen Y Dulaney
  • Patent number: 10325425
    Abstract: Systems and methods for generating vehicle operation logs are provided. According to certain aspects, an electronic device may receive and analyze image data depicting an individual located within a vehicle. The electronic device may also interface with a set of sensors to retrieve or access relevant data related to the operation of the vehicle, such as time and date information, location information, and other data. The electronic device may generate a vehicle operation log that associates the individual depicted in the image data with the vehicle operating parameters.
    Type: Grant
    Filed: March 22, 2017
    Date of Patent: June 18, 2019
    Assignee: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY
    Inventors: Kenneth J. Sanchez, Aaron Scott Chan
  • Patent number: 10325345
    Abstract: An image processing device that transforms an image includes a storage unit configured to store coordinate values in a coordinate system of a pre-transformed image, each of the coordinate value corresponding to a grid point in a coordinate system of a transformed image, a selection unit configured to select a grid point in the vicinity of a target pixel in the transformed image, a calculation unit configured to refer to the pre-transformed coordinate value, corresponding to the selected grid point and stored in the storage unit, and to calculate a pre-transformed coordinate value corresponding to the target pixel, using the referred coordinate value, and an output unit configured to output a pixel value of the coordinate value calculated in the pre-transformed image, as a pixel value of the target pixel in the transformed image.
    Type: Grant
    Filed: April 12, 2017
    Date of Patent: June 18, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventors: Tetsurou Kitashou, Tadayoshi Nakayama
  • Patent number: 10311317
    Abstract: Provided is a method for generating teacher data for image recognition while reducing the number of images used as the basis. A captured image is obtained by imaging an object by an imaging device C arranged at a first designated position Pi. A basic image region Si is extracted from the captured image. The teacher data is generated as a result of coordinate transformation of the basic image region Si from one image coordinate system to a coordinate system of a captured image by the imaging device C on the assumption that the imaging device C is arranged at a second designated position Pj which is different from the first designated position Pi.
    Type: Grant
    Filed: February 16, 2017
    Date of Patent: June 4, 2019
    Assignee: HONDA MOTOR CO., LTD.
    Inventor: Tomoyuki Kanamaru
  • Patent number: 10303756
    Abstract: This invention relates to creating a narrative description of media content. In an embodiment, a computer-implemented method describes content of a group of images. The group of images includes a first image and a second image. A first object in the first image is recognized to determine a first content data. A second object in the second image is recognized to determine a second content data. Finally, a narrative description of the group of images is determined according to a parameterized template and the first and second content data.
    Type: Grant
    Filed: August 4, 2017
    Date of Patent: May 28, 2019
    Assignee: Google LLC
    Inventor: Hyduke Noshadi
  • Patent number: 10303975
    Abstract: Methods and systems for automatic detection of landmarks in digital images and annotation of those images are disclosed. A method for detecting and annotating landmarks in digital images includes the steps of automatically assigning a tag descriptive of a landmark to one or more images in a plurality of text-associated digital images to generate a set of landmark-tagged images, learning an appearance model for the landmark from the set of landmark-tagged images, and detecting the landmark in a new digital image using the appearance model. The method can also include a step of annotating the new image with the tag descriptive of the landmark.
    Type: Grant
    Filed: July 30, 2017
    Date of Patent: May 28, 2019
    Assignee: Google LLC
    Inventors: Hartwig Adam, Li Zhang
  • Patent number: 10284879
    Abstract: The present technology relates to an image processing apparatus and method that enable suppression of increase in the load of encoding and decoding floating point-precision image data. The image processing apparatus of the present technology transforms floating point-precision image data composed of a sign, an exponent, and a mantissa into integer-precision image data, and encodes the integer-precision image data obtained by transformation. The present technology can be applied to image processing apparatuses such as encoding apparatuses that encode image data and decoding apparatuses that decode encoded data obtained by encoding image data, for example.
