Raising Or Lowering The Image Resolution (e.g., Subpixel Accuracy) Patents (Class 382/299)
  • Patent number: 10839483
    Abstract: An image conversion method includes: dividing a low-resolution image to generate a plurality of low-resolution image patches having N (N being a natural number of 2 or greater) number of pixels; classifying the low-resolution image patches into a plurality of image categories; converting the low-resolution image patches by using a conversion kernel for each image patch corresponding to its image category among prestored conversion matrices, to generate high-resolution image patches having L (L being a natural number) number of pixels, which is less than the N number of pixels; and arranging the high-resolution image patches to generate a high-resolution image. According to the image conversion method, an operation amount can be reduced compared with a conventional technique, and thus the image conversion method can be implemented in hardware having low complexity. A high quality and high-resolution image can be generated regardless of characteristic information of an image signal.
    Type: Grant
    Filed: June 30, 2016
    Date of Patent: November 17, 2020
    Assignee: Korea Advanced Institute of Science and Technology
    Inventors: Munchurl Kim, Jae Seok Choi
  • Patent number: 10817983
    Abstract: In one implementation, a method includes obtaining, for a particular pixel of an image, a real pixel value and a virtual pixel value. The method includes obtaining, for the particular pixel of the image, a first alpha and a second alpha. The method includes generating, for the particular pixel of the image, a combined pixel value as a weighted average of the real pixel value and the virtual pixel value, the weighting being based on at least one of the first alpha and the second alpha.
    Type: Grant
    Filed: August 14, 2018
    Date of Patent: October 27, 2020
    Assignee: APPLE INC.
    Inventors: Pedro Manuel Da Silva Quelhas, Stefan Auer
  • Patent number: 10817984
    Abstract: The invention relates to an image preprocessing method and device for a JPEG compressed file. The method comprises the following steps: receiving a JPEG image to be processed; and de-noising the received JPEG image by using a pre-trained full convolutional network model to obtain a de-noised and resolution-improved image. The method and the device in the invention can effectively improve the definition of an image in an electronic file, thus effectively facilitate the subsequent image-based file analysis, e.g., OCR and CHART parsing.
    Type: Grant
    Filed: April 17, 2018
    Date of Patent: October 27, 2020
    Assignee: ABC FINTECH CO., LTD.
    Inventors: Zhou Yu, Yongzhi Yang, Meng Guo
  • Patent number: 10791251
    Abstract: An imaging device includes a plurality of pixels arranged in a plurality of rows, in which each of the plurality of pixels outputs a pixel signal; a row scanning unit that scans the plurality of pixels on a row basis; and an output unit that outputs first time information corresponding to a processing timing of the pixel signal on one of the plurality of rows and second time information corresponding to the pixel signal on another of the plurality of rows and having a different value from the first time information.
    Type: Grant
    Filed: May 29, 2019
    Date of Patent: September 29, 2020
    Assignee: CANON KABUSHIKI KAISHA
    Inventors: Maasa Ito, Tomoya Onishi
  • Patent number: 10789680
    Abstract: A method, device, system, and article of manufacture are provided for generating an enhanced image of a predetermined scene from images. In one embodiment, a method comprises receiving, by a computing device, a first indication associated with continuous image capture of a predetermined scene being enabled; in response to the continuous image capture being enabled, receiving, by the computing device, from an image sensor, a reference image and a first image, wherein each of the reference image and the first image is of the predetermined scene and has a first resolution; determining an estimated second resolution of an enhanced image of the predetermined scene using the reference image and the first image; and in response to the continuous image capture being disabled determining the enhanced image using the reference image and the first image, wherein the enhanced image has a second resolution that is at least the first resolution and about the estimated second resolution.
    Type: Grant
    Filed: November 19, 2018
    Date of Patent: September 29, 2020
    Assignee: Google Technology Holdings LLC
    Inventor: Michael D. McLaughlin
  • Patent number: 10776688
    Abstract: Video interpolation is used to predict one or more intermediate frames at timesteps defined between two consecutive frames. A first neural network model approximates optical flow data defining motion between the two consecutive frames. A second neural network model refines the optical flow data and predicts visibility maps for each timestep. The two consecutive frames are warped according to the refined optical flow data for each timestep to produce pairs of warped frames for each timestep. The second neural network model then fuses the pair of warped frames based on the visibility maps to produce the intermediate frame for each timestep. Artifacts caused by motion boundaries and occlusions are reduced in the predicted intermediate frames.
    Type: Grant
    Filed: October 24, 2018
    Date of Patent: September 15, 2020
    Assignee: NVIDIA Corporation
    Inventors: Huaizu Jiang, Deqing Sun, Varun Jampani
  • Patent number: 10694129
    Abstract: Systems and methods for down-scaling are provided. In one example, a method for processing image data includes determining a plurality of output pixel locations using a position value stored by a position register, using the current position value to select a center input pixel from the image data and selecting an index value, selecting a set of input pixels adjacent to the center input pixel, selecting a set of filtering coefficients from a filter coefficient lookup table using the index value, filtering the set of source input pixels to apply a respective one of the set of filtering coefficients to each of the set of source input pixels to determine an output value for the current output pixel at the current position value, and correcting chromatic aberrations in the set of source input pixels.
