Patents Examined by Vikkram Bali
-
Patent number: 11321952Abstract: A computer-implemented method of alerting a driver of a vehicle is provided. The computer-implemented method includes obtaining a plurality of consecutive input images during a time interval using a three-dimensional depth camera, a respective one of the plurality of consecutive input images comprising a user sub-image and an object sub-image; deriving three-dimensional coordinates of user feature points in the user sub-image of the respective one of the plurality of consecutive input images using a first classifier; deriving three-dimensional coordinates of object feature points in the object sub-image of the respective one of the plurality of consecutive input images using the first classifier; and classifying user posture in the respective one of the plurality of consecutive input images by analyzing the three-dimensional coordinates of user feature points and the three-dimensional coordinates of object feature points using a second classifier.Type: GrantFiled: April 24, 2019Date of Patent: May 3, 2022Assignee: BOE Technology Group Co., Ltd.Inventor: Jibo Zhao
-
Enhanced imaging devices, and image construction methods and processes employing hermetic transforms
Patent number: 11304661Abstract: In an exemplary embodiment, a tomography device comprises a scanner that obtains image slices. The device additionally comprises at least one processor configured to: perform a Hermetic Transform on the image slices to obtain hermetically transformed data using; filter and perform an Inverse Hermetic Transform on the Hermetic Transform data to obtain filtered inverse Hermetic Transform data; and perform back projection and angle integration on the filtered inverse Hermetic Transform data.Type: GrantFiled: October 23, 2015Date of Patent: April 19, 2022Assignee: VERTOCOMM, INC.Inventors: Harvey C. Woodsum, Christopher M. Woodsum -
Patent number: 11308361Abstract: An example system includes a processor and a memory. The system performs sub-pixel convolution that is free of checkerboard artifacts. In one example implementation, the system may execute a method that includes initializing one or more parameters of a sub-kernel of a kernel and copying the one or more parameters of the sub-kernel to other sub-kernels of the kernel. The method may further include performing convolution of an input image with the sub-kernels of the kernel and generating a plurality of first output images. A second output image is then generated based on the plurality of first output images.Type: GrantFiled: July 5, 2018Date of Patent: April 19, 2022Assignee: Twitter, Inc.Inventors: Andrew Aitken, Christian Ledig, Lucas Theis, Jose Caballero, Zehan Wang, Wenzhe Shi
-
Patent number: 11301728Abstract: A method of processing image data representative of at least part of an image using a computing system to detect at least one class of object in the image. The method comprises processing the image data using a neural network system selected from a plurality of neural network systems including a first neural network system arranged to detect a class of objects, and a second neural network system arranged to detect the class of objects. The first neural network system comprises a first plurality of layers and the second neural network system comprises a second plurality of layers. The second neural network system has at least one of: more layers than the first neural network system; more neurons than the first neural network system; and more interconnections between neurons than the first neural network system. The method comprises obtaining a trigger and, on the basis of the trigger, processing the image data using a selected one of the first and second neural network systems.Type: GrantFiled: June 18, 2018Date of Patent: April 12, 2022Assignee: Apical Ltd.Inventor: Daren Croxford
-
Patent number: 11295438Abstract: Mixed-mode includes receiving inspection results including one or more images of a selected region of the wafer, the one or more images include one or more wafer die including a set of repeating blocks, the set of repeating blocks a set of repeating cells. In addition, mixed-mode inspection includes adjusting a pixel size of the one or more images to map each cell, block and die to an integer number of pixels. Further, mixed-mode inspection includes comparing a first wafer die to a second wafer die to identify an occurrence of one or more defects in the first or second wafer die, comparing a first block to a second block to identify an occurrence of one or more defects in the first or second blocks and comparing a first cell to a second cell to identify an occurrence of one or more defects in the first or second cells.Type: GrantFiled: November 30, 2018Date of Patent: April 5, 2022Assignee: KLA CorporationInventors: Jason Z. Lin, Allen Park, Ellis Chang, Richard Wallingford, Songnian Rong, Chetana Bhaskar
-
Patent number: 11295169Abstract: Provided is a method, device, and program for sampling a frame image of an object to be learned in a video for artificial intelligence video learning, and an image learning method thereof. The method includes receiving a raw video for the AI image learning, extracting a predetermined number of frame images from the received raw, detecting learning target objects in each of the frame images, removing a background other than the learning target objects from each of the frame images, measuring a movement amount of each of the detected learning target objects in a n-th frame image, from which the background is removed, and selecting the n-th frame image as the learning target frame image, by comparing a result of measuring the movement amount of each of the detected one or more learning target objects in the n-th frame image with a predetermined reference.Type: GrantFiled: March 25, 2021Date of Patent: April 5, 2022Assignee: CROWDWORKS INC.Inventor: Min Woo Park
-
