Color Image Processing Patents (Class 382/162)
  • Patent number: 12267548
    Abstract: The disclosed technology relates to an electronic device including a display device and an image sensor. The device may include a processor configured to cause the display device to output an illumination image in response to a command to capture one or more digital images of a scene. The processor can also be configured to cause the image sensor to receive the one or more digital images of the scene while the illumination image is displayed.
    Type: Grant
    Filed: January 18, 2024
    Date of Patent: April 1, 2025
    Assignee: QUALCOMM Incorporated
    Inventor: Stepan Moskovchenko
  • Patent number: 12266139
    Abstract: A method and apparatus for integrating data compression in a computer system includes receiving first data at a first system level. Based upon a number of planes of the first data being less than or equal to a threshold, the data is compressed with a first data compression scheme, and transferred to a second system level for processing. Based upon the number of planes of the first data exceeding the threshold, the first data is transferred uncompressed to the second system level for processing. Based upon the received data at the second system level being compressed with the first compression scheme, the data is transferred to a third system level, and based upon the received data at the second system level being uncompressed with the first compression scheme, compressing the data with a second compression scheme, and transferring the compressed data to the third system level.
    Type: Grant
    Filed: December 14, 2021
    Date of Patent: April 1, 2025
    Assignee: Advanced Micro Devices, Inc.
    Inventors: Christopher J. Brennan, Pazhani Pillai
  • Patent number: 12260798
    Abstract: An interpolated flat-panel display comprises a display substrate and an array of clusters disposed on the display substrate. Each cluster comprises an exclusive group of display pixels and a cluster controller for controlling the display pixels. The cluster controller is operable to receive input data specifying a desired light output from one or more but fewer than all of the display pixels in the group of display pixels, calculate interpolated data at least in part from the input data, and drive the display pixels to emit light in response to the calculated interpolated data and received input data. The input data can correspond to an image pixel in an input image. The cluster controller can be operable to receive a parameter value describing attributes of a local portion of the input image including the image pixel and the interpolated data is calculated at least in part from the parameter value.
    Type: Grant
    Filed: May 26, 2022
    Date of Patent: March 25, 2025
    Assignee: X Display Company Technology Limited
    Inventors: Matthew Alexander Meitl, Ronald S. Cok, Lee B. Baker, Christopher Andrew Bower
  • Patent number: 12236679
    Abstract: Crop detection is performed in image data obtained by capturing an image of a farm field. Then, a row is determined in the image data on the basis of a result of the crop detection. The row is a line in which a crop is planted.
    Type: Grant
    Filed: October 28, 2020
    Date of Patent: February 25, 2025
    Assignee: SONY GROUP CORPORATION
    Inventor: Nobuhiro Tsunashima
  • Patent number: 12226774
    Abstract: Embodiments disclosed herein may relate to a testing apparatus. The testing apparatus may include a sealed, chemically-resistant testing apparatus body defining a testing void; a first fluid port and a second fluid port; and a first geomaterial and a second geomaterial. The first and second geomaterials may be positioned between the first fluid port and the second fluid port and relative to one another such that a flow channel may be provided between the first and second geomaterials. The first and second geomaterials may be coupled to a testing void interior surface so as to restrict flow to the flow channel between an upflow region and a downflow region of the testing void. The first and second geomaterials may be comprised of a natural formation material.
    Type: Grant
    Filed: September 29, 2020
    Date of Patent: February 18, 2025
    Assignee: SAUDI ARABIAN OIL COMPANY
    Inventors: Hamad Alarji, Yara Alzahid
  • Patent number: 12223757
    Abstract: An image processing method, applied to an electronic apparatus, includes performing feature extraction processing on a source image to obtain a feature data set corresponding to a source file, determining an image processing parameter corresponding to the feature data set according to the feature data set, and processing the source image according to the image processing parameter.
    Type: Grant
    Filed: June 22, 2022
    Date of Patent: February 11, 2025
    Assignee: ZHUHAI PANTUM ELECTRONICS CO., LTD.
    Inventors: Jibing Peng, Yangxiao Ma
  • Patent number: 12201439
    Abstract: A device for photographing a human face comprising: a) a light-excluding housing configured to receive a human face at an aperture in said housing; and b) a stand on which the light-excluding housing is mounted at one or more (preferably two rotatable pivot points, such that rotation about said pivot points results in movement of the aperture upwards and/or downwards.
