Patents Examined by Phuoc Tran
  • Patent number: 10885648
    Abstract: A method of reconstructing a three dimensional image using a structured light pattern system is provided as follows. A class identifier of an observed pixel on a captured image by a camera is extracted. The observed pixel has a coordinate (x, y) on the captured image. A first relative position of the x coordinate of the observed pixel in a tile domain of the captured image is calculated. A second relative position of one of a plurality of dots in a tile domain of a reference image using the extracted class identifier is calculated. A disparity of the observed pixel using the first relative position and the second relative position is calculated.
    Type: Grant
    Filed: November 9, 2018
    Date of Patent: January 5, 2021
    Inventors: Lilong Shi, Yibing Michelle Wang
  • Patent number: 10867169
    Abstract: Aspects of the disclosure provide for mechanisms for character recognition using neural networks. A method of the disclosure includes assigning, using a first-level classifier of a grapheme classifier, an input grapheme image to a first grapheme cluster of a plurality of grapheme clusters, wherein the first grapheme cluster comprises a first plurality of graphemes; selecting, by a processing device, a classifier from a plurality of second-level classifiers of the grapheme classifier based on the first grapheme cluster, wherein the selected classifier is trained to recognize the first plurality of graphemes; and processing the input grapheme image using the selected classifier to recognize at least one character in the input grapheme image.
    Type: Grant
    Filed: June 22, 2018
    Date of Patent: December 15, 2020
    Assignee: ABBYY Production LLC
    Inventor: Aleksey Alekseevich Zhuravlev
  • Patent number: 10861135
    Abstract: An image processing apparatus including a pixel shifting super-resolution image generation circuit configured to generate a high-resolution composite image from a plurality of images, an evaluation area setting circuit configured to set a plurality of evaluation areas within an area extraction range of the composite image, a synthesis accuracy evaluation circuit configured to evaluate, for each of the plurality of evaluation areas, a pixel filling rate for the evaluation area and calculate a plurality of pixel filling rate evaluation values, and a determination circuit configured to determine a determination area from among the plurality of evaluation areas based on the plurality of pixel filling rate evaluation values.
    Type: Grant
    Filed: March 27, 2019
    Date of Patent: December 8, 2020
    Assignee: Olympus Corporation
    Inventor: Tetsushi Tanimoto
  • Patent number: 10853642
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining the identity of a user. In one aspect, a method comprises: obtaining a multi-spectral image that depicts an eye of a user, wherein the multi-spectral image comprises a plurality of registered two-dimensional channels, and each two-dimensional channel corresponds to a different spectrum of the multi-spectral image; processing the multi-spectral image using an encoder neural network to generate a fused image, wherein the fused image has a single two-dimensional channel; determining a set of features characterizing the eye of the user from the fused image; and determining an identity of the user based at least in part on the set of features characterizing the eye of the user.
    Type: Grant
    Filed: March 22, 2019
    Date of Patent: December 1, 2020
    Assignee: Advanced New Technologies Co., Ltd.
    Inventor: Vikas Gottemukkula
  • Patent number: 10846888
    Abstract: In one embodiment, a method for generating completed frames from sparse data may access sample datasets associated with a sequence of frames, respectively. Each sample dataset may comprise incomplete pixel information of the associated frame. The system may generate, using a first machine-learning model, the sequence of frames, each having complete pixel information, based on the sample datasets. The first machine-learning model is configured to retain spatio-temporal representations associated with the generated frames. The system may then access a next sample dataset comprising incomplete pixel information of a next frame after the sequence of frames. The system may generate, using the first machine-learning model, the next frame based on the next sample dataset.
