Artifact Removal Or Suppression (e.g., Distortion Correction) Patents (Class 382/275)
  • Patent number: 10789686
    Abstract: Supervised machine learning using neural networks is applied to denoising images rendered by MC path tracing. Specialization of neural networks may be achieved by using a modular design that allows reusing trained components in different networks and facilitates easy debugging and incremental building of complex structures. Specialization may also be achieved by using progressive neural networks. In some embodiments, training of a neural-network based denoiser may use importance sampling, where more challenging patches or patches including areas of particular interests within a training dataset are selected with higher probabilities than others. In some other embodiments, generative adversarial networks (GANs) may be used for training a machine-learning based denoiser as an alternative to using pre-defined loss functions.
    Type: Grant
    Filed: January 6, 2020
    Date of Patent: September 29, 2020
    Assignees: Pixar, Disney Enterprises, Inc.
    Inventors: Thijs Vogels, Fabrice Rousselle, Brian McWilliams, Mark Meyer, Jan Novak
  • Patent number: 10778885
    Abstract: A method and system for detecting facial expressions in digital images and applications therefore are disclosed. Analysis of a digital image determines whether or not a smile and/or blink is present on a person's face. Face recognition, and/or a pose or illumination condition determination, permits application of a specific, relatively small classifier cascade.
    Type: Grant
    Filed: April 9, 2018
    Date of Patent: September 15, 2020
    Assignee: FotoNation Limited
    Inventors: Catalina Neghina, Mihnea Gangea, Stefan Petrescu, Emilian David, Petronel Bigioi, Eric Zarakov, Eran Steinberg
  • Patent number: 10776978
    Abstract: A method is provided for the automated identification of real world objects. The invention, implementable via various means such as a processing system, method, or data structure in a recording medium such as memory or as a self-contained electronic circuit, has wide ranging applicability to numerous fields such as in a user interface for gaming systems, like Kinect, or immersive environments such as remote surgical operations, and other medical diagnostic applications. Similarly, our method can be utilized in artificial intelligence application for automated robotic identification of targets, such as drone assisted search and rescue missions, and the enablement of patent protection against unlawful replication on 3D printers.
    Type: Grant
    Filed: April 8, 2013
    Date of Patent: September 15, 2020
    Inventor: Jeffrey W. Holcomb
  • Patent number: 10776909
    Abstract: The disclosure includes: a memory section, storing a learned model and an internal parameter set in the learned model; an acquisition section, acquiring an image of an inspection object photographed under predetermined conditions; a preprocessing section, generating a predetermined preprocessing filter according to a feature value in a preprocessing image being an image of the inspection object that is acquired by the acquisition section and that includes a defect, and a feature value corresponding to the internal parameter, and generating a preprocessed image by applying the generated preprocessing filter to an inspection image being an image of the inspection object that is acquired by the acquisition section and converting the inspection image; and an inspection section, inspecting the preprocessed image for presence or absence of the defect of the inspection object by using the stored learned model.
    Type: Grant
    Filed: September 13, 2018
    Date of Patent: September 15, 2020
    Assignee: OMRON Corporation
    Inventors: Yasuyuki Ikeda, Masashi Kurita
  • Patent number: 10766342
    Abstract: A shading device comprises: a shading member formed using a dimming glass plate capable of changing light transmittance, the shading member having a plate shape; a display apparatus being capable of transmitting light and disposed on a surface of the shading member, the surface being to face an operator during use of the shading member, in such a manner that a display portion faces the operator; an image pickup device to pick up, as an image, a region which an opposite surface of the surface faces, and generate image pickup data; a data processing circuit to generate display image data to be displayed on the display portion during use of the shading member, based on the image pickup data generated by the image pickup device; and a switch to change light transmittance of the dimming glass plate.
    Type: Grant
    Filed: April 14, 2017
    Date of Patent: September 8, 2020
    Assignee: Sakai Display Products Corporation
    Inventor: Katsuhiko Kishimoto
  • Patent number: 10755391
    Abstract: Digital image completion by learning generation and patch matching jointly is described. Initially, a digital image having at least one hole is received. This holey digital image is provided as input to an image completer formed with a dual-stage framework that combines a coarse image neural network and an image refinement network. The coarse image neural network generates a coarse prediction of imagery for filling the holes of the holey digital image. The image refinement network receives the coarse prediction as input, refines the coarse prediction, and outputs a filled digital image having refined imagery that fills these holes. The image refinement network generates refined imagery using a patch matching technique, which includes leveraging information corresponding to patches of known pixels for filtering patches generated based on the coarse prediction. Based on this, the image completer outputs the filled digital image with the refined imagery.
    Type: Grant
    Filed: May 15, 2018
    Date of Patent: August 25, 2020
    Assignee: Adobe Inc.