    Type: Grant
    Filed: September 27, 2019
    Date of Patent: January 21, 2025
    Assignee: IIAA LIMITED
    Inventors: Alex Blondek, Daniel Richard Walmsley, Gary David Ross, Jeremy Frank Saunders, Richard Kier Bebbington
  • Patent number: 12175194
    Abstract: Video classification accuracy can be improved by utilizing multiple features. Classification based on a combination of an image classification model, an audio classification model, and a textual description classification model may improve classification. The image classification result is based on an image feature of the image frame. The audio classification result is based on an audio feature of the audio. The textual description classification result is based on a text feature of the textual description information. A target classification result of the target video is determined based on to the image classification result, the audio classification result, and the textual classification result.
    Type: Grant
    Filed: March 4, 2021
    Date of Patent: December 24, 2024
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Bing Xin Qu, Mao Zheng
  • Patent number: 12177473
    Abstract: Systems and techniques are provided for coding video data based on an optical flow correction and a residual correction. For example, a decoding device can obtain a frame of encoded video data associated with an input frame, the frame of encoded video data including an optical flow correction and a residual correction. A predicted optical flow can be generated based on one or more reference frames and a reference optical flow. A corrected prediction frame can be generated based on the predicted optical flow and the optical flow correction. A predicted residual can be generated based on at least the corrected prediction frame and a first reference frame included in the one or more reference frames. The decoding device can generate a reconstructed input frame based on the corrected prediction frame, the predicted residual, and the residual correction.
    Type: Grant
    Filed: July 11, 2022
    Date of Patent: December 24, 2024
    Assignee: QUALCOMM Incorporated
    Inventors: Reza Pourreza, Hoang Cong Minh Le, Auke Joris Wiggers
  • Patent number: 12170850
    Abstract: Systems and methods for shadow detection and reduction during document capture are disclosed herein. Temporary images of hardcopy documents are analyzed to determine the presence of a shadow or hotspot that obscures information of the hardcopy document. In response to detecting the shadow or hotspot, a controllable light source is used to illuminate the hardcopy document at predicted and/or predetermined intensities to minimize or eliminate the shadow on the hardcopy document. A permanent image of the hardcopy document illuminated by the controllable light source at the intensity that minimizes or eliminates the shadow is then stored. In this way, information of the hardcopy document (such as text, color, layout, spacing etc.) is increased in the permanent image and a need for post-processing the permanent image is reduced or eliminated.
    Type: Grant
    Filed: September 30, 2022
    Date of Patent: December 17, 2024
    Assignee: Adeia Guides Inc.
    Inventors: Tao Chen, Reda Harb
  • Patent number: 12159387
    Abstract: An inspection support apparatus includes: an image acquisition unit (11) that acquires an image obtained by photographing a concrete structure that is an inspection target; a damage region extraction unit (12) that extracts from the acquired image, a damage region (water leakage, free lime, etc.) appearing on a surface of the concrete structure; a causal part detection unit (17) that detects, in a case where the damage region is extracted, a causal part (a crack, a construction joint, a joint, a peeling part, etc.) causing damage from the image on the basis of a result of extraction of the damage region; and an output unit (19) that outputs the result of extraction of the damage region and a result of detection of the causal part.
    Type: Grant
    Filed: May 12, 2021
    Date of Patent: December 3, 2024
    Assignee: FUJIFILM Corporation
    Inventor: Kazuma Matsumoto
  • Patent number: 12154253
    Abstract: A method for removing false contours from a target image includes the following steps: A) receiving the target image having a two-dimensional pixel array arranged in rows and columns; B) performing a false contour detection on a target arrangement of the target image according to a target direction, wherein the target direction is one of the row direction or the column direction of the target image; C) predicting, based on at least a first band width of a first band, a second band width of a second band, in response to the detection of a false contour between the first band and the second band, wherein the first band and the second band are adjacent to each other in the target arrangement; and D) performing pixel interpolation processing on at least a part of pixels in the second band to remove the false contour.
    Type: Grant
    Filed: October 21, 2021
    Date of Patent: November 26, 2024
    Assignee: MONTAGE LZ TECHNOLOGIES (CHENGDU) CO., LTD.
    Inventors: Chengqiang Liu, Zhimin Qiu, Youyuan Huang
  • Patent number: 12106453
    Abstract: An image processing apparatus includes a pre-processor configured to receive, from an image sensor, input image data including a pattern corresponding to a filter array of the image sensor, and generate reconstructed image data by reconstructing the input image data based on phase information corresponding to each of a plurality of pixels of the image sensor, and a neural network processor configured to generate output image data based on the input image data and the reconstructed image data.
