Image Transformation Or Preprocessing Patents (Class 382/276)
  • Patent number: 11593858
    Abstract: Systems and techniques for a design-aware image search are described. The design-aware image search techniques described herein capture a design on an item to determine additional items with similar or matching designs. An image of the item is used to create an edge image of a design, and shape descriptors are generated describing features of the edge image. These shape descriptors are compared to shape descriptors associated with other images to locate images that have similar or matching designs as compared with the input image. The design-aware image search system may uses these relationships to generate a search result with images or products having a design similar to the design on the input image.
    Type: Grant
    Filed: January 29, 2020
    Date of Patent: February 28, 2023
    Assignee: Adobe Inc.
    Inventors: Rishu Aggarwal, Sunil Rawat, Ajay Bedi
  • Patent number: 11592547
    Abstract: Techniques and apparatuses are described that implement a smart-device-based radar system capable of detecting user gestures in the presence of saturation. In particular, a radar system 104 employs machine learning to compensate for distortions resulting from saturation. This enables gesture recognition to be performed while the radar system 104's receiver 304 is saturated. As such, the radar system 104 can forgo integrating an automatic gain control circuit to prevent the receiver 304 from becoming saturated. Furthermore, the radar system 104 can operate with higher gains to increasing sensitivity without adding additional antennas. By using machine learning, the radar system 104's dynamic range increases, which enables the radar system 104 to detect a variety of different types of gestures having small or large radar cross sections, and performed at various distances from the radar system 104.
    Type: Grant
    Filed: February 28, 2019
    Date of Patent: February 28, 2023
    Assignee: Google LLC
    Inventors: Changzhan Gu, Jaime Lien, Nicholas Edward Gillian, Jian Wang
  • Patent number: 11557053
    Abstract: Techniques for image processing and transformation are provided. A plurality of images and a plurality of maps are received, and a system of neural networks is trained based on the plurality of images and the plurality of maps. A first image is received, and a first map is generated by processing the first image using the system of neural networks.
    Type: Grant
    Filed: February 7, 2020
    Date of Patent: January 17, 2023
    Assignee: International Business Machines Corporation
    Inventors: Rui Zhang, Conrad M. Albrecht, Siyuan Lu, Wei Zhang, Ulrich Alfons Finkler, David S. Kung, Xiaodong Cui, Marcus Freitag
  • Patent number: 11526966
    Abstract: An image processing device includes a processor; and a memory to store the program which performs processing including: measuring a first texture amount indicating luminance variation in image regions, based on the image regions obtained by dividing the captured image and previously determining an image processing target region based on the first texture amount; judging whether the image processing on a current captured image is necessary based on luminance of the image processing target region in the current captured image; calculating a second texture amount indicating luminance variation in the image processing target region, and judging whether the image processing should be performed on the image processing target region or not based on the second texture amount; and performing the image processing on the image processing target region on which the judging based on the second texture amount is that the image processing should be performed.
    Type: Grant
    Filed: September 28, 2020
    Date of Patent: December 13, 2022
    Assignee: MITSUBISHI ELECTRIC CORPORATION
    Inventors: Ichiro Furuki, Kohei Okahara, Tsukasa Fukasawa, Nobuo Matsumura
  • Patent number: 11508031
    Abstract: A method of warping data includes the steps of providing a set of target coordinates x?N, calculating, by a warping engine, source coordinates x??N for the target coordinates x?N, requesting, by the warping engine, data values for a plurality of source coordinates from a cache, and computing, by the warping engine, interpolated data values for each x in a neighborhood of x? from the data values of the source coordinates returned from the cache. Requesting data values from the cache includes notifying the cache that data values for a particular group of source points will be needed for computing interpolated data values for a particular target point, and fetching the data values for the particular group of source points when they are need for computing interpolated data values for the particular target point.
    Type: Grant
    Filed: December 16, 2020
    Date of Patent: November 22, 2022
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Yuval Shicht, Eyal Rosin, Michael Dinerstein
  • Patent number: 11501457
    Abstract: A method for identifying a dendritic pore is provided. Line and pore images are obtained from a digital image of a subject's skin. These line and pore images are overlaid to identify those pores having at least one line intersecting the pore as dendritic pores.
    Type: Grant
    Filed: May 7, 2021
    Date of Patent: November 15, 2022
    Assignee: The Procter & Gamble Company
    Inventors: Dissanayake Mudiyanselage Mahathma Bandara Dissanayake, Naoki Miyamoto
  • Patent number: 11500115
    Abstract: A method can include accessing a trained machine model as trained to analyze digital seismic data of a region with respect to a structural feature of a geologic region; analyzing at least a portion of the digital seismic data using the trained machine model to generate results; and outputting the results as indicators of spatial locations of the structural feature of the geologic region.