    Type: Grant
    Filed: April 6, 2015
    Date of Patent: June 23, 2020
    Assignee: Apple Inc.
    Inventors: Guy Cote, Simon Wolfenden Butler, Joseph Anthony Petolino, Jr., Joseph P. Bratt
  • Patent number: 10650507
    Abstract: The present disclosure discloses an image display method and apparatus in a virtual reality (VR) device. The method includes: obtaining a first image to be displayed by the VR device, an edge of a target object in the first image having an aliasing shape, the VR device being provided with an electromagnetic vibrator, and the electromagnetic vibrator being configured to control the first image to move by a first distance along a first direction; obtaining a second image after the electromagnetic vibrator vibrates, the second image being an image obtained after the first image is moved by the first distance along the first direction; performing a superimposition operation on the first image and the second image to obtain a target image, an edge of the target object in the target image changing from the aliasing shape to a smooth shape; and displaying the target image in the VR device.
    Type: Grant
    Filed: July 9, 2019
    Date of Patent: May 12, 2020
    Assignee: Tencent Technology (Shenzhen) Company Limited
    Inventor: Hao Liu
  • Patent number: 10607321
    Abstract: Techniques related to video processing with adaptive sharpness enhancement are discussed. Such techniques may include determining a detail versus noise score for a video frame based on a noise level, a motion level, an average luma value, and spatial frequency information of the video frame and enhancing sharpness of the video frame based on sharpness enhancement control parameters generated based on the detail versus noise score for the video frame.
    Type: Grant
    Filed: June 22, 2016
    Date of Patent: March 31, 2020
    Assignee: Intel Corporation
    Inventors: Teahyung Lee, Jong Dae Oh, Yi-Jen Chiu
  • Patent number: 10599930
    Abstract: Disclosed is a method and apparatus of detecting an object of interest, where the apparatus acquires an input image, sets a region of interest (ROI) in the input image, and detects the object of interest from a restoration image, having a resolution greater than a resolution of the input image, corresponding to the ROI.
    Type: Grant
    Filed: May 30, 2018
    Date of Patent: March 24, 2020
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Wonju Lee, Jaewoo Lee, Dae Hyun Ji
  • Patent number: 10547873
    Abstract: A real-time system and method for displaying video on a display are disclosed. Received compressed video data is decoded to produce an uncompressed first video frame, a first frame syntax element, an uncompressed second video frame, and a second frame syntax element. A computationally intensive process is applied to the uncompressed first video frame to produce an enhanced first video frame. A block having a portion of the enhanced first video frame from the enhanced first video frame is adaptively transferred to the uncompressed second video frame to produce an enhanced second video frame without applying the computationally intensive process to the uncompressed second video frame. The transferring is guided by the first frame syntax element and the second frame syntax element. The enhanced first video frame and the enhanced second video frame are displayed.
    Type: Grant
    Filed: March 13, 2017
    Date of Patent: January 28, 2020
    Assignee: Massachusetts Institute of Technology
    Inventors: Zhengdong Zhang, Vivienne Sze
  • Patent number: 10540749
    Abstract: An image processing system includes an input interface to receive a set of pairs of images to train an image generator, each pair includes a low-resolution image of a scene and a high-resolution image of the scene, a processor to train the image generator by solving an optimization problem to produce parameters of the image generator reducing distances between image gradients of the high-resolution images and the corresponding low-resolution images upsampled by the image generator, and an output interface to render the parameters of the image generator.
    Type: Grant
    Filed: March 29, 2018
    Date of Patent: January 21, 2020
    Assignee: Mitsubishi Electric Research Laboratories, Inc.
    Inventor: Esra Cansizoglu
  • Patent number: 10529118
    Abstract: A technique for compressing an original image is disclosed. According to the technique, an original image is obtained and a delta-encoded image is generated based on the original image. Next, a segregated image is generated based on the delta-encoded image and then the segregated image is compressed to produce a compressed image. The segregated image is generated because the segregated image may be compressed more efficiently than the original image and the delta image.
    Type: Grant
    Filed: June 29, 2018
    Date of Patent: January 7, 2020
    Assignees: Advanced Micro Devices, Inc., ATI Technologies ULC
    Inventors: Ruijin Wu, Skyler Jonathon Saleh, Christopher J. Brennan, Kei Ming Kwong, Anthony Hung-Cheong Chan
  • Patent number: 10515435
    Abstract: The disclosure discloses an apparatus for upscaling an image, a method for training the same, and a method for upscaling an image, where a convolutional neural network circuit obtains feature images of the image, a multiplexer upscales the image by integrating every n*n feature images of an input signal into a feature image with a resolution which is n times the resolution of a feature image of the image, where n is an integer greater than 1.