    Type: Grant
    Filed: September 2, 2022
    Date of Patent: October 1, 2024
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Youngil Seo, Irina Kim, Seongwook Song
  • Patent number: 12100171
    Abstract: A system and method include receiving target image data associated with a target coating. A texture feature extraction analysis process is applied to the target image data to determine a target texture image feature. A machine learning model identifies one or more texture features for matching to a target coating.
    Type: Grant
    Filed: December 16, 2020
    Date of Patent: September 24, 2024
    Assignee: AXALTA COATING SYSTEMS IP CO., LLC
    Inventors: Larry E. Steenhoek, Dominic V. Poerio
  • Patent number: 12086479
    Abstract: An apparatus includes a print controller configured to perform color conversion on data using a color profile to generate image data for use in printing. The apparatus further includes a controller configured to acquire information regarding characteristic information of at least one illumination apparatus via a network, acquire first characteristic information based on the information regarding the characteristic information of the at least one illumination apparatus, acquire second characteristic information based on a color chart of the apparatus, and generate a color profile based on the first and second characteristic information.
    Type: Grant
    Filed: June 17, 2021
    Date of Patent: September 10, 2024
    Assignee: Canon Kabushiki Kaisha
    Inventor: Hidekazu Nakashio
  • Patent number: 12081718
    Abstract: An information processing apparatus includes a processor configured to receive document data, use a first design element forming the document data as a search key to search for a second design element in accordance with a condition of use for a design element, and perform processing on the second design element in accordance with the first design element to generate a third design element that has characteristics of the first design element.
    Type: Grant
    Filed: April 8, 2021
    Date of Patent: September 3, 2024
    Assignee: FUJIFILM Business Innovation Corp.
    Inventor: Yasunari Kishimoto
  • Patent number: 12073486
    Abstract: The disclosure provides a reversible watermarking method for the oblique photography three-dimensional models with controllable accuracy. According to the disclosure: firstly, by using the global stability of the average included angle of vertex normal vector, the feature points of the oblique photography three-dimensional model are extracted; secondly, the mapping relationship is established by the ratio of the distance between feature points and non-feature points, and the vertexes are grouped, and each group consists of a feature point corresponding to several non-feature points; finally, the spherical coordinate system is constructed by taking the feature points as the coordinate origin in grouping, and the watermark is embedded by modifying the radius of the coordinate system.
    Type: Grant
    Filed: March 20, 2024
    Date of Patent: August 27, 2024
    Assignee: LANZHOU JIAOTONG UNIVERSITY
    Inventors: Haowen Yan, Liming Zhang, Jingzhong Li, Xiaomin Lu, Weifang Yang, Pengbin Wang, Ziyi Zhang
  • Patent number: 12039711
    Abstract: Provided are a white balance abnormality determination method and apparatus, a storage medium, and an electronic device. The method includes: acquiring at least one target block in a first channel image, and acquiring at least one reference block in a second channel image for each target block, where the first channel image is adjacent to the second channel image; determining a color feature representative value of each target block and a color feature representative value of each reference block associated with a position of a respective target block; determining, a color feature difference value between the first channel image and the second channel image; determining whether a white balance abnormality image exists in the first channel image and the second channel image; and in a case where a white balance abnormality image exists in the first channel image and the second channel image, adjusting the white balance abnormality image.
    Type: Grant
    Filed: March 30, 2020
    Date of Patent: July 16, 2024
    Assignee: ZHEJIANG UNIVIEW TECHNOLOGIES CO., LTD.
    Inventors: Wenping Zhang, Qiong Xu
  • Patent number: 12026858
    Abstract: An electronic device may include an electronic display to display an image based on compensated image data in a panel space. The electronic device may also include image processing circuitry to generate the compensated image data. Further, generating the compensated image data may include determining a first inverse mapping of a pixel grid from the panel space to a rendering space and determining a forward mapping of the pixel grid from the rendering space to the panel space based on the first inverse mapping. The forward mapping may include corrections for multiple different warp operations stacked in a single warp operation. Additionally, the image processing circuitry may apply the forward mapping to input image data to generate the compensated image data.
    Type: Grant
    Filed: June 23, 2021
    Date of Patent: July 2, 2024
    Assignee: Apple Inc.