    Type: Grant
    Filed: June 7, 2019
    Date of Patent: November 15, 2022
    Assignee: Schlumberger Technology Corporation
    Inventor: Trond Hellem Bø
  • Patent number: 11488365
    Abstract: Examples of the disclosure describe systems and methods for recording augmented reality and mixed reality experiences. In an example method, an image of a real environment is received via a camera of a wearable head device. A pose of the wearable head device is estimated, and a first image of a virtual environment is generated based on the pose. A second image of the virtual environment is generated based on the pose, wherein the second image of the virtual environment comprises a larger field of view than a field of view of the first image of the virtual environment. A combined image is generated based on the second image of the virtual environment and the image of the real environment.
    Type: Grant
    Filed: October 23, 2020
    Date of Patent: November 1, 2022
    Assignee: Magic Leap, Inc.
    Inventors: John Carl Paulus, Jr., Michael Harold Liebenow
  • Patent number: 11460974
    Abstract: A client application associated with a content sharing network can include functionality for discovering content (e.g., text, image, audio, video, and other multimedia data) of the network. The content discovery functionality can be graphically represented as a feed with the top-ranking content (e.g., most relevant content, most recently created content, content created in a geographic location most proximate to a user, etc.) displayed at the top of the feed and lower-ranking content displayed at the bottom of the feed. The feed can re-order itself based on user interactions, content characteristics, system trends, and the like. A user can navigate to various portions of the feed, and the feed can continuously refresh itself to give the user an impression of an infinite feed of fresh, relevant content.
    Type: Grant
    Filed: August 23, 2018
    Date of Patent: October 4, 2022
    Assignee: Snap Inc.
    Inventor: Michael Brian Murray
  • Patent number: 11423509
    Abstract: The present disclosure describes a method and apparatus for displaying a face of a virtual role, a terminal, and a storage medium, and relates to the field of human-machine interaction. The method includes obtaining a face parameter corresponding to a user face, the face parameter being used for indicating a facial feature of a face region of the user face. The method also includes determining a warping control parameter according to the face parameter, the warping control parameter being used for controlling a warping degree of a face region of a virtual role; generating a virtual role face image according to the warping control parameter and a warping image set, the warping image set comprising a basic face image and at least one basic warping face image of the virtual role, and different basic warping face images corresponding to different face warping manners; and displaying the virtual role face image.
    Type: Grant
    Filed: May 10, 2021
    Date of Patent: August 23, 2022
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventor: Chao Shen
  • Patent number: 11423513
    Abstract: Systems and methods in accordance with embodiments of the invention are disclosed that use super-resolution (SR) processes to use information from a plurality of low resolution (LR) images captured by an array camera to produce a synthesized higher resolution image. One embodiment includes obtaining input images using the plurality of imagers, using a microprocessor to determine an initial estimate of at least a portion of a high resolution image using a plurality of pixels from the input images, and using a microprocessor to determine a high resolution image that when mapped through the forward imaging transformation matches the input images to within at least one predetermined criterion using the initial estimate of at least a portion of the high resolution image.
    Type: Grant
    Filed: November 15, 2020
    Date of Patent: August 23, 2022
    Inventors: Dan Lelescu, Gabriel Molina, Kartik Venkataraman
  • Patent number: 11398046
    Abstract: The present invention provides an object position determination circuit including a receiving circuit and a detecting circuit. In operations of the object position determination circuit, the receiving circuit receives an image signal; and the detecting circuit detects a position of an object in an Nth frame of the image signal, determines a partial region within an (N+M)th frame of the image signal according to the position of the object in the Nth frame, and only detects the partial region within the (N+M)th frame to determine a position of the object in the (N+M)th frame, wherein N and M are positive integers.
    Type: Grant
    Filed: August 19, 2019
    Date of Patent: July 26, 2022
    Assignee: Realtek Semiconductor Corp.
    Inventors: Teng-Hsiang Yu, Chun-Hsing Hsieh, Yen-Lin Chen
  • Patent number: 11393419
    Abstract: The display technologies relate to a method and computer-readable medium for displaying image and to a display device configured to perform the method for displaying image. The image display method includes acquiring an image for display in an nth frame on a display screen; detecting a first sub-image and a second sub-image within the image, a resolution of the first sub-image being higher than a resolution of the second sub-image; comparing the first sub-image in the nth frame with a corresponding sub-image in an (n?1)th frame; and refreshing a localized area of the display screen positionally corresponding to the first sub-image to display an interpolated sub-image in the localized area.
    Type: Grant
    Filed: December 12, 2019
    Date of Patent: July 19, 2022
    Assignees: BEIJING BOE OPTOELECTRONICS TECHNOLOGY CO., LTD., BOE TECHNOLOGY GROUP CO., LTD.