    Type: Grant
    Filed: November 15, 2018
    Date of Patent: November 24, 2020
    Assignee: Facebook Technologies, LLC
    Inventors: Anton S. Kaplanyan, Anton Sochenov, Thomas Sebastian Leimkuhler, Warren Andrew Hunt
  • Patent number: 10839531
    Abstract: An electronic device for object tracking based on a user-specified initialization point is provided. The electronic device stores a sequence of image frames, which includes a first image frame and a second image frame. The electronic device estimates a set of feature correspondences between a first set of features points in the first image frame and a second set of feature points in the second image frame. The electronic device generates different first motion-estimate models for different groups of feature correspondences of the set of feature correspondences and further estimates, from different groups of feature correspondences, a plurality of inlier feature correspondences that correspond to the object of interest in the first image frame and the second image frame. The electronic device generates a second motion-estimate model as an optimal motion-estimate model and tracks the object of interest in the sequence of frames, based on the second motion-estimate model.
    Type: Grant
    Filed: November 15, 2018
    Date of Patent: November 17, 2020
    Assignee: SONY CORPORATION
    Inventor: Houman Rastgar
  • Patent number: 10832036
    Abstract: Methods and systems are provided for generating a facial recognition system. A facial recognition system can be implemented using a meta-model based on a trained neural network. A neural network can be trained as multiple classifiers that identify individuals using a small number of images of the individual's face. A meta-model can learn from the neural networks to be capable to identify an individual based on a small number of images. In this way, the facial recognition system uses the meta-model that learns from the neural network trained to identify an individual based on a small number of images. Such a facial recognition system is tested to determine any misidentification for fine-tuning the system. A facial recognition system implemented using such a meta-model is capable of adapting the model to learn identities entered into the system using only a small number of images to enroll an identity into the system.
    Type: Grant
    Filed: July 16, 2018
    Date of Patent: November 10, 2020
    Assignee: ADOBE INC.
    Inventors: Haoxiang Li, Zhe Lin, Muhammad Abdullah Jamal
  • Patent number: 10821871
    Abstract: A method for transferring a container for holding one or more articles is provided. The method includes transferring the container using a transferring mechanism to a position which is adjacent to a destination space. The method further includes recording an image of the destination space before the container is deposited to the destination space. The method also includes performing an image analysis of the image and determining if the container is able to be sent to the destination space according to a result of the image analysis of the image.
    Type: Grant
    Filed: January 17, 2018
    Date of Patent: November 3, 2020
    Assignee: TAIWAN SEMICONDUCTOR MANUFACTURING CO., LTD.
    Inventors: Yi-Tang Huang, Yuan-Yu Feng, Chia-Han Lin, Chien-Fa Lee
  • Patent number: 10824899
    Abstract: Representative embodiments disclose mechanisms to create a text stream from raw OCR outputs. The raw OCR output comprises a plurality of bounding boxes, each bounding box defining a region containing text which has been recognized by the OCR system. A weight matrix is calculated that comprises a weight for each pair of bounding boxes. The weight representing the probability that a pair of bounding boxes belongs to the same cluster. The bounding boxes are then clustered along the weights. The resulting clusters are first ordered using an ordering criteria. The bounding boxes within each cluster are then ordered according to a second ordering criteria. The ordered clusters and bounding boxes are then arranged into a text stream.
    Type: Grant
    Filed: December 27, 2018
    Date of Patent: November 3, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Yan Wang, Arun Sacheti, Vishal Chhabilbhai Thakkar, Surendra Srinivas Ulabala, Shloak Jain
  • Patent number: 10824854
    Abstract: Embodiments of the present disclosure pertain to systems and method for extracting data from an image. In one embodiment, a method of extracting data from an image comprises receiving, from an optical character recognition (OCR) system, OCR text in response to sending an image to the OCR system. The OCR text comprises a plurality of lines of text. Each line of text is classified as either a line item or not a line item using a machine learning algorithm, and a plurality of data fields are extracted from each line of text classified as a line item.