    Inventors: Zhe Lin, Xin Lu, Xiaohui Shen, Jimei Yang, Jiahui Yu
  • Patent number: 10755173
    Abstract: Methods and systems are provided for deblurring images. A neural network is trained where the training includes selecting a central training image from a sequence of blurred images. An earlier training image and a later training image are selected based on the earlier training image preceding the central training image in the sequence and the later training image following the central training image in the sequence and based on proximity of the images to the central training image in the sequence. A training output image is generated by the neural network from the central training image, the earlier training image, and the later training image. Similarity is evaluated between the training output image and a reference image. The neural network is modified based on the evaluated similarity. The trained neural network is used to generate a deblurred output image from a blurry input image.
    Type: Grant
    Filed: December 4, 2019
    Date of Patent: August 25, 2020
    Assignee: ADOBE INC.
    Inventors: Oliver Wang, Jue Wang, Shuochen Su
  • Patent number: 10726525
    Abstract: An image denoising neural network training architecture includes an image denoising neural network and a clean data neural network, and the image denoising neural network and clean data neural network share information between each other.
    Type: Grant
    Filed: March 20, 2018
    Date of Patent: July 28, 2020
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Mostafa El-Khamy, Igor Fedorov, Jungwon Lee
  • Patent number: 10682116
    Abstract: An X-ray sensing apparatus includes a first photodiode array for imaging a first area, a second photodiode array for imaging a second area that overlaps a portion of the first area, and a light-blocking layer coupled to the first photodiode array that prevents at least a portion of visible light emitted by a scintillator layer of the X-ray sensing apparatus from reaching the second photodiode array. The light-blocking layer includes a first feature that is imagable by the second photodiode array and indicates a position along a first direction and a second feature that is imagable by the second photodiode array and indicates a position along a second direction that is different than the first direction.
    Type: Grant
    Filed: November 27, 2017
    Date of Patent: June 16, 2020
    Assignee: VAREX IMAGING CORPORATION
    Inventors: Ivan Mollov, Eric Amusin, Arundhuti Ganguly
  • Patent number: 10682870
    Abstract: A conveyed object detector includes first and second image obtaining units disposed at first and second positions different in a conveyance direction, to image a conveyed object to obtain first and second image data; respectively; a recognition unit to recognize an object adhering to the first and second image obtaining units based on imaging at the first and second positions to generate first and second stain data, respectively; a removal unit to remove the first and second stain data from the first and second image data, respectively; and a calculator to generate at least one of a position, a movement amount, and a moving speed of the conveyed object based on first and second corrected image data. Each of the first and second image obtaining units include a light source, an area sensor, and an optical element disposed between the area sensor and the conveyed object.
    Type: Grant
    Filed: June 8, 2017
    Date of Patent: June 16, 2020
    Assignee: RICOH COMPANY, LTD.
    Inventors: Katsuhiro Tobita, Koichi Kudo
  • Patent number: 10666934
    Abstract: A camera automatic calibration method includes determining a camera to be recalibrated; and determining a point-to-point matching relationship between a first projection point set and a first collection point set. The first projection point set is formed in a camera coordinate system when first spatial coordinates, formed by capturing a plurality of test points using cameras other than the camera to be recalibrated, are projected onto the camera to be recalibrated, and the first collection point set is formed by capturing the test points using the camera to be recalibrated. The method includes calculating a distance difference between each point in the first projection point set and a matching point in the first collection point set according to the point-to-point matching relationship; obtaining a new calibration parameter of the camera to be recalibrated; and updating the current calibration parameter of the camera to be recalibrated with the new calibration parameter.
    Type: Grant
    Filed: May 17, 2019
    Date of Patent: May 26, 2020
    Assignee: SHENZHEN REALIS MULTIMEDIA TECHNOLOGY CO., LTD.
    Inventors: Yue Wang, Xiaoqin Zhao, Qiuzi Xu
  • Patent number: 10650155
    Abstract: A content management system allows a user to create a collection folder to which a submitting user can add content items without being able to access content items added to the folder by other submitting users. A collection folder is created in a namespace of a collecting user and folder is made available to multiple submitting users to allow the submitting users to add items to the folder. When a submitting user first request to store a content item in the collection folder, the content management system creates a sub-folder associated with the submitting user in the collection folder and stores the content item in the sub-folder. The submitting user is given rights to the sub-folder, but is not given rights to sub-folders created for other submitting users.
    Type: Grant
    Filed: July 27, 2016
    Date of Patent: May 12, 2020
    Assignee: Dropbox, Inc.