    Inventors: Tiankuo Shi, Lingyun Shi, Xiaomang Zhang, Zhihua Ji, Yafei Li, Xin Duan, Xiurong Wang, Wei Sun, Hao Zhang, Ming Chen, Yuxin Bi
  • Patent number: 11386525
    Abstract: An image stitching apparatus and an operation method thereof are provided. The image stitching apparatus includes a stitching distance determining circuit and a stitching circuit. The stitching distance determining circuit dynamically determines the stitching distance according to the reference information related to the plurality of original images. The stitching circuit is coupled to the stitching distance determining circuit to receive the stitching distance. The stitching circuit image stitches the original images using a stitching distance to generate a stitched image.
    Type: Grant
    Filed: December 25, 2019
    Date of Patent: July 12, 2022
    Assignee: Acer Incorporated
    Inventor: Chen-Ju Cheng
  • Patent number: 11380131
    Abstract: A method and device for face recognition, a storage medium, and an electronic device are provided. The method includes the following. Face data to-be-tested is obtained. A first derived face data set related to the face data to-be-tested is generated according to the face data to-be-tested. For each of multiple derived face data in the first derived face data set, perform age determination, and generate an age distribution interval corresponding to the first derived face data set. Whether the age distribution interval matches a first reference age interval is determined. Upon determining that the age distribution interval matches the first reference age interval, age data corresponding to the face data to-be-tested is obtained according to the age distribution interval.
    Type: Grant
    Filed: December 30, 2019
    Date of Patent: July 5, 2022
    Assignee: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP., LTD.
    Inventor: Kun Liang
  • Patent number: 11380034
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for semantically-consistent image style transfer. One of the methods includes: receiving an input source domain image; processing the source domain image using one or more source domain low-level encoder neural network layers to generate a low-level representation; processing the low-level representation using one more high-level encoder neural network layers to generate an embedding of the input source domain image; processing the embedding using one or more high-level decoder neural network layers to generate a high-level feature representation of features of the input source domain image; and processing the high-level feature representation of the features of the input source domain image using one or more target domain low-level decoder neural network layers to generate an output target domain image that is from the target domain but that has similar semantics to the input source domain image.
    Type: Grant
    Filed: October 29, 2018
    Date of Patent: July 5, 2022
    Assignee: Google LLC
    Inventors: Stephan Gouws, Frederick Bertsch, Konstantinos Bousmalis, Amelie Royer, Kevin Patrick Murphy
  • Patent number: 11348370
    Abstract: The disclosure is inputting a first image captured an image of an authentication target; inputting a second image captured an image of a right eye or a left eye of the target; determining whether the second image is of a left eye or a right eye of the target based on information including the first image, and outputting a determination result as left/right information in association with the second image; detecting an overlap between a region including the second image and a predetermined region in the first image; calculating a verification score by comparing characteristic information that are related to the left/right information with iris characteristic information calculated from the second image, and calculating a first weighted verification score obtained by weighting the verification score with a detection result; and authenticating a target in the second image based on the first weighted verification score, and outputting an authentication result.
    Type: Grant
    Filed: October 16, 2018
    Date of Patent: May 31, 2022
    Assignee: NEC CORPORATION
    Inventors: Takashi Shibata, Shoji Yachida, Chisato Funayama, Masato Tsukada, Yuka Ogino, Keiichi Chono, Emi Kitagawa, Yasuhiko Yoshida, Yusuke Mori
  • Patent number: 11334970
    Abstract: One or more embodiments of an image enhancement system enable a computing device to generate an enhanced digital image. In particular, a computing device can enhance a digital image including, for example, a photograph of a whiteboard, document, chalkboard, or other object having a uniform background. The computing device can determine modifications to apply to the digital image by minimizing an energy heuristic that both causes pixels of the digital image to change to a uniform color (e.g., white) and preserves gradients from the digital image. The computing device can further generate an enhanced digital image by applying the determined modifications to the digital image.
    Type: Grant
    Filed: May 4, 2020
    Date of Patent: May 17, 2022
    Assignee: Dropbox, Inc.
    Inventor: Jongmin Baek
  • Patent number: 11335038
    Abstract: The present disclosure directs to a system and method for CT imaging. The method may include acquiring computed tomography (CT) data, wherein the CT data is generated by scanning a subject using a CT scanner, the CT scanner including a focal spot and a detector, and the detector including a plurality of detector units. The method may also include obtaining a forward projection model and a back projection model, wherein the forward projection model and the back projection model are associated with sizes of the detector units and a size of the focal spot of the CT scanner. The method may further include reconstructing a CT image of the subject iteratively based on the CT data, the forward projection model, and the back projection model.
    Type: Grant
    Filed: November 4, 2019
    Date of Patent: May 17, 2022
    Assignee: UIH AMERICA, INC.
    Inventors: Stanislav Zabic, Patrick Joseph Kling
  • Patent number: 11328038
    Abstract: Herein are disclosed computation units for batch normalization. A computation unit may include a first circuit to traverse a batch of input elements xi having a first format, to produce a mean ?1 in the first format and a mean ?2 in a second format, the second format having more bits than the first format. The computation unit may further include a second circuit operatively coupled to the first circuit to traverse the batch of input elements xi to produce a standard deviation ? for the batch using the mean ?1 in the first format. The computation unit may also include a third circuit operatively coupled to the second circuit to traverse the batch of input elements xi to produce a normalized set of values yi using the mean ?2 in the second format and the standard deviation ?.