    Inventors: Jim C. Chou, Jian Zhou
  • Patent number: 12025640
    Abstract: A current detection device includes: a first conductor providing a part of a current path between a first inverter and a first rotary electric machine; a second conductor providing a part of a current path between a second inverter and a second rotary electric machine; a third conductor providing a part of a current path between a DC power supply and a converter; and first to third elements respectively arranged to face the first to third conductors. Each of the first to third elements is configured to detect a magnetic flux generated by an electric current flowing through a corresponding conductor in a coreless manner. A maximum value of the electric current in the second conductor is smaller than maximum values of the electric current in the first and third conductors. The second conductor is arranged between the first conductor and the third conductor in a predetermined direction.
    Type: Grant
    Filed: September 9, 2022
    Date of Patent: July 2, 2024
    Assignee: DENSO CORPORATION
    Inventor: Hiromi Ichijyo
  • Patent number: 12007758
    Abstract: A process state monitoring device incudes a processor including hardware, the processor being configured to: separate two or more components from time series data of a value indicating a state of a process; compute a characteristic value from each of the separated components; and classify the state of the process on the basis of the computed characteristic values.
    Type: Grant
    Filed: March 24, 2020
    Date of Patent: June 11, 2024
    Assignee: JFE STEEL CORPORATION
    Inventors: Takehide Hirata, Tatsuhiro Sue, Masafumi Matsushita, Yohei Harada
  • Patent number: 12003860
    Abstract: An image processing method includes: obtaining a first image photographed by each of N1 first cameras in the M1 first cameras and a second image photographed by each of N2 second cameras in the M2 second cameras; obtaining luminance values of at least a part of pixels in the first image and luminance values of at least a part of pixels in the second image for each first image and each second image; and increasing luminance of a target image based on obtained luminance values, and using, as a photographed image of the under-display camera assembly, a target image obtained after the luminance is increased. M1, N1, M2, and N2 are all integers greater than or equal to 1.
    Type: Grant
    Filed: March 9, 2022
    Date of Patent: June 4, 2024
    Assignee: VIVO MOBILE COMMUNICATION CO., LTD.
    Inventor: Zhuojian Yang
  • Patent number: 11991486
    Abstract: Disclosed is a color transform method performed by an electronic device that includes generating an initial color transformed image by performing color transform on a raw image, determine noise amplification degrees indicating degrees to which noise included in the raw image is amplified by the color transform, processing the determined noise amplification degrees, and generating a final color transformed image by filtering the generated initial color transformed image using the processed noise amplification degrees and at least one of the raw image or luminance information of the raw image.
    Type: Grant
    Filed: March 7, 2022
    Date of Patent: May 21, 2024
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Geonwoo Kim, Sung Kwang Cho, Yang Ho Cho, Dong Kyung Nam
  • Patent number: 11989854
    Abstract: An electronic device may include an electronic display to display an image based on processed image data. The electronic device may also include image processing circuitry to generate the processed image data. The image processing circuitry may receive input image data corresponding to an image in a first perspective and warp the input image data from the first perspective to a second perspective, generating warped image data. Additionally, the image processing circuitry may determine one or more occluded regions in the second perspective and determine fill-data corresponding to the occluded regions. The processed image data may be generated by combining the warped image data and the fill-data.
    Type: Grant
    Filed: June 23, 2021
    Date of Patent: May 21, 2024
    Assignee: Apple Inc.
    Inventors: Jim C. Chou, Jian Zhou
  • Patent number: 11978372
    Abstract: This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for synchronized dual eye variable refresh rate update for a VR display. A display processor obtains an indication of a synchronous flush or an asynchronous flush with respect to a first DPU and/or a second DPU. The display processor determines whether a first flush operation and/or a second flush operation is available at a time instance, where the first flush operation and the second flush operation are associated with the first DPU and/or the second DPU. The display processor performs, based on a VSync instance, the first flush operation and/or the second flush operation based on whether the first flush operation and/or the second flush operation are available at the time instance and based on the indication of the synchronous flush or the asynchronous flush.