    Inventors: Aaron Staley, Aditi Jain, Aisha Ferrazares, Alicia Chen, Ashish Warty, John Adams, Joseph Hui, Kathryn Siegel, Lennart Jansson, Matteus Pan, Rob Baesman, Siyao Xu
  • Patent number: 10652487
    Abstract: An image processing apparatus of an embodiment includes: a distortion correction circuit configured to perform a correction operation to a plurality of pixels composing an input image; a plurality of output buffers layered to two or more stages configured to receive an output of the distortion correction circuit, and perform output for each transmission block which is a set of pixels with the consecutive corrected pixel positions; and a controller configured to write an output pixel of the distortion correction circuit in the first-stage output buffer, sequentially transfer the written pixel to a post-stage output buffer, and cause output buffers at respective stages to store pixels of sub-blocks into which the transmission block is divided.
    Type: Grant
    Filed: September 5, 2018
    Date of Patent: May 12, 2020
    Assignees: Kabushiki Kaisha Toshiba, Toshiba Electronic Devices & Storage Corporation
    Inventor: Ryuji Hada
  • Patent number: 10643096
    Abstract: There is provided with an image processing apparatus. An obtaining unit obtains a video with consecutive frame images. A dividing unit divides a frame image of interest into a plurality of divided regions by reference to information of divided regions previously stored in a storage unit. A determining unit determines whether or not a moving object is included in a divided region of interest in the frame image of interest. An updating unit switches whether or not to update information of the divided region of interest stored in the storage unit with information of the divided region of interest of the frame image of interest, according to whether or not a moving object is included in the divided region of interest in the frame image of interest.
    Type: Grant
    Filed: September 21, 2017
    Date of Patent: May 5, 2020
    Assignee: Canon Kabushiki Kaisha
    Inventors: Hiroshi Tojo, Masahiro Ariizumi
  • Patent number: 10621752
    Abstract: A method for camera calibration, performed by a processing unit, at least contains: controlling a camera module to obtain a shooting image with a distortion; generating reference position information of a plurality of pixels of the shooting image, wherein the reference position information includes position information of the plurality of pixels after eliminating the distortion; storing the reference position information in a lookup table, wherein the lookup table contains entries and each entry stores reference position of one pixel; and adjusting an output from the camera module by using the lookup table.
    Type: Grant
    Filed: November 13, 2017
    Date of Patent: April 14, 2020
    Assignee: SHANGHAI ZHAOXIN SEMICONDUCTOR CO., LTD.
    Inventors: Xu Wang, Feifei Yang, Yalong Jiang
  • Patent number: 10614235
    Abstract: A content management system allows a user to create a collection folder to which a submitting user can add content items without being able to access content items added to the folder by other submitting users. A collection folder is created in a namespace of a collecting user and folder is made available to multiple submitting users to allow the submitting users to add items to the folder. When a submitting user first request to store a content item in the collection folder, the content management system creates a sub-folder associated with the submitting user in the collection folder and stores the content item in the sub-folder. The submitting user is given rights to the sub-folder, but is not given rights to sub-folders created for other submitting users.
    Type: Grant
    Filed: July 27, 2016
    Date of Patent: April 7, 2020
    Assignee: Dropbox, Inc.
    Inventors: Aaron Staley, Aditi Jain, Aisha Ferrazares, Alicia Chen, Ashish Warty, John Adams, Joseph Hui, Kathryn Siegel, Lennart Jansson, Matteus Pan, Rob Baesman, Siyao Xu
  • Patent number: 10607319
    Abstract: Supervised machine learning using neural networks is applied to denoising images rendered by MC path tracing. Specialization of neural networks may be achieved by using a modular design that allows reusing trained components in different networks and facilitates easy debugging and incremental building of complex structures. Specialization may also be achieved by using progressive neural networks. In some embodiments, training of a neural-network based denoiser may use importance sampling, where more challenging patches or patches including areas of particular interests within a training dataset are selected with higher probabilities than others. In some other embodiments, generative adversarial networks (GANs) may be used for training a machine-learning based denoiser as an alternative to using pre-defined loss functions.
    Type: Grant
    Filed: April 5, 2018
    Date of Patent: March 31, 2020
    Assignees: Pixar, Disney Enterprises, Inc.
    Inventors: Thijs Vogels, Fabrice Rousselle, Brian McWilliams, Mark Meyer, Jan Novak
  • Patent number: 10602077
    Abstract: An image processing method and an image processing system for eye-gaze correction are provided. The method is applicable to an image processing system having a screen and an image capturing device and includes the following steps. A user's face in front of the screen is captured by the image capturing device to generate a facial image. A head offset and an eye-gaze position of the user with respect to the screen are obtained based on the facial image so as to accordingly determine whether to correct the facial image. If yes, the facial image is corrected based on the eye-gaze position and a preset codebook to generate a corrected facial image, where the preset codebook records correction information of multiple preset eye-gaze positions.