    Type: Grant
    Filed: June 23, 2015
    Date of Patent: May 7, 2019
    Assignee: SONY CORPORATION
    Inventor: Takahiro Fukuhara
  • Patent number: 10217239
    Abstract: Shifting of a focus of a first user within a first 360-view data is tracked during an observation of the first 360-view data by the first user to determine a first set of POIs in the 360-view data where the first user pauses for a duration. A subset of the first set of POIs is regarded as non-obvious POIs in the first 360-view data. For a second user who has not observed the 360-view data, a second set of POIs is computed and includes a second subset of non-obvious POIs. A non-obvious POI from the second subset is matched to a particular non-obvious POI in the first subset. During an observation of the first 360-view data by the second user, a location of focus is computed. Guidance is provided by computing a movement of the focus from the location to a non-obvious POI in the first 360-view data.
    Type: Grant
    Filed: February 15, 2017
    Date of Patent: February 26, 2019
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: James E. Bostick, John M. Ganci, Jr., Martin G. Keen, Sarbajit K. Rakshit
  • Patent number: 10217257
    Abstract: Devices, systems and methods are disclosed for determining if an image is displayed using multiple pages of content and loading and displaying the multiple pages in a single context. Bordering pixels may be compared between a first page and a second page to determine if the pixels match above a threshold. If they match above a threshold, the first page and the second page may be aligned, stitched together and displayed in a shared context, allowing a user to pan and zoom between the first page and the second page without interruption, margins, page breaks or the like. The first page and/or the second page may be compared to additional pages of content and each of the additional pages of content is included in the shared context if matching above the threshold.
    Type: Grant
    Filed: March 17, 2015
    Date of Patent: February 26, 2019
    Assignee: AMAZON TECHNOLOGIES, INC.
    Inventor: Sudhir Kumar
  • Patent number: 10217195
    Abstract: Devices and techniques are generally described for image editing. In various examples, color image data and segmentation image data may be identified. In some examples, the segmentation image data may identify a first portion of the color image data as a foreground region and a second portion of the color image data as a background region. A segmentation boundary may be identified between the foreground region and the background region. A first area of the second portion may be identified, where the first area extends from the segmentation boundary to a first area outer boundary. A second area of the second portion may be identified, where the second area extends from the first area outer boundary to a second area outer boundary. A blended and blurred representation of the first area and the second area may be generated.
    Type: Grant
    Filed: April 17, 2017
    Date of Patent: February 26, 2019
    Assignee: AMAZON TECHNOLOGIES, INC.
    Inventors: Amit Kumar Agrawal, Prakash Ramu, Apoorv Chaudhri, Noam Sorek, Abhishek Singh, Rohith Mysore Vijaya Kumar
  • Patent number: 10217294
    Abstract: A three dimensional (3D) model of an object or environment may be created from images and other information of the object or environment. The 3D model may be created by aligning the images. The 3D model may include surfaces that are based on surfaces of the object or environment. The 3D model may be displayed, exported, modified and so on.
    Type: Grant
    Filed: March 30, 2017
    Date of Patent: February 26, 2019
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Blaise Aguera Y. Arcas, Brett D. Brewer, Steven M. Drucker, Karim T Farouki, Gary W. Flake, Stephen Lawler, Donald J. Lindsay, Adam P Sheppard
  • Patent number: 10210616
    Abstract: Methods are described for detecting an edge of an object within an image with a fractional differential operator. Methods are also described for calculating 3D information using a strip pattern and the disclosed edge detection method. The fractional differential operator may be a modified Riesz space fractional differential operator. When calculating the fractional derivative of the image, a kernel approximation, in which a scaled Gaussian kernel function or a simplified scaled Gaussian kernel function, is applied to discretize the modified Riesz space fractional differential operator locally. The disclosed method improves the accuracy of edge detection, eliminates the need of applying additional fractional integration for noise suppression, and requires a smaller mask length to achieve desired accuracy.