    Type: Grant
    Filed: May 16, 2023
    Date of Patent: May 7, 2024
    Assignee: QUALCOMM Incorporated
    Inventors: Sreekanth Modaikkal, Kumar Saurabh, Kalyan Thota, Vishnuvardhan Prodduturi, Chun Wang
  • Patent number: 11977319
    Abstract: A device for image capture comprises a memory and one or more processors coupled to the memory and configured to: receive, during a preview mode or a recording, a first image, generate a first saliency map indicative of relative saliency of different regions within the first image, wherein the relative saliency of the different regions is indicative of a likelihood of attracting viewer gaze, generate one or more additional images based on manipulating pixels in the first image, generate one or more additional saliency maps indicative of relative saliency of different regions within the one or more additional images, and determine, during the preview mode or the recording, a camera setting based on the first saliency map and the one or more additional saliency maps.
    Type: Grant
    Filed: September 21, 2021
    Date of Patent: May 7, 2024
    Assignee: QUALCOMM Incorporated
    Inventors: Micha Galor Gluskin, Ying Noyes, Wenbin Wang, Lee-Kang Liu, Balakrishna Mandadi, Yiqian Wang, Nan Cui
  • Patent number: 11978233
    Abstract: A system and method include receiving target image data associated with a target coating. A feature extraction analysis process is applied to the target image data to determine a target image feature. The feature extraction analysis process includes dividing the target image into sub-images which contains a plurality of target pixels. A machine learning model identifies one or more types of flakes present in the target coating using target pixel features.
    Type: Grant
    Filed: December 16, 2020
    Date of Patent: May 7, 2024
    Assignee: AXALTA COATING SYSTEMS IP CO., LLC
    Inventors: Larry E. Steenhoek, Dominic V. Poerio
  • Patent number: 11967002
    Abstract: A method for anonymizing a digital colour image comprising obtaining the digital colour image, and applying a linear random function to a respective colour vector representing colour components of a respective pixel of the digital colour image to obtain a monochrome image. The linear random function varies over the pixels of the digital colour image, and is further dependent on at least one random parameter.
    Type: Grant
    Filed: June 17, 2021
    Date of Patent: April 23, 2024
    Assignee: AXIS AB
    Inventors: Carl-Axel Alm, Håkan Ardö, Raphael Teller, Song Yuan, Tim Borglund
  • Patent number: 11961450
    Abstract: In a display controller, a standard information acquisition unit acquires at least one of a luminance characteristic and a color gamut of a standard display panel. A luminance information storage unit of an output adjustment unit stores a measurement value of a luminance characteristic of a panel of a displaying destination. A luminance range adjustment unit gradually adjusts a luminance range for an image to be a luminance range same as that of the standard display panel. A color gamut information storage unit stores a measurement value of a color gamut of the panel of the displaying destination. A color adjustment unit adjusts a pixel value of an image on the basis of the color gamut such that the image is displayed in a color same as that on the standard display panel.
    Type: Grant
    Filed: September 28, 2020
    Date of Patent: April 16, 2024
    Assignee: Sony Interactive Entertainment Inc.
    Inventor: Shoichi Ikenoue
  • Patent number: 11954825
    Abstract: An image processing method for an image processing device according to an embodiment of the present invention comprises the steps of: obtaining a first RGB image by means of an RGB camera; extracting a reflection component from the first RGB image; obtaining a TOF IR image by means of a TOF camera; and obtaining a second RGB image by calculating the reflection component of the first RGB image and the TOF IR image, wherein the TOF IR image is an amplitude or intensity image generated from an IR image with respect to four phases.
    Type: Grant
    Filed: August 27, 2019
    Date of Patent: April 9, 2024
    Assignee: LG INNOTEK CO., LTD.
    Inventors: Jung Ah Park, Seon Hee Park
  • Patent number: 11940328
    Abstract: The present invention relates to a color control system for controlling, in real time, the color of an article positioned on a moving carrier. The system comprises: an illuminating device configured to illuminate the moving article in successive illuminating cycles, each illuminating cycle comprising successively generating, at a given rate, a given number of lines of light having distinct spectral bands the lines of light being substantially perpendicular to the direction of movement; a detecting device configured to detect the light back scattered by the article successively illuminated by each of the lines of light, such as to generate for each dot of a given number of dots of an observation strip perpendicular to the direction of movement, a number of signals corresponding to the light back scattered by the dot; and a processing unit configured to determine at least one value representative of the color of the dot.