    Type: Grant
    Filed: December 12, 2017
    Date of Patent: March 24, 2020
    Assignee: Winstron Corporation
    Inventors: Chin-Lun Lai, Jun-Horng Chen, Jie-Ci Yang, Meng-Chao Kao
  • Patent number: 10580133
    Abstract: Techniques for estimating blepharoptosis from an image of a face are disclosed. The image is captured by a camera. Histogram of Oriented Gradients and Linear Classifiers are used to predict the location of the face and eyes. An Ensemble of Regression Trees is used to detect points on each eyelid and the canthi. The location of the iris is ascertained by thresholding HLS values of individual pixels and applying a sliding window algorithm. Using regression, the eyelid shape curve is approximated. The eyelid shape curve function is used to measure the MRD1 value and distance below the limbus after detecting the Purkinje image/corneal light reflex. Finally, the intensity of blepharoptosis is estimated by categorizing the measured MRD1 and distance-from-Limbus values.
    Type: Grant
    Filed: September 24, 2018
    Date of Patent: March 3, 2020
    Inventors: Viswesh Krishna, Vrishab Krishna
  • Patent number: 10582126
    Abstract: Embodiments of the present invention relate to a method for generating a microscopy representation of a three-dimensional sample having a lateral extension in the x and y directions. The method has the following steps: a) arranging the flat three-dimensional sample on a positioner; b) recording the sample by means of an imaging device to obtain a first microscopy picture of the sample having a first section; c) altering the perspective onto the two-dimensional sample in the z direction; d) recording the sample by means of the imaging device to obtain a second microscopy picture of the sample having a second section; e) determining change information which allows drawing conclusions as to the change in perspective in the z direction, using a difference between the first and second microscopy pictures; and f) merging the first and second microscopy pictures while considering the change information to obtain the microscopy panoramic representation.
    Type: Grant
    Filed: October 14, 2016
    Date of Patent: March 3, 2020
    Assignee: Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V.
    Inventors: Christian Muenzenmayer, Alexander Gryanik, Tobias Bergen, Thomas Wittenberg
  • Patent number: 10580202
    Abstract: Techniques described herein are directed to a system and methods for generating 3D models of an object which accurately depict reflective properties of the object. To do this, an image of an object is captured and a rendered image of the object is generated from the image. The system then generates a lighting effect which approximates an effect of the actual light source on the appearance of the object when the image was captured. A number of rendered images of the object are generated using the lighting effect, each having different visual material property values. Once the rendered images have been generated, the system may compare the generated rendered images to the actual image in order to identify the rendered image which best approximates the actual image. The visual material property values associated with the best approximation are then assigned to the object.
    Type: Grant
    Filed: January 24, 2019
    Date of Patent: March 3, 2020
    Assignee: LOWE'S COMPANIES, INC.
    Inventors: Mason E. Sheffield, Oleg Alexander
  • Patent number: 10572979
    Abstract: Supervised machine learning using neural networks is applied to denoising images rendered by MC path tracing. Specialization of neural networks may be achieved by using a modular design that allows reusing trained components in different networks and facilitates easy debugging and incremental building of complex structures. Specialization may also be achieved by using progressive neural networks. In some embodiments, training of a neural-network based denoiser may use importance sampling, where more challenging patches or patches including areas of particular interests within a training dataset are selected with higher probabilities than others. In some other embodiments, generative adversarial networks (GANs) may be used for training a machine-learning based denoiser as an alternative to using pre-defined loss functions.
    Type: Grant
    Filed: April 5, 2018
    Date of Patent: February 25, 2020
    Assignees: Pixar, Disney Enterprises, Inc.
    Inventors: Thijs Vogels, Fabrice Rousselle, Brian McWilliams, Mark Meyer, Jan Novak
  • Patent number: 10572982
    Abstract: Techniques related to image distortion correction for images captured by using a wide-angle lens include homography and a lens distortion correction using a radial-ratio-based look up table.
    Type: Grant
    Filed: October 4, 2017
    Date of Patent: February 25, 2020
    Assignee: Intel Corporation
    Inventors: Aleksandar Beric, Kari Pulli, Nemanja Jankovic, Zoran Zivkovic
  • Patent number: 10521935
    Abstract: The invention relates to a method for creating a virtual dental image from a 3D volume (1) comprising volumetric image data. Firstly, a sub-volume (8, 12, 15, 18) of the 3D volume (1) is defined and then a virtual projection image (30, 41) is generated for said sub-volume (8, 12, 15, 18) from a specific X-ray imaging direction (11) by computation of the volumetric image data in said X-ray imaging direction (11).