    Type: Grant
    Filed: April 27, 2017
    Date of Patent: February 19, 2019
    Assignee: HONG KONG APPLIED SCIENCE AND TECHNOLOGY RESEARCH INSTITUTE CO., LTD.
    Inventor: Ka Chun Cheung
  • Patent number: 10212312
    Abstract: Methods of image calibration and in particular of image calibration having a multiple of color scales as well as to quantitative imaging such as quantitative medical imaging, or to a display device or to a system for displaying an image, or to a controller of a display, or to software to enable the image calibration, or to a visualization application and a display. The method for processing an image, includes the steps of: —selecting at least one trajectory in a color space; —defining a transformation which primarily increases perceptual linearity of consecutive points belonging to the at least one trajectory; —applying the transformation to the image. This has the advantage that the perceptual linearity can be restricted to the trajectory.
    Type: Grant
    Filed: July 10, 2015
    Date of Patent: February 19, 2019
    Assignee: BARCO NV
    Inventor: Tom Kimpe
  • Patent number: 10210600
    Abstract: A method of removing noise from image data output from an image sensor includes comparing a target block in the image data with each of at least one comparison blocks around the target block in the image data. A center pixel similarity between center pixels of the target block and each comparison block is calculated. A neighboring pixel similarity between neighboring pixels neighboring the center pixels in the target block and each comparison block is calculated. The method includes determining whether an impulsive noise exists in the center pixel of the target block based on the center pixel similarity and the neighboring pixel similarity. A weight applied to a value of the center pixel of each comparison block is adjusted based on a result of the determining. Weighted averaging is performed on values of the center pixels of the comparison blocks to estimate a value of the center pixel of the target block.
    Type: Grant
    Filed: February 17, 2017
    Date of Patent: February 19, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventor: Byung-Joon Baek
  • Patent number: 10198612
    Abstract: A method includes: normalizing intensities at each pixel in a fingerprint slap scan image such that variations of pixel intensities between fingerprint ridges and valleys are regularized; subsequently dividing the fingerprint slap scan image into blocks of pixels; for each block of pixels, estimating a spatial separation between adjacent fingerprint ridges as well as a ridge orientation for each fingerprint ridge within the particular block of pixels; calculating a distortion map for the various blocks by projecting, according to the estimated ridge orientation for each fingerprint ridge, an adjustment to the estimated spatial separation that is based on a difference between the estimated spatial separation and a target spatial separation; and warping the fingerprint slap scan image to compensate for the calculated distortion map such that the fingerprint ridges in the warped fingerprint slap scan image are scaled to compensate for local variations of adjustments in the calculated distortion map.
    Type: Grant
    Filed: July 29, 2016
    Date of Patent: February 5, 2019
    Assignee: MorphoTrust USA, LLC
    Inventor: Rein-Lien Hsu
  • Patent number: 10185883
    Abstract: The present invention relates to a mobile terminal capable of a new type of user input, comprising: a backside input unit including a plurality of buttons and exposed to the backside of the mobile terminal; a memory for storing relationships between combinations of the plurality of buttons and control instructions of the mobile terminal and biometric information; a sensor unit, arranged on the backside of the mobile terminal and adjacent to the backside input unit, for sensing a user's bio signal; and a control unit for, upon receiving a user input in accordance with a particular combination of the plurality of buttons, controlling the sensor unit to sense the user's bio signal, and authenticating the user using the sensed bio signal and the stored biometric information.
    Type: Grant
    Filed: January 9, 2015
    Date of Patent: January 22, 2019
    Assignee: LG ELECTRONICS INC.