    Type: Grant
    Filed: November 25, 2019
    Date of Patent: May 10, 2022
    Assignee: SambaNova Systems, Inc.
    Inventors: Mingran Wang, Xiaoyan Li, Yongning Sheng
  • Patent number: 11315283
    Abstract: A system for object detection and posture estimation based on an object-customized image feature detection algorithm according to an embodiment of the present disclosure comprises at least one or more processors; and at least one or more memories, wherein at least one application, as an application that is stored in the memory and performs object detection and posture estimation based on an object-customized image feature detection algorithm by being executed by the at least one or more processors, learns a goal object based on a plurality of image feature detection algorithms, generates an algorithm list that includes evaluation of the plurality of image feature detection algorithms for detecting the learned goal object, detects a target object corresponding to the goal object among at least one or more candidate objects within an input image based on the generated algorithm list, and performs a posture estimation process for the detected target object based on the generated algorithm list.
    Type: Grant
    Filed: December 16, 2021
    Date of Patent: April 26, 2022
    Assignee: VIRNECT INC.
    Inventors: Ki Young Kim, Yeon Jo Kim, Noh Young Park
  • Patent number: 11303806
    Abstract: A method for displaying a surround view on a single display screen is disclosed. A plurality of image frames for a particular time may be received from a corresponding plurality of cameras. A viewpoint warp map corresponding to a predetermined first virtual viewpoint may be selected, wherein the viewpoint warp map defines a source pixel location in the plurality of image frames for each output pixel location in the display screen. The warp map was predetermined offline and stored for later use. An output image is synthesized for the display screen by selecting pixel data for each pixel of the output image from the plurality of image frames in accordance with the viewpoint warp map. The synthesized image is then displayed on a display screen.
    Type: Grant
    Filed: December 19, 2019
    Date of Patent: April 12, 2022
    Assignee: TEXAS INSTRUMENTS INCORPORATED
    Inventors: Vikram VijayanBabu Appia, Sujith Shivalingappa, Brijesh Rameshbhai Jadav, Hemant Hariyani, Shashank Dabral, Mayank Mangla
  • Patent number: 11281287
    Abstract: The invention relates to computerized data processing, more particularly to methods of generating an augmented reality environment, and comprises the following steps: controlling the position of an unmanned transport vehicle having a built-in camera, determining the position coordinates of the unmanned transport vehicle, transmitting a captured camera image to a user display means for visualization, exchanging messages in real time between the user and at least one second user located within visual range of the unmanned transport vehicle and equipped with augmented reality visualization means, visualizing an image captured by a camera of the second user using augmented reality generating means of the second user, visualizing a spatial model of the user, wherein the position of the spatial model in the visualized image corresponds to the position of the unmanned transport vehicle in the captured image from the camera of the second user.
    Type: Grant
    Filed: July 13, 2017
    Date of Patent: March 22, 2022
    Assignee: DEVAR ENTERTAINMENT LIMITED
    Inventors: Vitaly Vitalyevich Averyanov, Andrey Valeryevich Komissarov
  • Patent number: 11276207
    Abstract: An image processing method for a computer device. The method includes obtaining a to-be-processed image belonging to a first image category; inputting the to-be-processed image into a first stage image conversion model, to obtain a first intermediate image; and converting the first intermediate image into a second intermediate image through a second stage image conversion model. The method also includes determining a first weight matrix corresponding to the first intermediate image; determining a second weight matrix corresponding to the second intermediate image; and fusing the first intermediate image and the second intermediate image according to the corresponding first weight matrix and second weight matrix, to obtain a target image corresponding to the to-be-processed image and belonging to a second image category. A sum of the first weight matrix and the second weight matrix being a preset matrix.
    Type: Grant
    Filed: May 21, 2020
    Date of Patent: March 15, 2022
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Minjun Li, Haozhi Huang, Lin Ma, Wei Liu, Yugang Jiang
  • Patent number: 11275962
    Abstract: The present disclosure provides a method for image capturing, a method for image capturing control and associated apparatuses. The method for image capturing includes: obtaining Region Of Interest (ROI) information of a target ROI corresponding to a current frame of image; buffering captured pixel data of the current frame of image; obtaining, when determining that the pixel data of the current frame of image has been buffered completely, pixel data associated with the target ROI from the buffered pixel data of the current frame of image based on the ROI information if the ROI information of the target ROI corresponding to the current frame of image can be obtained; and outputting the pixel data associated with the target ROI.
    Type: Grant
    Filed: January 17, 2019
    Date of Patent: March 15, 2022
    Assignee: BEIJING TUSEN ZHITU TECHNOLOGY CO., LTD.