    Type: Grant
    Filed: November 22, 2017
    Date of Patent: December 24, 2019
    Assignee: BOE Technology Group Co., Ltd.
    Inventors: Pablo Navarrete Michelini, Hanwen Liu, Xiaoyu Li
  • Patent number: 10438332
    Abstract: Various embodiments of the present technology may comprise a method and apparatus for pixel readout. The method and apparatus may comprise a pixel array capable of reading out one or more non-rectilinear subsets of the pixel array to form a non-rectilinear primary image. The one or more non-rectilinear subsets may be selected according to a desired rectilinear output image, wherein the rectilinear output image is formed using only the one or more subsets. The primary image may then be transformed to form the rectilinear output image.
    Type: Grant
    Filed: May 18, 2017
    Date of Patent: October 8, 2019
    Assignee: SEMICONDUCTOR COMPONENTS INDUSTRIES, LLC
    Inventors: Airell Richard Clark, II, Timothy Brown, Ignacio J. Perez, Agustin B. Hernandez
  • Patent number: 10423843
    Abstract: A vision system for a vehicle includes a camera disposed at the vehicle and having a field of view exterior of the vehicle. The camera captures image data. A control includes an image processor operable to process image data captured by the camera. The control, responsive at least in part to putative detection of a traffic sign via image processing by the image processor of image data captured by the camera, enhances resolution of captured image data based at least in part on known traffic sign images to generate upscaled image data. The control compares captured image data to upscaled image data to determine and/or classify and/or identify the putatively detected traffic sign.
    Type: Grant
    Filed: February 23, 2018
    Date of Patent: September 24, 2019
    Assignee: MAGNA ELECTRONICS INC.
    Inventors: Michael Biemer, Ruediger Boegel
  • Patent number: 10410322
    Abstract: An image and/or temporal sequence of images is received. The image and/or sequence of images was captured by an image capturing device of a vehicle apparatus onboard a vehicle and was down-sampled thereby. A scale of the image(s) is determined. An up-sampling network receives the image(s) and the scale. The up-sampling network determines appropriate network weights based on the scale. Based on the appropriate network weights, the up-sampling network generates a higher resolution image having a pre-defined scale.
    Type: Grant
    Filed: April 5, 2017
    Date of Patent: September 10, 2019
    Assignee: HERE GLOBAL B.V.
    Inventors: Anirudh Viswanathan, Peter Christian
  • Patent number: 10356355
    Abstract: A display device includes an imaging unit, a display unit, and a processing unit. The processing unit determines whether or not a subject to be operated is included in a captured image. When the subject to be operated is included in the captured image, the processing unit causes an additional image and the captured image to be displayed so that they are superimposed on each other. When displaying the additional image, the processing unit sets, in the captured image, a first region in which display of a human's hand is allowed and a second region in which display of the hand is not allowed. The processing unit allows a hand imaged into the first region to be displayed as it is and does not allow a hand imaged into the second region to be displayed.
    Type: Grant
    Filed: March 13, 2018
    Date of Patent: July 16, 2019
    Assignee: KYOCERA DOCUMENT SOLUTIONS INC.
    Inventor: Hiroshi Sugihara
  • Patent number: 10325346
    Abstract: An image processor inputs a first image and outputs a downscaled second image by upscaling the second image to a third image, wherein the third image is substantially the same size as the first image size with a third resolution, associating pixels in the second image with a corresponding group of pixels from the third set of pixels, sampling a first image area at a first location of the first set of pixels to generate a first image sample, sampling a second image area of the third set of pixels to generate a second image sample, measuring similarity between the image areas, generating a perceptual image value, recursively adjusting values of third set of pixels until the image perception value matches a perceptual standard value, and adjusting pixel values in the second image to a representative pixel value of each of the corresponding group of pixels.
    Type: Grant
    Filed: July 25, 2016
    Date of Patent: June 18, 2019
    Assignee: ETH-Zurich
    Inventors: Ahmet Cengiz Öztireli, Markus Gross
  • Patent number: 10306210
    Abstract: An image processing apparatus includes: an acquisition unit configured to acquire captured image data and depth map data representing a distribution of depth information of an object acquired from the captured image data; a reduction unit configured to reduce the captured image data acquired by the acquisition unit in accordance with a data amount of the depth map data; and a correction unit configured to correct the depth map data by using the reduced captured image data.