    Type: Grant
    Filed: June 18, 2018
    Date of Patent: November 3, 2020
    Assignee: SAP SE
    Inventors: Everaldo Aguiar, Ravi Sharma, Shivani Patel, Jesper Lind, Michael Stark, Yongjian Bi
  • Patent number: 10810722
    Abstract: Forensic method for identifying forged documents. For each of a stream of incoming jpeg images, using a processor configured for determining whether jpeg image/s is a replacement forgery by determining whether a first portion of individual image which resides at a known location (known likely to be replaced by forger) within the individual jpeg image has been replaced, including: indicator, face-djpg, for the first portion at known location; computing indicator, aka nonface-djpg, for a second portion of individual image which resides at a comparison location within the jpeg image known as unlikely to be replaced by a forger; and determining whether face-djpg and nonface-djpg fulfill predetermined logical criterion and deciding whether the individual jpeg image is a replacement forgery accordingly.
    Type: Grant
    Filed: July 16, 2018
    Date of Patent: October 20, 2020
    Assignee: AU10TIX LIMITED
    Inventors: Ron Atzmon, Sergey Markin, Yael Moscovitz, Vadim Vereschagin
  • Patent number: 10810699
    Abstract: Working efficiency in position matching of multiple point cloud data displayed on a display is improved. A point cloud data processing device includes a highlight controlling part. In a condition in which a first point cloud containing multiple markers for position matching and a second point cloud containing multiple markers for position matching are displayed on a display, when a marker of one of the first point cloud and the second point cloud is specified, the highlight controlling part highlights a corresponding marker of the other point cloud.
    Type: Grant
    Filed: February 27, 2018
    Date of Patent: October 20, 2020
    Assignee: TOPCON CORPORATION
    Inventors: Takahiro Komeichi, Naoki Morikawa
  • Patent number: 10796428
    Abstract: Disclosed are an inspection system and an inspection method of performing image processing on an outline of an inspection object according to whether the inspection object is good or defective, and overlapping and displaying the image-processed outline with reference information for determining whether the inspection object is good or defective. The inspection system includes: a data acquisition unit configured acquire an image of an inspection object by irradiate light on the inspection object; a processing unit configured to detect an outline of the inspection object based on the image data of the inspection object; and an output unit configured to overlap and display the outline with reference information, wherein the processing unit is configured to determine whether the outline is good or defective based on the reference information to perform image processing on the outline according to whether the outline is good or defective.
    Type: Grant
    Filed: August 8, 2019
    Date of Patent: October 6, 2020
    Assignee: KOH YOUNG TECHNOLOGY INC.
    Inventors: Seung Ae Seo, Won Mi Ahn, Hye In Lee, Jong Hui Lee
  • Patent number: 10795453
    Abstract: Systems and methods for testing or correcting optical pointing systems are disclosed. An optical pointing system may include an imaging sensor including a field-of-view (FOV) carried by the optical pointing system, at least one collecting device for collecting optical photons and directing the optical photons to the imaging sensor, at least one directing device for directing the at least one collecting device to different pointing vectors, and at least one non-transitory computer-readable storage medium carried by the optical pointing system having instructions encoded thereon that when executed by at least one processor operates to test the optical pointing system by, inter alia, determining a pointing error based, at least in part, on a macro image of a targeted object.
    Type: Grant
    Filed: July 27, 2018
    Date of Patent: October 6, 2020
    Assignee: BAE Systems Information and Electronic Systems Integration Inc.
    Inventor: Michael J. Powers
  • Patent number: 10785903
    Abstract: Described is a system for determining crop residue fraction. The system includes a color video camera mounted on a mobile platform for generating a two-dimensional (2D) color video image of a scene in front or behind the mobile platform. In operation, the system separates the 2D color video image into three separate one-dimensional (1D) mixture signals for red, green, and blue channels. The three 1D mixture signals are then separated into pure 1D component signals using blind source separation. The 1D component signals are thresholded and converted to 2D binary, pixel-level abundance maps, which can then be integrated to allow the system to determine a total component fractional abundance of crop in the scene. Finally, the system can control a mobile platform, such as a harvesting machine, based on the total component fractional abundance of crop in the scene.