Patent number: 11295437Abstract: Disclosed are computer-implemented methods, non-transitory computer-readable media, and systems for authentication. One computer-implemented method includes obtaining a first image, where the first image is an image of an identification (ID) document captured when the ID document is tilted at a first angle relative to a projected light source. A second image is obtained, where the second image is an image of the ID document captured when the ID document is tilted at a second angle relative to the projected light source. The ID document is authenticated based on identification of a first illuminated region and a second illuminated region, where the first illuminated region is associated with the first image and the second illuminated region is associated with the second image, and a comparison between a first position of the first illuminated region and a second position of the second illuminated region.Type: GrantFiled: June 23, 2021Date of Patent: April 5, 2022Assignee: ALIPAY LABS (SINGAPORE) PTE. Ltd.Inventors: Yan Xu, Jiangbo Huang
-
Patent number: 11257229Abstract: A method of processing an image is disclosed. The method comprises decomposing the image into a plurality of channels, each being characterized by a different depth-of-field, and accessing a computer readable medium storing an in-focus dictionary defined over a plurality of dictionary atoms, and an out-of-focus dictionary defined over a plurality of sets of dictionary atoms, each set corresponding to a different out-of-focus condition. The method also comprises computing one or more sparse representations of the decomposed image over the dictionaries.Type: GrantFiled: December 3, 2019Date of Patent: February 22, 2022Assignee: Ramot at Tel-Aviv University Ltd.Inventors: Harel Haim, Emanuel Marom, Alexander Bronstein
-
Patent number: 11258953Abstract: According to one embodiment, the image processing device includes imagers disposed on an outer circumference of a mobile object for imaging surroundings of the mobile object to generate multiple images including mutually overlapping regions, and a processor that corrects the images on the basis of one color-value mean value and another color-value mean value to generate a peripheral image by combining the corrected images. The one color-value mean value is an average of color values of a target region set in an overlapping region of one of the images. Another color-value mean value is an average of color values of a target region set in an overlapping region of another one of the images.Type: GrantFiled: May 30, 2018Date of Patent: February 22, 2022Assignee: AISIN SEIKI KABUSHIKI KAISHAInventors: Kota Ito, Haruyuki Horie, Miki Tsujino
-
Patent number: 11234798Abstract: Provided are a system, method, and computer readable storage medium for generating an intra-oral scan of a dentition. A contiguous scan of an occlusal surface of at least a part of one arch of the dentition is generated. At least one additional surface is associated to the contiguous scan of the occlusal surface.Type: GrantFiled: October 15, 2018Date of Patent: February 1, 2022Assignee: ORMCO CORPORATIONInventors: Robert F. Dillon, Craig A. Andreiko, Andrew F. Vesper, Neil H. K. Judell, Timothy I. Fillion
-
Patent number: 11235175Abstract: A method and apparatus to automatically control the timing of an image acquisition by an imaging system in developing a correlation model of movement of a target within a patient.Type: GrantFiled: January 8, 2016Date of Patent: February 1, 2022Assignee: Accuray IncorporatedInventors: Shutian Li, Ye Sheng, Sohail Sayed
-
Patent number: 11232577Abstract: There is provided a method for registration of intravital anatomical imaging modality image data and nuclear medicine image data of a patient's heart comprising: obtaining anatomical image data including a heart of a patient outputted by an anatomical intravital imaging modality; obtaining at least one nuclear medicine image data outputted by a nuclear medicine imaging modality, the nuclear medicine image data including the heart of the patient; identifying a segmentation of a network of vessels of the heart in the anatomical image data; identifying a contour of at least part of the heart in the nuclear medicine image data, the contour including at least one muscle wall border of the heart; correlating between the segmentation and the contour; registering the correlated segmentation and the correlated contour to form a registered image of the anatomical image data and the nuclear medicine image data; and providing the registered image for display.Type: GrantFiled: January 26, 2016Date of Patent: January 25, 2022Assignee: Speetrum Dynamics Medical LimitedInventors: Yoel Zilberstien, Nathaniel Roth
-
Patent number: 11213374Abstract: Method for realistic visualization of a virtual dental model in a first image of a face comprising at least an inner mouth region of the face, the inner mouth region comprising teeth (31) and a mouth cavity background, the method comprising using an inpainting algorithm to compute, based on background pixels corresponding to the mouth cavity background (35), plausible background pixels for at least a part of tooth pixels of the first image, the tooth pixels corresponding to the teeth, and to replace at least a part of the tooth pixels by plausible background pixels, at least partially removing the teeth (31) from the first image; and visualizing the first image with the at least partially removed teeth (31?), wherein the first image is overlaid with a representation (21) of the dental model.Type: GrantFiled: February 19, 2019Date of Patent: January 4, 2022Assignee: Ivoclar Vivadent AGInventors: Marcel Lancelle, Roland Mörzinger, Nicolas Degen, Gabor Sörös, Bartolovic Nemanja
-