    Type: Grant
    Filed: October 27, 2014
    Date of Patent: May 28, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Shin Tanaka
  • Patent number: 10262190
    Abstract: A method, system and computer program product for recognizing a face are provided, comprising: acquiring an image for the face; detecting a set of first feature points representing detail features of the image; extracting, for each first feature point in the set of first feature points, a first descriptor describing feature information on the first feature point; acquiring, for each second feature point in a set of second feature points, a second descriptor describing feature information on the second feature point; detecting matched feature point pairs between the set of first feature points and the set of second feature points, based on the first descriptor and the second descriptor; calculating the number of the matched feature point pairs; and recognizing the image as being consistent with the registered image, if the number of the matched feature point pairs is larger than a first preset threshold.
    Type: Grant
    Filed: March 26, 2015
    Date of Patent: April 16, 2019
    Assignees: BEIJING KUANGSHI TECHNOLOGY CO., LTD., PINHOLE (BEIJING) TECHNOLOGY CO., LTD.
    Inventor: Tao He
  • Patent number: 10257525
    Abstract: An apparatus comprises: a receiver configured to receive an image; and a processor coupled to the receiver and configured to: obtain pixels of the image; reorder the pixels to create reordered pixels; generate a first sub-image and a second sub-image using the reordered pixels; generate a first instruction to store the first sub-image in a first sub-image node; and generate a second instruction to store the second sub-image in a second sub-image node; and a transmitter coupled to the processor and configured to transmit the first instruction and the second instruction to a database.
    Type: Grant
    Filed: October 31, 2016
    Date of Patent: April 9, 2019
    Assignee: Futurewei Technologies, Inc.
    Inventors: John R. Sopka, Kandarp Patel, Lei Rao, Jian Li
  • Patent number: 10204428
    Abstract: According to one or more aspects of the disclosed subject matter, reconstructing 3D radio frequency tomographic images can include detecting a plurality of frequencies of a target and generating a low resolution image for each frequency. Additionally, a high frequency low resolution image can be selected from the plurality of low resolution images to be a reference image. Further, pixel values of the reference image can be obtained and the pixel values of the reference image can be compared to each of the plurality of low resolution images. The method can also include determining new features in each of the low resolution images based on the comparisons, generating a high resolution grid based on the new features determined by the comparisons, wherein the high resolution grid is generated using interpolation, performing deconvolution of the high resolution grid using a Wiener filter, and outputting a high resolution image.
    Type: Grant
    Filed: February 2, 2017
    Date of Patent: February 12, 2019
    Inventor: Muhannad Salem S. Almutiry
  • Patent number: 10181092
    Abstract: A method for reconstructing a super-resolution image, including: 1) reducing the resolution of an original high-resolution image to obtain an equal low-resolution image, respectively expressed as matrix forms yh and yl; 2) respectively conducting dictionary training on yl and yhl to obtain a low-resolution image dictionary Dl; 3) dividing the sparse representation coefficients ?l and ?hl into training sample coefficients ?l_train and ?hl_train and test sample coefficients ?l_test and ?hl_test; 4) constructing an L-layer deep learning network using a root-mean-square error as a cost function; 5) iteratively optimizing network parameters so as to minimize the cost function by using the low-resolution image sparse coefficient ?l_train as the input of the deep learning network; 6) inputting the low-resolution image sparse coefficient ?l_test as the test portion into the trained deep learning network in 5), outputting to obtain a predicted difference image sparse coefficient {circumflex over (?)}hl_test, computing
    Type: Grant
    Filed: April 6, 2017
    Date of Patent: January 15, 2019
    Assignee: WUHAN UNIVERSITY
    Inventors: Zhenfeng Shao, Lei Wang, Zhongyuan Wang, Jiajun Cai
  • Patent number: 10178373
    Abstract: Systems and methods for correcting stereo yaw of a stereoscopic image sensor pair using autofocus feedback are disclosed. A stereo depth of an object in an image is estimated from the disparity of the object between the images captured by each sensor of the image sensor pair. An autofocus depth to the object is found from the autofocus lens position. If the difference between the stereo depth and the autofocus depth is non zero, one of the images is warped and the disparity is recalculated until the stereo depth and the autofocus depth to the object is substantially the same.
    Type: Grant
    Filed: April 11, 2014
    Date of Patent: January 8, 2019
    Assignee: QUALCOMM Incorporated
    Inventors: Vikas Ramachandra, Kalin Mitkov Atanassov, Ruben Manuel Velarde
  • Patent number: 10169852
    Abstract: Systems, methods, and computer-readable media for feedback on and improving the accuracy of super-resolution imaging. In some embodiments, a low resolution image of a specimen can be obtained using a low resolution objective of a microscopy inspection system. A super-resolution image of at least a portion of the specimen can be generated from the low resolution image of the specimen using a super-resolution image simulation. Subsequently, an accuracy assessment of the super-resolution image can be identified based on one or more degrees of equivalence between the super-resolution image and one or more actually scanned high resolution images of at least a portion of one or more related specimens identified using a simulated image classifier. Based on the accuracy assessment of the super-resolution image, it can be determined whether to further process the super-resolution image. The super-resolution image can be further processed if it is determined to further process the super-resolution image.