    Type: Grant
    Filed: May 8, 2017
    Date of Patent: December 31, 2019
    Assignee: Sirona Dental Systems GmbH
    Inventor: Johannes Ulrici
  • Patent number: 10515438
    Abstract: System and method can support an image processing device. The image processing device operates to obtain a first set of characterization values, which represents a first group of pixels that are associated with a denoising pixel in an image. Also, the image processing device can obtain a second set of characterization values, which represents a second group of pixels that are associated with a denoising reference pixel. Furthermore, the image processing device operates to use the first set of characterization values and the second set of characterization values to determine a similarity between the denoising pixel and the denoising reference pixel. Then, the image processing device can calculate a denoised value for the denoising pixel based on the determined similarity between the denoising pixel and the denoising reference pixel.
    Type: Grant
    Filed: June 22, 2018
    Date of Patent: December 24, 2019
    Assignee: SZ DJI TECHNOLOGY CO., LTD.
    Inventors: Zisheng Cao, Junping Ma, Xing Chen, Mingyu Wang
  • Patent number: 10515439
    Abstract: A method of correcting an image obtained by an image acquisition device includes obtaining successive measurements, Gn, of device movement during exposure of each row of an image. An integration range, idx, is selected in proportion to an exposure time, te, for each row of the image. Accumulated measurements, Cn, of device movement for each row of an image are averaged across the integration range to provide successive filtered measurements, G, of device movement during exposure of each row of an image. The image is corrected for device movement using the filtered measurements G.
    Type: Grant
    Filed: April 2, 2018
    Date of Patent: December 24, 2019
    Assignee: FotoNation Limited
    Inventor: Piotr Stec
  • Patent number: 10489887
    Abstract: In a method for super resolution imaging, the method includes: receiving, by a processor, a low resolution image; generating, by the processor, an intermediate high resolution image having an improved resolution compared to the low resolution image; generating, by the processor, a final high resolution image based on the intermediate high resolution image and the low resolution image; and transmitting, by the processor, the final high resolution image to a display device for display thereby.
    Type: Grant
    Filed: August 7, 2017
    Date of Patent: November 26, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Mostafa El-Khamy, Jungwon Lee, Haoyu Ren
  • Patent number: 10482324
    Abstract: The invention relates to a method for analyzing a structured document likely to be deformed from a first image and a second image of the document, comprising steps of: matching first points of interest extracted in the first image with second points of interest of a reference image showing a model of the document, estimation of a first geometric transformation taking account of deformations of the structured document shown in the first image relative to the model from the matches, determination of at least one first region to be analyzed in the first image, by projection of at least one reference region of the reference image by means of the first transformation, analysis of the content of the first determined region, matching third points of interest extracted in the second image with fourth points of interest extracted in the first image, estimation, from the matches made in the preceding step, of a second geometric transformation taking account of deformations of the document shown in the second image r
    Type: Grant
    Filed: March 29, 2018
    Date of Patent: November 19, 2019
    Assignee: IDEMIA IDENTITY & SECURITY FRANCE
    Inventors: Jeremy Nicolas Laurent Dura, Laurent Patrice Rostaing, Alain Rouh
  • Patent number: 10477167
    Abstract: An image processing apparatus comprise a correction unit configured to generate a corrected image from an input image using a correction value; an image processing unit configured to generate a first image, in which a first pattern for measuring an ambient light distribution is incorporated into the input image or the corrected image, and a second image that is different from the first image; an acquisition unit configured to acquire an ambient light distribution based on captured images of a region in which the first image and the second image are displayed while the first image and the second image are switched therebetween in the same frame; and a correction value calculation unit configured to calculate the correction value based on an ambient light distribution acquired by the acquisition unit.
    Type: Grant
    Filed: November 14, 2017
    Date of Patent: November 12, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Azusa Koike
  • Patent number: 10469871
    Abstract: Representation and coding of multi-view images using tapestry encoding are described for standard and enhanced dynamic ranges compatibility. A tapestry comprises information on a tapestry image, a left-shift displacement map and a right-shift displacement map. Perspective images of a scene can be generated from the tapestry and the displacement maps. Different methods for achieving compatibility are described.
    Type: Grant
    Filed: December 10, 2015
    Date of Patent: November 5, 2019
    Assignee: Dolby Laboratories Licensing Corporation
    Inventors: Guan-Ming Su, Gregory John Ward, Timo Kunkel, Scott Daly, Samir N. Hulyalkar
  • Patent number: 10445615
    Abstract: A method and device for extracting images from PDF documents are disclosed. The method includes performing a text recognition process on a PDF document that includes one or more images. The text recognition process replaces the one or more images with a plurality of contiguous newlines. The method further includes storing a location of each of the one or more images within the PDF document based on occurrence of the plurality of contiguous newlines within the PDF document. The method includes converting each page of the PDF document to an image format in order to generate an image document corresponding to the PDF document. The method further includes extracting each of the one or more images from the image document based on the location stored for each of the one or more images within the PDF document.