    Inventors: Ming Wang, Jie Sun
  • Patent number: 11265564
    Abstract: Disclosed are a display apparatus and a method of controlling the same, the display apparatus including: a video decoder configured to decode a video signal; and an artificial intelligence (AI) scaler including a plurality of filters provided to make an output of a certain filter be used as an input of another filter, and configured to control a resolution of an image by processing the decoded video signal, each of the plurality of filters being selectively turned on or off based on a control signal, the filter being turned on processing the video signal based on a parameter set by learning, and the filter being turned off bypassing and outputting the input video signal.
    Type: Grant
    Filed: November 12, 2019
    Date of Patent: March 1, 2022
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Sangjo Lee, Sangkwon Na, Doohyun Kim
  • Patent number: 11249173
    Abstract: An imaging apparatus includes first and second imaging devices configured to capture first and second images of a scene, respectively. The first and second images include multiple first image blocks relative to a first coordinate system and multiple second image blocks relative to a second coordinate system, respectively. The apparatus further includes a processor configured to calibrate one or more first image blocks and one or more corresponding second image blocks using the first and second coordinate systems, convert each calibrated first image block to an intensity image and a first depth map, convert each calibrated second image block to a grayscale image, and generate a second depth map associated with the second image by enhancing a resolution of the first depth map for each calibrated first image block based on calculating a relationship between the intensity image and the grayscale image for each calibrated first and second image blocks.
    Type: Grant
    Filed: November 25, 2019
    Date of Patent: February 15, 2022
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventors: Zhenyu Zhu, Cong Zhao, Ketan Tang
  • Patent number: 11237308
    Abstract: The embodiments of the present disclosure disclose a display apparatus. The display apparatus includes: a display unit having a plurality of pixel units; a lens unit; and a light path adjustment unit disposed between the display unit and the lens unit and configured to adjust a light path of light emitted from at least one of the plurality of pixel units, such that the adjusted light path has a predetermined range of incident angles with respect to the lens unit.
    Type: Grant
    Filed: April 27, 2018
    Date of Patent: February 1, 2022
    Assignee: BOE TECHNOLOGY GROUP CO., LTD.
    Inventors: Xinli Ma, Xiaochuan Chen
  • Patent number: 11223749
    Abstract: A scaler includes an input interface, an output Vsync pulse generating circuit and a data buffer circuit. The input interface is arranged to receive an input Vsync pulse and input image data. The output Vsync pulse generating circuit is arranged to accordingly generate a first output Vsync pulse and a first output request in response to the input Vsync pulse. The data buffer circuit is arranged to buffer the input image data and, in response to the first output request, output a first output frame according to the input image data. The output Vsync pulse generating circuit further generates a second output Vsync pulse and a second output request according to the first output Vsync pulse and a first predetermined period and in response to the second output request, the data buffer circuit further outputs a second output frame according to the input image data.
    Type: Grant
    Filed: May 27, 2021
    Date of Patent: January 11, 2022
    Assignee: Realtek Semiconductor Corp.
    Inventors: Ying-Hsin Lin, Wen-Hsia Kung, Chun-Chieh Chan
  • Patent number: 11221740
    Abstract: As three-dimensional (3D) printing and additive manufacturing becomes a way for individuals and companies to distribute physical goods, there is a growing need for creators of physical goods to enable customers to customize 3D printed objects while protecting core electronic assets in the form of the files used to define and print the objects. Server-side rendering of 3D object images provides an opportunity to protect 3D object files while offering performance advantages. A scripting language may be central to delivering a seamless user experience interacting with 3D object models on client devices. Object creators and vendors may rely on the scripting language to create user interfaces for selling customizable objects. And once the user interface is developed, it may provide the basis for users accessing, viewing, manipulating, selecting materials, rendering, pricing, and printing a range of 3D objects.
    Type: Grant
    Filed: March 12, 2018
    Date of Patent: January 11, 2022
    Assignee: Shapeways, Inc.
    Inventor: Alan D. Hudson
  • Patent number: 11220269
    Abstract: A computer-implemented method for fording depth estimation based on a real-time image recognition is provided according an embodiment of the present disclosure. In the method, a first image of a low-lying road being submerged under a bridge can be acquired. At least one second image of the low-lying road without being submerged can be determined. A fording depth of the low-lying road can be estimated based on the first image and the at least one second image.