    Type: Grant
    Filed: July 3, 2018
    Date of Patent: January 1, 2019
    Assignee: NANOTRONICS IMAGING, INC.
    Inventors: Matthew C. Putman, John B. Putman, Vadim Pinskiy, Joseph R. Succar
  • Patent number: 10117617
    Abstract: The present invention relates to systems and methods for early detection, assessment, monitoring and prevention of pathophysiological conditions originating and/or emanating from skin or localized tissues, including but not limited to acute or chronic episodes of soft tissue pathology, wound, injury, dermatological or rheumatoid condition where bio-signal patterns, biomarkers or other identifiable elements or references would deviate from baseline. Specifically, the present invention relates to methods and systems specially designed and adapted for early detection of a latent pathogenic bio-signal anomaly using multiple aggregated sensors before the anomaly would otherwise be detectable.
    Type: Grant
    Filed: October 7, 2015
    Date of Patent: November 6, 2018
    Assignee: Revealix, Inc.
    Inventors: Adrianna Cantu, Gary Johnson
  • Patent number: 10115011
    Abstract: A document type recognition apparatus includes an image region separation unit, a smoothing unit, an edge enhancement unit, a histogram creation unit, and a document type recognition unit. The image region separation unit outputs a signal indicative of each region obtained by separating an input image into a character region and a pattern region. The smoothing unit performs smoothing processing to remove halftone dots of a particular number of lines or greater in the pattern region of the input image. The edge enhancement unit outputs an image subjected to edge enhancement processing depending on an amount of edge on an edge portion of the character region in the input image subjected to the smoothing processing. The histogram creation unit creates a histogram of the image subjected to the edge enhancement processing. The document type recognition unit recognizes a document type of the input image by utilizing the histogram.
    Type: Grant
    Filed: March 13, 2017
    Date of Patent: October 30, 2018
    Assignee: Ricoh Company, Ltd.
    Inventors: Satoshi Ouchi, Takuji Kamada
  • Patent number: 10043239
    Abstract: Systems and methods for generation of images of a particular type from images of a different type are disclosed. In an embodiment, an agricultural intelligence computer system receives a first plurality of images of a first type and a second plurality of images of a second type. The first and second types may refer to variances in resolution, frequency ranges of frequency bands, and/or types of frequency bands used to generate the images. Based on the first plurality of images and the second plurality of images, the agricultural intelligence computer system generates a feature set dictionary comprising mappings from features of the first plurality of images to features of the second plurality of images. When the agricultural intelligence computer system receives a particular image of the first type, the agricultural intelligence computer system uses the received image and the feature set dictionary to generate an image of the second type.
    Type: Grant
    Filed: November 21, 2016
    Date of Patent: August 7, 2018
    Assignee: The Climate Corporation
    Inventor: Gardar Johannesson
  • Patent number: 10044946
    Abstract: There is provided for an embodiment a method for enabling improved analysis and interpretation of associated image data in an infrared (IR) image and a visible light (VL) image depicting a real world scene, captured using a thermography arrangement comprising an IR imaging system and a VL imaging system, the method comprising: capturing an IR image depicting the scene, having a first field of view (FOV); capturing a VL image depicting the scene, having a second FOV; processing at least one of the VL image and the IR image such that the FOV represented in the VL image substantially corresponds to the FOV represented in the IR image; associating the resulting IR and VL images to provide associated images; and enabling a user to access the associated images for display, wherein analysis and interpretation of the associated images, having image pair content, is intuitive as the resulting VL image and the resulting IR image after associating represent the same FOV.
    Type: Grant
    Filed: September 30, 2014
    Date of Patent: August 7, 2018
    Assignee: FLIR SYSTEMS AB
    Inventors: Katrin Strandemar, Björn Roth, Mats Ahlström
  • Patent number: 10026201
    Abstract: An image classifying method includes the following operations: reducing an order of a color of a first image to generate a first order reduction image, wherein the first order reduction image includes several first image blocks; obtaining a second order reduction image from a database, wherein the second order reduction image includes several second image blocks; calculating several block color difference values between the first order reduction image and the second order reduction image respectively according to differences between a color value of each of the first image blocks and a color value of each of the second image blocks; and determining whether or not the first image belongs to a same category as the second order reduction image according to the block color difference values between the first order reduction image and the second order reduction image.
    Type: Grant
    Filed: March 26, 2017
    Date of Patent: July 17, 2018
    Assignees: Inventec (Pudong) Technology Corporation, INVENTEC CORPORATION
    Inventors: Shao-Liang Peng, Jia-Yu Juang, Wen-Ching Hu, Te-Yi Wu
  • Patent number: 9998759
    Abstract: Disclosed herein are a method and apparatus for filtering a reference pixel. A method of smoothing a reference pixel may include determining whether or not to perform smoothing on a reference pixel based on the size of a transform block and information about an intra-prediction mode for the transform block and determining a smoothing method by comparing the size of the transform block with the size of a maximum transform block. Accordingly, image coding efficiency can be increased, and picture quality can be improved.