    Type: Grant
    Filed: July 11, 2017
    Date of Patent: October 15, 2019
    Assignee: Wipro Limited
    Inventors: Balaji Jagan, Naveen Kumar Nanjappa
  • Patent number: 10412273
    Abstract: Various embodiments of the present disclosure may include an imaging device configured to determine appropriate conditions for updating non-uniformity correction (NUC) terms. In certain embodiments, the imaging device may determine when the imaging device is likely not in use and update NUC terms during the times when the imaging device is likely not in use. Data from various position sensors such as gyroscopes, accelerometers, global positioning system receivers, and/or other data may be used to determine when the imaging device is likely not in use. Such position sensors may be coupled to the imaging device and/or may be remote from the imaging device. In certain embodiments, while NUC terms are updated, imaging data obtained may be modified with historical data to provide usable data.
    Type: Grant
    Filed: March 6, 2018
    Date of Patent: September 10, 2019
    Assignee: FLIR SYSTEMS AB
    Inventors: Pontus H├Ąger, Katrin Strandemar
  • Patent number: 10410377
    Abstract: The invention notably relates to a computer-implemented method for compressing data representing values of a physical attribute in a predetermined space. The method comprises providing a signal that includes a mapping from leaf cells of a hierarchical subdivision of the predetermined space each onto a respective coefficient representative of a value of the physical attribute at the respective leaf cell. The method also comprises determining a discrete wavelet transform of the signal and encoding the determined discrete wavelet transform. The method provides an improved way to compress a modeled object that represents a real object.
    Type: Grant
    Filed: September 12, 2017
    Date of Patent: September 10, 2019
    Assignee: DASSAULT SYSTEMS
    Inventors: Jean-Julien Tuffreau, Malika Boulkenafed
  • Patent number: 10382652
    Abstract: According to one example, there is provided a method of generating a day/night image on a media. The method comprises obtaining an image to be printed as a front-to-back image, printing the obtained image on a first side of the media, processing the obtained image by flipping the image, applying a degree of edge removal, and applying a degree blur. The method further comprises printing the processed image on a reverse side of the media, such that the first printed image and printed modified image are substantially aligned with one another.
    Type: Grant
    Filed: January 29, 2015
    Date of Patent: August 13, 2019
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: Li Qian, Xavier Domingo Reguant, Secundino Vicente Vicente
  • Patent number: 10373293
    Abstract: A first image and a second image with resolutions different from each other are generated from an image captured by an imaging unit, and the first image and the second image are subject to different types of image processing. A virtual image is generated by calculating a position and an orientation of the imaging unit based on the processed first image. A composite image is generated by combining the generated virtual image with the second image subjected to the image processing, and the generated composite image is used as a display image.
    Type: Grant
    Filed: November 1, 2017
    Date of Patent: August 6, 2019
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Akihito Taketani
  • Patent number: 10365160
    Abstract: Provided is a spectrum measurement apparatus including a light source configured to emit light to a sample; a light detector configured to receive light, which is reflected or scattered from, or transmitted through the sample, and to measure an intensity of the received light, and a processor configured to reconstruct a spectrum of the sample for calibration while adjusting a value of a spectrum reconstruction parameter in response to the light detector receiving the light and measuring the intensity of the received light, and to determine an optimal value of the spectrum reconstruction parameter based on a similarity between the reconstructed spectrum of the sample for calibration and an original spectrum of the sample for calibration.
    Type: Grant
    Filed: January 26, 2018
    Date of Patent: July 30, 2019
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Hyo Sun Hwang, So Young Lee, Jae Wook Shim
  • Patent number: 10319079
    Abstract: Methods and devices for reducing noise in an image may include receiving an in focus image and at least one out of focus image of a scene, wherein the out of focus image has a second value of at least one focus-related parameter offset from a first value of the at least one focus-related parameter used for the in focus image. The methods and devices may include estimating a noise model of noise in at least a section of the out of focus image, and determining at least one parameter value for a filter based on the noise model. The methods and devices may include generating a noise-reduced image by applying the filter with the at least one parameter value to the in focus image to reduce at least part of the noise from at least a corresponding section of the in focus image.
    Type: Grant
    Filed: June 30, 2017
    Date of Patent: June 11, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventor: Sudhanshu Sohoni
  • Patent number: 10311605
    Abstract: Provided are an iterative image reconstruction method, an iterative image reconstruction program, and a tomography apparatus capable of effectively performing image reconstruction by shorting computation time when performing image reconstruction using an iterative method. In this iterative image reconstruction method, in cases where the image quality after image reconstruction is insufficient when the image was obtained with the number of iterations of 100 times in the first image reconstruction processing, when resuming the image reconstruction, the number of iterations and the state variables at the end of the reconstruction in which the number of iterations is 100 times are read, and then the image reconstruction is resumed.