    Type: Grant
    Filed: July 21, 2020
    Date of Patent: March 26, 2024
    Assignee: VEORIA
    Inventors: Philippe Copin, Dominique Martin
  • Patent number: 11935275
    Abstract: An image processing method includes: extracting, based on pixel values of a plurality of pixels of an image obtained, a plurality of first current pixels having pixel values included in a first color range including a specific color range that defines a specific color, from the plurality of pixels; excluding, in second region different from a first region including a center region of the image, (i) a low saturation pixel from the plurality of first current pixels when the number of low saturation pixels is greater than or equal to a first threshold value, and (ii) a high saturation pixel, which has a pixel value included in a high saturation range, from the plurality of first current pixels when the number of high saturation pixels is greater than or equal to a second threshold value; and outputting a plurality of second current pixels obtained as a result of the excluding.
    Type: Grant
    Filed: January 16, 2020
    Date of Patent: March 19, 2024
    Assignee: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.
    Inventor: Isao Ueda
  • Patent number: 11919531
    Abstract: One variation of a method for customizing motion characteristics of an autonomous vehicle for a user includes: accessing a baseline emotional state of the user following entry of the user into the autonomous vehicle at a first time proximal a start of a trip; during a first segment of the trip, autonomously navigating toward a destination location according to a first motion planning parameter, accessing a second emotional state of the user at a second time, detecting degradation of sentiment of the user based on differences between the baseline and second emotional states; and correlating degradation of sentiment of the user with a navigational characteristic of the autonomous vehicle; modifying the first motion planning parameter of the autonomous vehicle to deviate from the navigational characteristic; and, during a second segment of the trip, autonomously navigating toward the destination location according to the revised motion planning parameter.
    Type: Grant
    Filed: January 31, 2019
    Date of Patent: March 5, 2024
    Inventors: Carol Reiley, Fabien Blanc-Paques, Gahl Levy, Bradley Perry, Chih Hu, Vineet Jain, Chip J. Alexander, Alex Tomala
  • Patent number: 11908137
    Abstract: The present disclosure provides a method, device and equipment for identifying and detecting a macular region in a fundus image. The method includes the following steps: reading a current fundus image to be positioned and detected; detecting a macular region in the fundus image using a target detection model; when the macular region in the fundus image is not detected, detecting an optic disk region in the fundus image, and identifying and positioning the macular region based on the detected optic disk region; based on a positioning result of the macular region, extracting a macular image corresponding to the macular region from the fundus image; and performing multi-modal processing on the macular image, fusing images obtained by the multi-modal processing to obtain a fused image, and detecting whether the macular region is qualified or not according to the fused image.
    Type: Grant
    Filed: August 17, 2021
    Date of Patent: February 20, 2024
    Assignee: BEIJING ZHENHEALTH TECHNOLOGY CO., LTD.
    Inventor: Dongdong Zhang
  • Patent number: 11900507
    Abstract: A computer implemented method and system for generating a visualization of a stained wood substrate are provided. The method includes receiving an image of the wood substrate to be stained; subdividing the image i-14 into a plurality of sub-images, each sub-image corresponding to the portion of the image having a color falling in a respective one of color bands; for each sub-image, retrieving a reflectance curve representative for the wood substrate for the color corresponding to the sub-image; retrieving absorption and scattering values for the stain; for each sub-image, determining the reflectance curve representative for the stained wood based on the absorption and scattering values for the stain and the reflectance curve for the wood substrate for that sub-image; and for each pixel of each sub-image, determining a color based on the reflectance curve representative for the stained wood, resulting in a generated image of the substrate after applying the stain.
    Type: Grant
    Filed: June 29, 2020
    Date of Patent: February 13, 2024
    Assignee: Akzo Nobel Coatings International B.V.
    Inventors: Margot Julia Vlot, Peter Mark Spiers, Eric Jacob Jan Kirchner
  • Patent number: 11887219
    Abstract: A method for training an image colorization model may include inputting a training input image into a colorization model and receive a predicted color map as an output of the colorization model. A first color distance may be calculated between a first pixel of the predicted color map and a second pixel of the predicted color map. A second color distance may be calculated between a third pixel included in a ground truth color map and a fourth pixel included in the ground truth colorization map. The third pixel and fourth pixel included in the ground truth color map may spatially correspond, respectively, with the first pixel and second pixel included in the predicted color map. The method may include adjusting parameters associated with the colorization model based on a neighborhood color loss function that evaluates a difference between the first color distance and the second color distance.