    Inventors: Junhak Lee, Yonghan Lee, Byeongkil Ahn, Donghyeon Kim, Hyungchul Won
  • Patent number: 10163010
    Abstract: Systems and methods for eye pose identification using features of an eye are described. Embodiments of the systems and methods can include segmenting an iris of an eye in the eye image to obtain pupillary and limbic boundaries of the eye, determining two angular coordinates (e.g., pitch and yaw) of an eye pose using the pupillary and limbic boundaries of the eye, identifying an eye feature of the eye (e.g., an iris feature or a scleral feature), determining a third angular coordinate (e.g., roll) of the eye pose using the identified eye feature, and utilizing the eye pose measurement for display of an image or a biometric application. In some implementations, iris segmentation may not be performed, and the two angular coordinates are determined from eye features.
    Type: Grant
    Filed: October 12, 2016
    Date of Patent: December 25, 2018
    Assignee: Magic Leap, Inc.
    Inventors: Adrian Kaehler, Michael Anthony Klug, Gholamreza Amayeh
  • Patent number: 10140516
    Abstract: Managing a plurality of images may include generating, using a processor, clusters of images from a plurality of images having locations and timestamps. The clusters may represent events and may be generated according to a distance metric based upon geographic distance and time difference between consecutive pairs of the plurality of images sorted according to time. Selected clusters may be merged, using the processor, into a merged cluster representing a trip based upon geographic distance between the clusters and unique dates within the clusters. The plurality of images may be displayed, using the processor, organized according to the trip.
    Type: Grant
    Filed: December 16, 2015
    Date of Patent: November 27, 2018
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Jinghai Rao, Wu Guan, Syyean Gastelum
  • Patent number: 10140692
    Abstract: A method of rectifying an image representing a surface of a tire is provided. According to the method, a circumferential marking present on a tire is detected in an image of the tire. Based on the marking, and for each line of a plurality of lines of the image, a reference position on the tire is determined. For each of the lines of the image, a difference between the reference position on the line under analysis and a minimum value of the reference positions for all of the lines of the image is determined. For each of the lines of the image, pixels of the line under analysis are radially offset by a value of the difference.
    Type: Grant
    Filed: June 12, 2015
    Date of Patent: November 27, 2018
    Assignee: COMPAGNIE GENERALE DES ETABLISSEMENTS MICHELIN
    Inventors: Alexandre Joly, Jean-Paul Zanella
  • Patent number: 10096121
    Abstract: A human-shape image segmentation method comprising: extracting multi-scale context information for all first pixel points for training a human-shape image; sending image blocks of all scales of all the first pixel points into a same convolution neural network to form a multi-channel convolutional neural network group, wherein each channel corresponds to image blocks of one scale; training the neural network group using a back propagation algorithm to obtain human-shape image segmentation training model data; extracting multi-scale context information for all second pixels points for testing the human-shape image; sending image blocks of different scales of each of the second pixel points into a neural network channel corresponding to the human-shape image segmentation training model, wherein if said first probability is larger than said second probability, the second pixel points belong to the human-shape region, otherwise, the second pixel points are outside of the human-shape region.
    Type: Grant
    Filed: May 23, 2014
    Date of Patent: October 9, 2018
    Assignee: Watrix Technology
    Inventors: Tieniu Tan, Yongzhen Huang, Liang Wang, Zifeng Wu
  • Patent number: 10095952
    Abstract: The invention provides a method and device for acquiring clothing image attribute points, which can increase an efficiency of acquiring the clothing image attribute points. The method comprises: saving five attribute points manually calibrated and determining first to eleventh points in sequence by taking a horizontal direction as a horizontal coordinate and a vertical direction as a vertical coordinate, for a first side of two bilaterally symmetric sides of the clothing image. By means of a technical solution of an embodiment of the present invention, for the clothing image, five points are manually calibrated first; and then the other eleven attribute points can be determined by a computer, so that a manual workload is reduced, and the efficiency of acquiring the clothing image attribute points is increased.
    Type: Grant
    Filed: June 11, 2015
    Date of Patent: October 9, 2018
    Assignees: BEIJING JINGDONG SHANGKE INFORMATION TECHNOLOGY CO., LTD., BEIJING JINGDONG CENTURY TRADING CO., LTD.
    Inventor: Gang Zhao