    Type: Grant
    Filed: April 2, 2019
    Date of Patent: January 11, 2022
    Assignee: International Business Machines Corporation
    Inventors: Cheng Xu, Su Liu, Kuo-Liang Chou, Shun Xian Wu, Yin Xi Guo
  • Patent number: 11213374
    Abstract: 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: Grant
    Filed: February 19, 2019
    Date of Patent: January 4, 2022
    Assignee: Ivoclar Vivadent AG
    Inventors: Marcel Lancelle, Roland Mörzinger, Nicolas Degen, Gabor Sörös, Bartolovic Nemanja
  • Patent number: 11202053
    Abstract: Techniques are disclosed for conversion of panoramas between different panoramic projections, including stereoscopic panoramic projections. The pixels of one panoramic image are mapped to the pixels of another panoramic image using ray tracing so that the images can be combined without introducing visual distortions caused by mismatches in the optics of each image. The conversion is performed using a process for mapping one or more pixels of an output image to pixels of an input image by tracing a ray between the UV coordinates corresponding to each pixel in the images. The conversion process accounts for arbitrary projections and for arbitrary stereo camera rig configurations by using metadata that describe the projection and positioning of each image being combined. The origin of each ray is offset to account for the interpupillary distance between left and right images and to account for any rotation of the scene.
    Type: Grant
    Filed: June 1, 2020
    Date of Patent: December 14, 2021
    Assignee: Adobe Inc.
    Inventor: Bhautik Jitendra Joshi
  • Patent number: 11188768
    Abstract: An object detection apparatus 100 is an apparatus for detecting an object in a fish-eye image. The object detection apparatus 100 includes a normalized image acquisition unit 10 configured to acquire a normalized image obtained by normalizing a fish-eye image in which an object appears; a position detecting unit 20 configured to detect position coordinates of the object in the normalized image; and a determination unit 30 configured to determine a positional relationship between the object and the object detection apparatus 100 using the position coordinates of the object in the normalized image.
    Type: Grant
    Filed: June 23, 2017
    Date of Patent: November 30, 2021
    Assignee: NEC CORPORATION
    Inventor: Kosuke Yoshimi
  • Patent number: 11190808
    Abstract: There is provided an image processing apparatus and an image processing method in which S/N can be improved. A class tap selection unit configures a class tap by selecting a pixel that is a class tap used in class classification of classifying a pixel to be processed of a first image obtained by adding a residual error of prediction encoding and a prediction image together, into any one class of a plurality of classes, from the first image. A class classification unit performs the class classification of the pixel to be processed by using the class tap, and a filter processing unit performs filter processing corresponding to class of the pixel to be processed, with respect to the first image, to generate a second image used in prediction of the prediction image. The class tap selection unit updates a tap structure of the class tap to a selected tap structure.
    Type: Grant
    Filed: December 28, 2017
    Date of Patent: November 30, 2021
    Assignee: SONY CORPORATION
    Inventors: Takuro Kawai, Kenichiro Hosokawa, Ohji Nakagami, Masaru Ikeda
  • Patent number: 11189066
    Abstract: Embodiments disclosed herein describe systems, methods, and products that train one or more neural networks and execute the trained neural network across various applications. The one or more neural networks are trained to optimize a loss function comprising a pixel-level comparison between the outputs generated by the neural networks and the ground truth dataset generated from a bubble view methodology or an explicit importance maps methodology. Each of these methodologies may be more efficient than and may closely approximate the more expensive but accurate human eye gaze measurements. The embodiments herein leverage an existing process for training neural networks to generate importance maps of a plurality of graphic objects to offer interactive applications for graphics designs and data visualizations.
    Type: Grant
    Filed: November 13, 2018
    Date of Patent: November 30, 2021
    Assignee: Adobe Inc.
    Inventors: Zoya Bylinskii, Aaron Hertzmann, Bryan Russell
  • Patent number: 11179884
    Abstract: Systems and methods are provided for incremental 3D printing, wherein wireframes are generated and printed (scheduled for print) during the design process. In another aspect, systems and methods are provided for printing arbitrary meshes. A 3D printer system is described having, for example, five degree-of-freedom (5DOF). The 5DOF printer may be used to perform any of the methods described herein and combinations of the methods.
    Type: Grant
    Filed: April 14, 2017
    Date of Patent: November 23, 2021
    Assignee: Cornell University
    Inventors: Francois Guimbretiere, Huaishu Peng, Stephen Robert Marschner, Rundong Wu
  • Patent number: 11153449
    Abstract: A display processor of a controller extracts data such as images and characters from display data stored in a storage based on setting information stored in the storage, and displays a document orientation instructing pane and a 90-degree rotation operation icon in a document image operating pane on a display device. The display processor also displays a print preview image based on the document image data. When a rotation operation is performed through the 90-degree rotation operation icon, the document image data is also subjected to the same rotation process.
    Type: Grant
    Filed: June 23, 2020
    Date of Patent: October 19, 2021
    Assignee: SHARP KABUSHIKI KAISHA
    Inventor: Kazuhisa Kubota
  • Patent number: 11147647
    Abstract: To reduce more load related to the correction of deformation of an observation image that is caused by an error between a plurality of imaging sections. A medical stereoscopic observation device includes: an acquisition section configured to acquire, from an imaging unit including a first imaging section configured to capture a left-eye image and a second imaging section configured to capture a right-eye image, correction data for correcting an error related to capturing of an image between the first imaging section and the second imaging section, the imaging unit being rotatably held by a support section; and a correction section configured to correct a difference of parallax between the left-eye image and the right-eye image on a basis of the correction data, using a position corresponding to a rotation axis of the imaging unit as a reference position.