    Type: Grant
    Filed: April 3, 2017
    Date of Patent: June 12, 2018
    Assignee: Research & Business Foundation Sungkyunkwan University
    Inventors: Byeung Woo Jeon, Ho Young Lee, Kwang Hyun Won
  • Patent number: 9984440
    Abstract: Image upscaling techniques are described. These techniques may include use of iterative and adjustment upscaling techniques to upscale an input image. A variety of functionality may be incorporated as part of these techniques, examples of which include content-adaptive patch finding techniques that may be employed to give preference to an in-place patch to minimize structure distortion. In another example, content metric techniques may be employed to assign weights for combining patches. In a further example, algorithm parameters may be adapted with respect to algorithm iterations, which may be performed to increase efficiency of computing device resource utilization and speed of performance. For instance, algorithm parameters may be adapted to enforce a minimum and/or maximum number to iterations, cease iterations for image sizes over a threshold amount, set sampling step sizes for patches, employ techniques based on color channels (which may include independence and joint processing techniques), and so on.
    Type: Grant
    Filed: June 18, 2013
    Date of Patent: May 29, 2018
    Assignee: ADOBE SYSTEMS INCORPORATED
    Inventors: Zhe Lin, Jianchao Yang, Scott D. Cohen
  • Patent number: 9972072
    Abstract: In order to reduce the possibility of damaging a signal component of the original image during the noise reduction of an image created by pan-sharpen processing or the like based on a plurality of images of the same image object, which are taken simultaneously with different resolutions, a noise reduction apparatus according to the present invention includes a multiresolution decomposition means that performs multiresolution decomposition on a first image inputted to obtain components having a prescribed first resolution, the first image having a prescribed resolution, the prescribed first resolution being lower than the prescribed resolution of a second image inputted, the second image being captured simultaneously with the first image, the first image and the second image being images of a same object, a low resolution component compensation means that compensates at least one decomposition component created by the decomposition with use of the second image, and an image reconfiguration means that replaces
    Type: Grant
    Filed: August 20, 2014
    Date of Patent: May 15, 2018
    Assignee: NEC CORPORATION
    Inventor: Akira Monden
  • Patent number: 9886769
    Abstract: Disclosed herein according to one embodiment is an object tracker for tracking an object. The object tracker includes a depth camera for acquiring a 3D depth map and a low-resolution 2D image of the object, and an image camera for acquiring a high-resolution 2D image of the object. A processor is in communication with the depth camera and the image camera. The processor is configured to: identify a region of interest within the 3D depth map; identify an approximate object silhouette within the low-resolution 2D image using information about the region of interest from the 3D depth map; identify the approximate object silhouette in the high-resolution 2D image using information about the approximate object silhouette from the low-resolution 2D image; generate a refined object silhouette within the high-resolution 2D image using a region segmentation process; and track the object using the refined object silhouette.
    Type: Grant
    Filed: December 9, 2015
    Date of Patent: February 6, 2018
    Inventors: Jamie Douglas Tremaine, Oliver Pilgrim Hinds, Brian Frederick Rossa
  • Patent number: 9875523
    Abstract: An image processing apparatus and image processing method enlarge an input image (Din) to generate a low-resolution enlarged image (D101). Depending on a result of identification of the pattern of the input image (Din), coefficient data (D108) for conversion to a high-resolution are selected, and a feature component (D102H) of a low resolution is converted to a feature component (D103H) of a high resolution. Decision as to whether or not the pattern of a local region of the input image (Din) is flat is made. If it is flat, the coefficient data are so selected that no substantial alteration is made to pixel values in a high-resolution conversion unit (103). It is possible to reduce the circuit size and the memory capacity, and to improve the noise immunity, and achieve conversion to a high resolution suitable for implementation by hardware.
    Type: Grant
    Filed: July 10, 2014
    Date of Patent: January 23, 2018
    Assignee: MITSUBISHI ELECTRIC CORPORATION
    Inventors: Yoshitaka Toyoda, Kohei Kurihara, Shotaro Moriya, Takeo Fujita, Narihiro Matoba
  • Patent number: 9832455
    Abstract: An automatic range finding method is applied to measure a distance between a stereo camera and a reference plane. The automatic range finding method includes acquiring a disparity-map video by the stereo camera facing the reference plane, analyzing the disparity-map video to generate a depth histogram, selecting a pixel group having an amount greater than a threshold from the depth histogram, calculating the distance between the stereo camera and the reference plane by weight transformation of the pixel group, and applying a coarse-to-fine computation for the disparity-map video.
    Type: Grant
    Filed: July 19, 2015
    Date of Patent: November 28, 2017
    Assignee: VIVOTEK INC.