    Type: Grant
    Filed: May 7, 2019
    Date of Patent: January 30, 2024
    Assignee: GOOGLE LLC
    Inventor: Noritsugu Kanazawa
  • Patent number: 11882278
    Abstract: A method for video coding, executable by a processor, includes receiving video data, determining a directionality of a sample block of the received video data, the directionality corresponding to a descriptor, applying a geometric transformation in which filter coefficients of a cross-component filter or reconstructed samples in a filter support region are rotated by a first amount based on the directionality being a first direction and rotated by a second amount based on the directionality being a second direction different from the first direction, and decoding the video data based on the applied geometric transformation.
    Type: Grant
    Filed: June 10, 2022
    Date of Patent: January 23, 2024
    Assignee: TENCENT AMERICA LLC
    Inventors: Yixin Du, Xin Zhao, Shan Liu
  • Patent number: 11867869
    Abstract: A process of constructing a micromodel for a multiple porosity system includes: drilling a well; coring the well for acquiring core plugs from the well; producing thin section images of the core plugs for acquiring a first feature of the core plugs; and transforming the thin section images to binary images.
    Type: Grant
    Filed: February 11, 2021
    Date of Patent: January 9, 2024
    Assignee: SAUDI ARABIAN OIL COMPANY
    Inventors: Amer Alanazi, Abdulkareem Alsofi, Ammar Alshehri
  • Patent number: 11871077
    Abstract: A transmission method in the present disclosure includes; obtaining an image and image signal characteristics information indicating one of an opto-electrical transfer function (OETF) or an electro-optical transfer function (EOTF) as image signal characteristics of the image; and transmitting a signal including the image and the image signal characteristics information. According to the transmission method in the present disclosure, a receiving device that received a high dynamic range (HDR) image and a standard dynamic range (SDR) image transmitted through broadcasting or the like can display these images appropriately.
    Type: Grant
    Filed: March 29, 2022
    Date of Patent: January 9, 2024
    Assignee: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.
    Inventors: Takahiro Nishi, Tadamasa Toma
  • Patent number: 11869224
    Abstract: A method and a system for establishing a light source information prediction model are provided. A plurality of training images are captured for a target object. A white object is attached on the target object. True light source information of the training images is obtained according to a color of the white object in each of the training images. A neural network model is trained according to the training images and the true light source information, and a plurality of pieces of predicted light source information is generated according to the neural network model during the training. A learning rate for training the neural network model is adaptively adjusted based on the predicted light source information.
    Type: Grant
    Filed: October 4, 2022
    Date of Patent: January 9, 2024
    Assignee: Acer Incorporated
    Inventors: Yi-Jin Huang, Chien-Hung Li, Yin-Hsong Hsu
  • Patent number: 11853713
    Abstract: Techniques that facilitate graph similarity analytics are provided. In one example, a system includes an information component and a similarity component. The information component generates a first information index indicative of a first entropy measure for a first graph-structured dataset associated with a machine learning system. The information component also generates a second information index indicative of a second entropy measure for a second graph-structured dataset associated with the machine learning system. The similarity component determines similarity between the first graph-structured dataset and the second graph-structured dataset based on a graph similarity computation associated with the first information index and the second information index.
    Type: Grant
    Filed: April 17, 2018
    Date of Patent: December 26, 2023
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Pin-Yu Chen, Lingfei Wu, Chia-Yu Chen, Yada Zhu
  • Patent number: 11849096
    Abstract: A printing system includes: a scanner configured to scan a document to generate a document image; a determination section configured to automatically determine a first color in accordance with a situation; a specification section configured to cause a user to specify a color with recommendation of the first color; and a print section configured to perform two-color copying on a medium by using a color specified by the specification section.
    Type: Grant
    Filed: July 14, 2022
    Date of Patent: December 19, 2023
    Assignee: Seiko Epson Corporation
    Inventor: Toshifumi Sakai
  • Patent number: 11840357
    Abstract: Embodiments of the present invention relate to a dual-light image integration method, a dual-light image integration device and an unmanned aerial vehicle (UAV). The method includes: receiving first image data from a first image device and second image data from a second image device; separately storing the first image data and the second image data; combining the first image data and the second image data to composite third image data; and transmitting the third image data. According to the present invention, dual-light images are processed by using different data processing methods depending on subsequent operations, which can maintain synchronization of the dual-light images during image transmission while avoiding information loss during image storage, thereby well satisfying user needs.
    Type: Grant
    Filed: May 6, 2021
    Date of Patent: December 12, 2023
    Assignee: AUTEL ROBOTICS CO., LTD.