    Type: Grant
    Filed: January 24, 2017
    Date of Patent: October 19, 2021
    Assignee: SONY OLYMPUS MRDICAL SOLUTIONS INC.
    Inventors: Masataka Kado, Tomonori Ishikawa, Gakuji Higuchi, Hiroshi Ushiroda, Takahiro Yamamoto, Masashige Kimura
  • Patent number: 11134080
    Abstract: A method for authenticating a user of a terminal equipment connected to a communication network, for access from this terminal equipment to a remote service hosted by a server equipment connected to the network. The method includes the following steps, implemented by the server: authenticating the user from credentials; in the event of successful user authentication, authenticating the client equipment from credentials stored in a first memory of the server in association with the user's credentials, including a command to render a first pattern, the command including parameters describing the first pattern and rendering the first pattern received from the client equipment, so-called reference pattern; deciding on authenticating the client equipment according to the evaluated score, a successful authentication being decided when the match score is greater than a predetermined threshold; and following the authentication decision, updating the credentials of the terminal equipment.
    Type: Grant
    Filed: October 19, 2017
    Date of Patent: September 28, 2021
    Assignee: FONDATION B-COM
    Inventors: Gaetan Le Guelvouit, Alexandre Garel
  • Patent number: 11106894
    Abstract: An image processing apparatus comprises a normalisation module operatively connected across a bus to a memory storing an image in which a region of interest (ROI) has been identified within the image. The ROI is bound by a rectangle having a non-orthogonal orientation within the image. In one embodiment, the normalisation module is arranged to divide the ROI into one or more slices, each slice comprising a plurality of adjacent rectangular tiles. For each slice, the apparatus successively reads ROI information for each tile from the memory including: reading a portion of the image extending across at least a width of the slice line-by-line along an extent of a slice. For each tile, the apparatus downsamples the ROI information to a buffer to within a scale SD<2 of a required scale for a normalised version of the ROI.
    Type: Grant
    Filed: October 25, 2018
    Date of Patent: August 31, 2021
    Assignee: FotoNation Limited
    Inventors: Vlad Georgescu, Mihai Constantin Munteanu, Petronel Bigioi, Corneliu Zaharia, Szabolcs Fulop, Gyorgy Simon
  • Patent number: 11107185
    Abstract: Disclosed are systems, methods, and computer-readable storage media to perform automatic image inpainting using local patch statistics. The method includes receiving a user input identifying a user-selected region of an image and determining a local region for the user-selected region. The local region includes a portion of the image outside of the user-selected region and that surrounds the user-selected region. The method may further include identifying patch matches within the local region, and inpainting the user-selected region using some of the patch matches identified within the local region.
    Type: Grant
    Filed: March 25, 2020
    Date of Patent: August 31, 2021
    Assignee: Snap Inc.
    Inventors: Kun Duan, Yunchao Gong, Nan Hu
  • Patent number: 11094108
    Abstract: Systems and methods for rendering three-dimensional (3D) scenes having improved visual characteristics from a pair of 2D images having different viewpoints. The 3D scene is created by obtaining a first two-dimensional (2D) image of a scene object from a first viewpoint, obtaining a second 2D image of the scene object from a second viewpoint that is different than the first viewpoint, creating a depth map from the first and second 2D images, creating a 3D scene from the depth map and the first and second 2D images, detecting regions of the initial 3D scene with incomplete image information, reconstructing the detected regions of the 3D scene, determining replacement information and modify the reconstructed regions, and rendering the 3D scene with the modified reconstructed regions from a plurality of viewpoints.
    Type: Grant
    Filed: September 4, 2019
    Date of Patent: August 17, 2021
    Assignee: Snap Inc.
    Inventors: Nir Daube, Zachi Karni
  • Patent number: 11055886
    Abstract: There is provided a method for filling at least one color in one or more outline images at a multi-function device. The method includes providing a user interface for displaying a color fill option. Based on receiving a selection of the color fill option, a file including at least one outline image is received by a controller. The at least one outline image includes at least one image field. Then, it is identified by an image processor, if the at least one image field includes at least one color marking. Based on the identification, the at least one image field is automatically filled by the image processor according to the at least one color marking to generate a color filled image.
    Type: Grant
    Filed: April 15, 2019
    Date of Patent: July 6, 2021
    Assignee: XEROX CORPORATION
    Inventors: Srinivasarao Bindana, Sudhagar Subbaian
  • Patent number: 11049434
    Abstract: An electronic device and a method for controlling the electronic device are provided. The electronic device includes a substantially circular or oval display, a processor configured to generate content, a display driving unit comprising display driving circuitry including a first driver and a second driver, wherein the display driving unit is configured to control driving of the display, to identify a shape of an area of content which is displayed in the display, to identify the shape of the display, to determine a first area of the display in which the content is to be displayed, to determine a second area of the display in which the content is not to be displayed based on at least a result of the identification, to deactivate at least part of the display driving unit, corresponding to the second area, while activating the display driving unit corresponding to the first area.