    Inventors: Cheng-Chieh Liu, Shih-Ming Huang
  • Patent number: 9792664
    Abstract: This disclosure relates generally to video analysis, and more particularly to systems and methods for mapping object co-ordinates from a video frame view to real world co-ordinates using perspective transformation. In one embodiment, a processor-implemented video frame coordinate transformation method is disclosed. The method may include obtaining an image from an image capture device and identifying, via one or more hardware processors, an object depicted in the image. Further, the method may include determining image-frame object coordinates for the object, and selecting one of a plurality of coordinate transformation matrices associated with the image capture device, based on the image-frame object coordinates for the object.
    Type: Grant
    Filed: March 18, 2015
    Date of Patent: October 17, 2017
    Assignee: WIPRO LIMITED
    Inventors: Akash Gupta, Rinku Vatnani, Krupal Chandresh Modi, Akbar Abdulmalik Ladak
  • Patent number: 9786062
    Abstract: The disclosure provides an approach for estimating depth in a scene. According to one aspect, regions where the depth estimation is expected to perform well may first be identified in full-resolution epipolar-plane images (EPIs) generated from a plurality of images of the scene. Depth estimates for EPI-pixels with high edge confidence are determined by testing a number of discrete depth hypotheses and picking depths that lead to highest color density of sampled EPI-pixels. The depth estimate may also be propagated throughout the EPIs. This process of depth estimation and propagation may be iterated until all EPI-pixels with high edge confidence have been processed, and all EPIs may also be processed in this manner. The EPIs are then iteratively downsampled to coarser resolutions, at which edge confidence for EPI-pixels not yet processed are determined, depth estimates of EPI-pixels with high edge confidence made, and depth estimates propagated throughout the EPIs.
    Type: Grant
    Filed: July 17, 2013
    Date of Patent: October 10, 2017
    Assignees: Disney Enterprises, Inc., ETH Zurich (Eidgenoessische Technische Hochschule Zurich)
    Inventors: Alexander Sorkine-Hornung, Changil Kim, Henning Zimmer, Yael Pritch, Markus Gross
  • Patent number: 9692931
    Abstract: In executing a job for combining a plurality of images and outputting the combined image, an information processing apparatus stores log information to allow a system administrator to later identify what image has been output while effectively saving the capacity of a storage device to be used.
    Type: Grant
    Filed: October 24, 2011
    Date of Patent: June 27, 2017
    Assignee: Canon Kabushiki Kaisha
    Inventor: Yasuhiro Takahashi
  • Patent number: 9693012
    Abstract: Super-resolution of dynamic scenes using sampling rate diversity, processes and systems thereof are provided. The method implementing the processes includes: in a first stage, super-resolving secondary low-resolution (LR) images using a set of primary LR images to create LR dictionaries to represent polyphase components (PPCs) of high resolution (HR) patches of images; and, in a second stage, reverting to a single frame super-resolution (SR) applied to each frame which comprises an entire image, using the HR dictionaries extracted from the super-resolved sequence obtain in the first stage.
    Type: Grant
    Filed: February 11, 2016
    Date of Patent: June 27, 2017
    Assignee: KING ABDULAZIZ CITY FOR SCIENCE AND TECHNOLOGY
    Inventors: Faisal M. al-Salem, Andrew E. Yagle
  • Patent number: 9651766
    Abstract: A microscopy method for generating a high-resolution image (55) of a sample (2) comprising the following steps: a) the sample (2) is provided with a marker, which upon excitation emits statistically flashing luminescent radiation, or a sample (2) is used which upon excitation emits locally distributed, statistically flashing luminescent radiation; b) the sample (2) is excited to luminescence by means of structured illumination, wherein the sample is repeatedly illuminated in at least nine different illumination conditions (0.01-0.09) of the structured illumination by realizing at least three rotary positions, and at least three displacement positions per rotary position of the structured illumination; c) the luminescing sample (2) is repeatedly displayed in each of the different illumination conditions on a flat panel detector having pixels, such that an image sequence (44.01-44.09) is obtained for each of the different illumination conditions (0.01-0.
    Type: Grant
    Filed: May 22, 2012
    Date of Patent: May 16, 2017
    Assignee: CARL ZEISS MICROSCOPY GMBH
    Inventors: Ingo Kleppe, Yauheni Novikau
  • Patent number: 9633043
    Abstract: Systems, methods, and media for storing a digital image using the Digital Imaging and Communication in Medicine (DICOM) standard. In an embodiment, a digital image at a first resolution is divided into a plurality of regions. Each of the plurality of regions is stored as a separate DICOM image file. In addition, each of the DICOM image files is associated with a DICOM series representing the digital image at the first resolution.
    Type: Grant
    Filed: April 4, 2016
    Date of Patent: April 25, 2017
    Assignee: LEICA BIOSYSTEMS IMAGING, INC.