    Type: Grant
    Filed: September 15, 2017
    Date of Patent: June 4, 2019
    Assignee: Shimadzu Corporation
    Inventor: Kenta Chinomi
  • Patent number: 10311552
    Abstract: The present disclosure relates to using a neural network to efficiently denoise images that were generated by a ray tracer. The neural network can be trained using noisy images generated with noisy samples and corresponding denoised or high-sampled images (e.g., many random samples). An input feature to the neural network can include color from pixels of an image. Other input features to the neural network, which would not be known in normal image processing, can include shading normal, depth, albedo, and other characteristics available from a computer-generated scene. After the neural network is trained, a noisy image that the neural network has not seen before can have noise removed without needing manual intervention.
    Type: Grant
    Filed: June 22, 2017
    Date of Patent: June 4, 2019
    Assignee: Pixar
    Inventors: Mark Meyer, Anthony DeRose, Steve Bako
  • Patent number: 10304908
    Abstract: The present disclosure relates to a method and apparatus for image processing, comprising: transforming RGB luminance input values of each of pixels in an image into coordinate values in a uniform color space; moving the coordinates of each of pixels in the uniform color space a setting distance based on luminous efficiencies of RGBW and a replacement ratio of W; the setting distance being set so as to satisfy that a color difference between RGB luminance values transformed from the moved coordinate values in the uniform color space and the respective RGB luminance input values of each of pixels is less than a preset value, in order to maintain image quality; and the setting distance being set so as to satisfy that the minimum of the transformed RGB luminance values is greater than the minimum of the RGB luminance input values. In this way, power consumption is reduced.
    Type: Grant
    Filed: August 22, 2016
    Date of Patent: May 28, 2019
    Assignee: BOE TECHNOLOGY GROUP CO., LTD.
    Inventor: Szuheng Tseng
  • Patent number: 10291844
    Abstract: An image processing apparatus includes: an image storage unit storing a first image affected by aberration of an optical system; a position information generation unit generating position information about a pixel of the first image corresponding to a scanned target pixel on the basis of position information about the target pixel scanned in the predetermined order and a distortion aberration table; an image output unit outputting a first image in which distortion aberration correction is performed in units of one pixel based on integer information about the position information generated by the position information generation unit; a first aberration correction unit, using fractional part information about the position information, correcting phase shift caused by distortion aberration for each pixel of the first image; and a second aberration correction unit generating the second image by correcting aberration other than distortion aberration in the first image.
    Type: Grant
    Filed: March 14, 2016
    Date of Patent: May 14, 2019
    Assignee: REALOP CORPORATION
    Inventor: Akihiro Okumura
  • Patent number: 10282820
    Abstract: A method includes obtaining at least one of projection data from a spectral scan or image data generated from the projection data, selecting a local reference dataset from the at least one of the projection data or the image data, determining a noise pattern for the selected reference dataset, estimating underlying local structure from the reference dataset based on the noise pattern, and restoring at least one of the projection data or the image data based on the estimated underlying local structure.
    Type: Grant
    Filed: February 11, 2014
    Date of Patent: May 7, 2019
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventor: Liran Goshen
  • Patent number: 10254594
    Abstract: Embodiments of the present disclosure relates to a liquid crystal drop filling system comprising a liquid crystal drop filling device performing a liquid crystal drop filling process to obtain a liquid crystal panel; an image acquisition device acquiring an image of the liquid crystal panel; an image processor processing the acquired image and determining a defect of the liquid crystal panel based on the processed image; and a communication module communicating an information about the defect determined by the image processor to the liquid crystal drop filling device, so that the liquid crystal drop filling device can adjust parameters of the liquid crystal drop filling process according to the information. In addition, the present disclosure further discloses a control method of a liquid crystal drop filling system.
    Type: Grant
    Filed: February 24, 2016
    Date of Patent: April 9, 2019
    Assignees: BOE TECHNOLOGY GROUP CO., LTD., HEFEI XINSHENG OPTOELECTRONICS TECHNOLOGY CO., LTD.
    Inventors: Xuebing Jiang, Ran Zhang, Jian Zhao
  • Patent number: 10244179
    Abstract: An image processing apparatus performs first image processing of processing a target image as a processing target and writing a first image as a processing result in a storage, and second image processing of reading out the first image written in the storage, processing the first image, and outputting a second image as a processing result. The first image processing and the second image processing are performed for each of a plurality of regions. Readout of the first image in the second image processing is performed in parallel with writing of the first image in the first image processing. A size of a second region defined for the first image as a processing target of the second image processing is set to be smaller than a size of a first region defined for a processing target image of the first image processing.