    Type: Grant
    Filed: April 20, 2017
    Date of Patent: June 29, 2021
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Jong-Kon Bae, Yo-Han Lee, Dong-Hui Kim, Dong-Kyoon Han
  • Patent number: 11025681
    Abstract: A method of processing of a sequence of video frames from a camera capturing a writing surface for subsequent transmission to at least one of a remote videoconferencing client and a remote videoconferencing server. The method comprises receiving the sequence of video frames from the camera; and selecting an image area of interest in the video frames, comprising selecting one of a sub-area of the video frames and an entire area of the video frames. The method also comprises, for each current video frame of the sequence of video frames, generating a pen stroke mask by applying adaptive thresholding to the image area of interest. The method also comprises generating an output video frame using the pen stroke mask. Corresponding systems and computer readable media are disclosed.
    Type: Grant
    Filed: September 27, 2018
    Date of Patent: June 1, 2021
    Assignee: Dolby Laboratories Licensing Corporation
    Inventor: Timothy Alan Port
  • Patent number: 11004226
    Abstract: A stereo image capturing device captures a stereo image with a measurement target range in front of a vehicle as an angle of field, and a display device is disposed so as to cover at least part of the measurement target range as seen from the viewpoint position of a driver inside the vehicle. Then a distance measuring section measures the distances to another object in the measurement target range using the stereo image and identifies the object within a predetermined distance as an obstacle, and an image generating section generates a virtual mirror image that allows at least the vehicle and the obstacle to be seen using a reflection by a mirror in a case where the mirror is assumed to be virtually disposed above a location at which the obstacle is seen from the viewpoint position of the driver in the vehicle, and causes the display device to display the virtual mirror image. The present technology can be applied, for example, to in-vehicle image display systems.
    Type: Grant
    Filed: August 28, 2018
    Date of Patent: May 11, 2021
    Assignee: SONY CORPORATION
    Inventor: Shingo Tsurumi
  • Patent number: 11004173
    Abstract: A video processing method includes: obtaining a plurality of projection faces from an omnidirectional content of a sphere, wherein the omnidirectional content of the sphere is mapped onto the projection faces via cubemap projection, and the projection faces comprise a first projection face; obtaining, by a re-sampling circuit, a first re-sampled projection face by re-sampling at least a portion of the first projection face through non-uniform mapping; generating a projection-based frame according to a projection layout of the cubemap projection, wherein the projection-based frame comprises the first re-sampled projection face packed in the projection layout; and encoding the projection-based frame to generate a part of a bitstream.
    Type: Grant
    Filed: September 26, 2018
    Date of Patent: May 11, 2021
    Assignee: MEDIATEK INC.
    Inventors: Jian-Liang Lin, Peng Wang, Lin Liu, Ya-Hsuan Lee, Hung-Chih Lin, Shen-Kai Chang
  • Patent number: 10984338
    Abstract: Various examples are provided for dynamically updating or adapting predictive modeling for prediction of outcomes of interest for operating systems and processes. Embodiments of the disclosure may provide systems, apparatus, processes, and methods for generating and deploying dynamically updated predictive models. In some embodiments, the predictive model may be deployed for the purpose of predicting operational outcomes of interests in operating systems, hardware devices, machines and/or processes associated therewith prior to the operational outcomes of interest occurring. The predictions can, for example, provide sufficient time for maintenance or repairs to be scheduled and carried out to avoid the predicted operational outcome. Autonomous evaluation of features allows the predictive models to be dynamically updated in response to changes in the environment or monitored data.
    Type: Grant
    Filed: April 20, 2016
    Date of Patent: April 20, 2021
    Assignee: RAYTHEON TECHNOLOGIES CORPORATION
    Inventors: Robert G. Morris, II, William McGinnis
  • Patent number: 10977439
    Abstract: Methods, systems and computer program products for multi-style text transformation are provided herein. A computer-implemented method includes obtaining input text and selecting a set of style specifications for transforming the input text. The set of style specifications include one or more target writing style domains selected from a plurality of writing style domains, weights for each of the target writing style domains representing relative impact of the target writing style domains for transformation of the input text, and weights for each of a set of linguistic aspects for transformation of the input text. The computer-implemented method also includes generating one or more style-transformed output texts based at least in part on the set of style specifications utilizing an unsupervised neural network.
    Type: Grant
    Filed: April 1, 2019
    Date of Patent: April 13, 2021
    Assignee: International Business Machines Corporation
    Inventors: Abhijit Mishra, Parag Jain, Amar P. Azad, Karthik Sankaranarayanan