Patent number: 11210794Abstract: A method, apparatus, system for tracking an object, the method. A region of interest in an image pair is determined based on a bounding box determined for the object in the image pair. A mask based on the region of interest is applied to the image pair. The mask masks out portions of the image pair outside of the region of interest to form masked images. Intensity averaging is performed on the masked images to detect a set of pixels having a greatest intensity in the masked images. The set of pixels in the masked images is a set of common pixels in the masked images in which the set of common pixels is assumed to have a same location in both of the masked images. A three-dimensional position of the object is determined using the set of common pixels.Type: GrantFiled: March 20, 2020Date of Patent: December 28, 2021Assignee: Aurora Flight Sciences Corporation, a subsidiary of The Boeing CompanyInventors: Igor Janjic, Douglas Famularo
-
Patent number: 11200653Abstract: A method includes obtaining, using at least one sensor of an electronic device, multiple image frames of a scene. The multiple image frames include a first image frame and a second image frame captured using different exposures. The method also includes excluding, using at least one processor of the electronic device, pixels in the first and second image frames based on a coarse motion map. The method further includes generating, using the at least one processor, multiple local histogram match maps based on different portions of the first and second image frames. In addition, the method includes generating, using the at least one processor, an image of the scene using the local histogram match maps.Type: GrantFiled: December 9, 2019Date of Patent: December 14, 2021Assignee: Samsung Electronics Co., Ltd.Inventors: Zhen Tong, John W. Glotzbach, Ruiwen Zhen, Hamid R. Sheikh
-
Patent number: 11191342Abstract: In some embodiments of the present disclosure, one or more machine learning models are trained to accurately estimate skin color in one or more images regardless of the lighting conditions. In some embodiments, the models can then be used to estimate a skin color in a new image, and that estimated skin color can be used for a variety of purposes. For example, the skin color may be used to generate a recommendation for a foundation shade that accurately matches the skin color, or a recommendation for another cosmetic product that is complimentary with the estimated skin color. Thus, the need for an in-person test of the product is eliminated.Type: GrantFiled: July 18, 2019Date of Patent: December 7, 2021Assignee: L'OrealInventors: Christine Elfakhri, Florent Valceschini, Loic Tran, Matthieu Perrot, Robin Kips, Emmanuel Malherbe
-
Patent number: 11195064Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining an alignment between cross-modal sensor data. In one aspect, a method comprises: obtaining (i) an image that characterizes a visual appearance of an environment, and (ii) a point cloud comprising a collection of data points that characterizes a three-dimensional geometry of the environment; processing each of a plurality of regions of the image using a visual embedding neural network to generate a respective embedding of each of the image regions; processing each of a plurality of regions of the point cloud using a shape embedding neural network to generate a respective embedding of each of the point cloud regions; and identifying a plurality of region pairs using the embeddings of the image regions and the embeddings of the point cloud regions.Type: GrantFiled: July 11, 2019Date of Patent: December 7, 2021Assignee: Waymo LLCInventors: Colin Andrew Braley, Volodymyr Ivanchenko, Yu Zhang
-
Patent number: 11182591Abstract: Methods and apparatuses for detecting a face, and electronic devices include: performing face location on a face image to be detected; performing face attribute detection on the face image based on a face location result; and displaying a face attribute detection result of the face image to be detected. Use experience of face image detection can be improved while diversified requirements of a user for obtaining corresponding face information in a face image from different angles are satisfied.Type: GrantFiled: May 28, 2019Date of Patent: November 23, 2021Assignee: SHENZHEN SENSETIME TECHNOLOGY CO, LTDInventors: Xiao Jin, Chenchen Hu, Zhanghui Kuang, Wei Zhang
-
Patent number: 11184507Abstract: System and techniques for adaptive color transformation to aid computer vision are described herein. Colors from an image are mapped into a multi-dimensional space to create a distribution of colors in the image. A line can be fit to the distribution. Here, the line includes an angle relative to a coordinate system of the multi-dimensional space. A transformation to colors can then be applied to the image based on the angle of the line. The transformation producing a reduced image where a color complexity of the original image is reduced.Type: GrantFiled: July 11, 2019Date of Patent: November 23, 2021Assignee: Raven Industries, Inc.Inventors: Yuri Sneyders, John D. Preheim, Jeffrey Allen Van Roekel
-
Patent number: 11176419Abstract: A method for labeling image comprises: obtaining a target image of a target object; generating a reconstruction image according to the target image and a reconstruction model, wherein the reconstruction model is trained with a plurality of reference images and a machine learning algorithm, each of the reference images is an image of a reference object whose defect level is in a tolerable range with an upper limit, and each of the reference objects is associated with the target object; generating a first difference image and a second difference image respectively by performing a first difference algorithm and a second difference algorithm respectively according to the target image and the reconstruction image; and generating an output image by performing a pixel-scale operation according to the first difference image and the second difference image, wherein the output image includes a label indicating a defect of the target object.Type: GrantFiled: June 18, 2020Date of Patent: November 16, 2021Assignees: INVENTEC (PUDONG) TECHNOLOGY CORPORATION, INVENTEC CORPORATIONInventors: Yi-Chun Chen, Trista Pei-Chun Chen, Daniel Stanley Young Tan, Wei-Chao Chen