    Type: Grant
    Filed: June 7, 2017
    Date of Patent: March 26, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Yuya Ebata
  • Patent number: 10222959
    Abstract: A method includes formatting for display, on a visual screen, an image comprising: (1) a coordinate system, (2) a plurality of distinguishable areas within the coordinate system, each distinguishable area graphically representing a respective formula, and (3) a plurality of data points. The method also includes receiving user input comprising a modification to a particular distinguishable area. In response to receiving the user input, the method includes modifying one or more respective formulas based on the modification to the distinguishable area. For each data point, the method further includes associating the data point with one of the distinguishable areas by determining which of the modified formulas the data point falls within. The method further includes formatting for display a graphical representation of each modified formula. The method additionally includes storing the graphical representation of each modified formula for use as a modified image in future operations.
    Type: Grant
    Filed: March 31, 2016
    Date of Patent: March 5, 2019
    Assignee: CA, Inc.
    Inventors: Serguei Mankovskii, Ian Davis, Michael Godfrey
  • Patent number: 10223772
    Abstract: Methods and systems for denoising a digital image are provided. The method includes determining first and second plurality of pixel patches including respective first (p) and second (q) pixels, determining a patch distance between each pair of corresponding pixel patches in the first plurality and the second plurality of pixel patches, determining an effective distance between the first pixel (p) and the second pixel (q), repeating the above steps for the same first pixel (p) and another second pixel (q) until a predetermined number of pixels (q) in the raw digital image is processed, and then denoising the first pixel (p), including determining respective contributions of the pixels (q) into a noise reduction of the pixel (p), using respective effective distances of the pixels (q). A corresponding system is also provided. Embodiments of the invention provide computational advantages for denoising digital images.
    Type: Grant
    Filed: March 22, 2017
    Date of Patent: March 5, 2019
    Assignee: ALGOLUX INC.
    Inventors: Emmanuel Luc Julien Onzon, Nicolas Joseph Paul Robidoux
  • Patent number: 10223764
    Abstract: A method of processing a frame in a data processing system is provided, in which the frame comprises one or more frame regions that together form the frame, and each frame region is represented as one or more data values, with each data value being represented by a set of data.
    Type: Grant
    Filed: October 16, 2015
    Date of Patent: March 5, 2019
    Assignee: ARM Limited
    Inventor: Daren Croxford
  • Patent number: 10197808
    Abstract: Embodiments of the present application disclose a light field display control method and apparatus and a light field display device. The light field display control method comprises: determining a partial depth distribution sub-region of content according to at least depth distribution information of the content; and tilting a first display unit at least with respect to an original plane of a display array of a light field display device according to a display depth of field (DoF) range of the light field display device and the depth distribution sub-region, wherein the first display unit is a display unit that is in the display array and affects display of a first object, and the first object is a part, which is located in the depth distribution sub-region, of the content. The present application can improve display quality of an object, which is located in a partial depth distribution sub-region, of content to be displayed or content being displayed.
    Type: Grant
    Filed: January 4, 2017
    Date of Patent: February 5, 2019
    Assignee: Beijing Zhigu Rui Tuo Tech Co., Ltd.
    Inventors: Lin Du, Liang Zhou
  • Patent number: 10191941
    Abstract: The present invention extends to methods, systems, and computing system program products for iteratively calculating a skewness for streamed data. Embodiments of the invention include iteratively calculating one or more components of skewness in an adjusted computation window based on the one or more components of the skewness calculated for a previous computation window and then calculating the skewness based on the iteratively calculated components. Iteratively calculating skewness avoids visiting all data elements in the computation window and performing redundant computations thereby increasing calculation efficiency, saving computing resources and reducing computing system power consumption.
    Type: Grant
    Filed: December 9, 2015
    Date of Patent: January 29, 2019
    Assignee: CLOUD & STREAM GEARS LLC
    Inventor: Jizhu Lu
  • Patent number: RE47984
    Abstract: In embodiments of the invention, an apparatus may include a display comprising a plurality of pixels. The apparatus may further include a computer system coupled with the display and operable to instruct the display to display a deconvolved image corresponding to a target image, wherein when the display displays the deconvolved image while located within a near-eye range of an observer, the target image may be perceived in focus by the observer.
    Type: Grant
    Filed: March 27, 2017
    Date of Patent: May 12, 2020
    Assignee: NVIDIA CORPORATION
    Inventors: David Patrick Luebke, Douglas Lanman, Thomas F. Fox, Gerrit Slavenburg