    Type: Grant
    Filed: March 11, 2019
    Date of Patent: September 29, 2020
    Assignee: HRL Laboratories, LLC
    Inventor: Yuri Owechko
  • Patent number: 10783383
    Abstract: A detection of a boundary in an environment. For this purpose, information of an occupancy grid is used, wherein the occupancy grid provides information about the probability of occupancy in the environment. Upon detecting a starting transition point between a free and an occupied grid cell in the occupancy grid, a region of interest window surrounding the starting transition point is analyzed to identify further transition points. The identified transition points are combined to one or more polygon chain. After the analysis of the boundary is performed within the region of interest, successive regions of interest may be analyzed. For this purpose, the successive regions of interest are determined based on the transition points and/or the boundary information of a current region of interest window.
    Type: Grant
    Filed: January 4, 2019
    Date of Patent: September 22, 2020
    Assignee: CONTINENTAL AUTOMOTIVE GMBH
    Inventors: Pothuraju Chavali, Naveen Onkarappa, Gerrit Wischer
  • Patent number: 10762617
    Abstract: The present disclosure relates to a process and a system for assessing the performance of cleaning operations by utilizing an automatic read out routine for test strips subjected to a cleaning operation. Furthermore, the present disclosure relates to a computer program product capable of performing the process.
    Type: Grant
    Filed: October 1, 2018
    Date of Patent: September 1, 2020
    Assignee: Ecolab USA Inc.
    Inventors: Jan Sanders, Fernanda Furtado de Melo Albino, Sabine Swoboda, Sebastian Niebur, Nadine Göhring, Ann Mangskau, Carola Stingl, Daniel D. Anderson, Florian M. Witt, Christian Lührs, Andreas Krohn, Marc Delling
  • Patent number: 10753851
    Abstract: Among other things, an imaging sensor includes a two-dimensional array of photosensitive elements and a surface to receive a sample within a near-field distance of the photosensitive elements. Electronics classify microbeads in the sample as belonging to different classes based on the effects of different absorption spectra of the different classes of microbeads on light received at the surface. In some examples, the number of different distinguishable classes of microbeads can be very large based on combinations of the effects on light received at the surface of the different absorption spectra together, spatial arrangements of colorants in the microbeads that impart the different absorption spectra, different sizes of microbeads, and different shapes of microbeads, among other things.
    Type: Grant
    Filed: November 20, 2018
    Date of Patent: August 25, 2020
    Assignee: Alentic Microscience Inc.
    Inventor: Alan Marc Fine
  • Patent number: 10748264
    Abstract: The present technique relates to an image processing apparatus and an image processing method capable of obtaining an obstacle-removed image in which an obstacle does not appear using disparity information. A removal section generates after-removal photographic images at a plurality of viewpoints by removing part of subjects from respective photographic images at the plurality of viewpoints using disparity information associated with the photographic images at the plurality of viewpoints. An image generation section generates an obstacle-removed image at a predetermined viewpoint by registering the after-removal photographic images at the plurality of viewpoints using the disparity information. The present technique is applicable to a case, for example, of generating an obstacle-removed image in which an obstacle does not appear using photographic images at a plurality of viewpoints.
    Type: Grant
    Filed: August 26, 2016
    Date of Patent: August 18, 2020
    Assignee: SONY CORPORATION
    Inventors: Katsuhisa Ito, Makibi Nakamura, Kengo Hayasaka
  • Patent number: 10748262
    Abstract: Apparatus for binning an input value into one of a plurality of bins which collectively represent a histogram of input values, each of the plurality of bins representing a corresponding range of input values, the apparatus comprising: an input for receiving an input value; a noise source configured to generate an error value according to a predetermined noise distribution; and a binning controller configured to mix the received input value with the error value so as to generate a modified input value and to allocate the modified input value to the bin corresponding to that modified input value.
    Type: Grant
    Filed: June 21, 2017
    Date of Patent: August 18, 2020
    Assignee: Imagination Technologies Limited
    Inventor: Tim Lee