    Inventor: Zhaozao Li
  • Patent number: 11829832
    Abstract: There is provided a barcode detection device including an image sensor and a processor. The image sensor captures an image frame of a color barcode. The processor sequentially processes every row of the image frame to find at least one color segment in each row of the image frame, categorizes color segments of a same color in one cluster according to a position relationship and a color similarity of the color segments in the image frame, and recognize a color of the pixels in one cluster according to color parameters of pixels in said one cluster.
    Type: Grant
    Filed: June 20, 2022
    Date of Patent: November 28, 2023
    Assignee: PIXART IMAGING INC.
    Inventor: Wen-Han Yao
  • Patent number: 11823416
    Abstract: A search system searches a storage where one electronic document or a plurality of electronic documents is/are stored for an electronic document that satisfies an entered search condition. The search system includes a first processor and a second processor. The first processor manages a feature relating to a color shade of the electronic document as an index of the electronic document and retrieves the electronic document that satisfies the search condition from the storage based on the index. The second processor reads an image of a document, converts a first image into a second image in accordance with designated setting including setting about the color shade, and has the second image stored in the storage as the electronic document. Managing a feature relating to a color shade of the electronic document includes registering the index based on first information on the first image and second information on the second image.
    Type: Grant
    Filed: June 4, 2021
    Date of Patent: November 21, 2023
    Assignee: KONICA MINOLTA, INC.
    Inventor: Kenya Haba
  • Patent number: 11823313
    Abstract: The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating a modified digital image by identifying patch matches within a digital image utilizing a Gaussian mixture model. For example, the systems described herein can identify sample patches and corresponding matching portions within a digital image. The systems can also identify transformations between the sample patches and the corresponding matching portions. Based on the transformations, the systems can generate a Gaussian mixture model, and the systems can modify a digital image by replacing a target region with target matching portions identified in accordance with the Gaussian mixture model.
    Type: Grant
    Filed: May 27, 2021
    Date of Patent: November 21, 2023
    Assignee: Adobe Inc.
    Inventors: Xin Sun, Sohrab Amirghodsi, Nathan Carr, Michal Lukac
  • Patent number: 11816576
    Abstract: A system for image quality assessment of non-aligned images includes a first deep path portion of a convolutional neural network having a set of parameters and a second deep path portion of the convolutional neural network sharing a set of parameters with the first deep path convolutional neural network. Weights are shared between the first and second deep path convolutional neural networks to support extraction of a same set of features in each neural network pathway. Non-aligned reference and distorted images are respectively provided to the first and second deep paths of the convolutional neural network for processing. A concatenation layer is connected to both the first and second deep paths convolutional neural network, and a fully connected layer is connected to the concatenation layer to receive input from both the first and second deep paths of the convolutional neural network, generating an image quality assessment as a linear regressor and outputting an image quality score.
    Type: Grant
    Filed: July 20, 2021
    Date of Patent: November 14, 2023
    Assignee: DEEP NORTH, INC.
    Inventors: Jinjun Wang, Yudong Liang
  • Patent number: 11810329
    Abstract: Methods and systems for determining a surface color of a target surface under an environment with an environmental light source. A plurality of images of the target surface are captured as the target surface is illuminated with a variable intensity, constant color light source and a constant intensity, constant color environmental light source, wherein the intensity of the light source on the target surface is varied by a known amount between the capturing of the images. A color feature tensor, independent of the environmental light source, is extracted from the image data, and used to infer a surface color of the target surface.
    Type: Grant
    Filed: November 19, 2020
    Date of Patent: November 7, 2023
    Assignee: Huawei Technologies Co., Ltd.
    Inventors: Yuanhao Yu, Shuhao Li, Juwei Lu, Jin Tang
  • Patent number: 11790503
    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 22, 2022
    Date of Patent: October 17, 2023
    Assignee: Imagination Technologies Limited
    Inventor: Tim Lee
  • Patent number: 11778240
    Abstract: A banding detection application generates a first set of pixel confidence values based on a first intensity difference value and first image scale associated with a first image, wherein each pixel confidence value included in the first set of pixel confidence values indicates a likelihood that a corresponding pixel included in the first image at the first image scale corresponds to banding in the first image. The banding detection application then generates a banding index corresponding to the first image based on the first set of pixel confidence values.
    Type: Grant
    Filed: June 18, 2021
    Date of Patent: October 3, 2023
    Assignee: NETFLIX, INC.
    Inventors: Pulkit Tandon, Mariana Fernandez Afonso, Joel Sole Rojals, Lukas Krasula