    Inventor: Ole Eichhorn
  • Patent number: 9626761
    Abstract: Disclosed is a sampling method for estimating a homography matrix. This sampling method, for estimating a homography matrix that represents conversion correlations between pluralities of images by means of Constraint Satisfaction-Random Sample Consensus (CS-RANSAC), includes the steps of: sampling to divide an input image into a form of grids (N by N), select features, which are used for calculating a homography matrix, from features, which are abstracted from the input image, by means of a random sampling, and inspect whether the features selected by the random sampling satisfy predefined constraints; and executing model estimation to calculate the homography matrix from the features only if the selected features satisfy the constraints.
    Type: Grant
    Filed: April 7, 2015
    Date of Patent: April 18, 2017
    Assignee: INHA INDUSTRY PARTNERSHIP INSTITUTE
    Inventor: Geun Sik Jo
  • Patent number: 9619870
    Abstract: Techniques are disclosed for removing blur from a single image by accumulating a blur kernel estimation across several scale levels of the image and balancing the contributions of the different scales to the estimation depending on the noise level in each observation. In particular, a set of observations can be obtained by applying a set of variable scale filters to a single blurry image at different scale levels. A single blur kernel can be estimated across all scales from the set of observations and used to obtain a single latent sharp image. The estimation at a large scale level is refined using the observations at successively smaller scale levels. The filtered observations may be weighted during the estimation to balance the contributions of each scale to the estimation of the blur kernel. A deblurred digital image is recovered by deconvolving the blurry digital image using the estimated blur kernel.
    Type: Grant
    Filed: July 26, 2016
    Date of Patent: April 11, 2017
    Assignee: Adobe Systems Incorporated
    Inventor: Jianchao Yang
  • Patent number: 9584699
    Abstract: An image processing apparatus includes a first screen processing unit that performs first screen processing using a first screen angle on a line region of a character, a second screen processing unit that performs second screen processing using a second screen angle on at least an outline region out of the line region, the second screen angle being different from the first screen angle, and a composition unit that performs composition of a processing result of the first screen processing and a processing result of the second screen processing, on at least the outline region out of the line region.
    Type: Grant
    Filed: January 25, 2012
    Date of Patent: February 28, 2017
    Assignee: Konica Minolta, Inc.
    Inventors: Tomohiro Yamaguchi, Hideyuki Toriyama
  • Patent number: 9558532
    Abstract: An image decoder includes a base layer to decode at least a portion of an encoded video stream into a first image having a first image format. The image decoder can generate a color space prediction by scaling a color space of the first image from the first image format into a color space corresponding to a second image format. The image decoder includes an enhancement layer to decode the encoded video stream to generate a second image in the second image format based, at least in part, on the color space prediction.
    Type: Grant
    Filed: June 12, 2015
    Date of Patent: January 31, 2017
    Assignee: SHARP LABORATORIES OF AMERICA, INC.
    Inventors: Mohammad Aghagolzadeh, Christopher A. Segall
  • Patent number: 9467551
    Abstract: The present invention relates to a mobile terminal enabling a user to more conveniently use the terminal and a method of controlling therefor. According to at least one of embodiments of the present invention, it is able to provide a user with a control method capable of easily and efficiently sharing an image with a different mobile terminal using tag information which is stored together with the image.
    Type: Grant
    Filed: January 16, 2015
    Date of Patent: October 11, 2016
    Assignee: LG Electronics Inc.
    Inventors: Hyunkyu Kim, Yoosang Won
  • Patent number: 9445025
    Abstract: An embodiment of a method for resolving features on a probe array is described that, comprises acquiring a plurality of micro-shifted images of a region of a probe array; reconstructing an image of the probe array using the micro-shifted images; and deriving intensity values for one or more probe features disposed on the probe array from the reconstructed image.
    Type: Grant
    Filed: August 23, 2013
    Date of Patent: September 13, 2016
    Assignee: Affymetrix, Inc.
    Inventors: Michael D. Kaiser, David R. Smith
  • Patent number: 9442583
    Abstract: An optical mouse apparatus includes a light source circuit, a sensing circuit, and a processing circuit. The light source circuit is used for generating and emitting a light signal onto a surface so as to generate a light reflected signal. The sensing circuit is used for estimating an image offset of the optical mouse apparatus. The processing circuit is coupled to the light source circuit and the sensing circuit and used for generating and outputting a control signal to a terminal according to the image offset outputted by the sensing circuit. The sensing circuit is further used for detecting at least one of a moving speed or an offset direction of the image offset of the optical mouse apparatus, so as to dynamically determine whether to compress data of the image offset outputted to the processing circuit, for reducing data amount read by the processing circuit.
    Type: Grant
    Filed: July 24, 2013
    Date of Patent: September 13, 2016
    Assignee: PixArt Imaging Inc.
    Inventors: Yung-Chang Lin, Tsung-Fa Wang, Ching-Lin Chung