Image Filter Patents (Class 382/260)
  • Patent number: 10657632
    Abstract: The invention relates to an apparatus (100) for processing a medical image (IM) of a structure of interest (SOI). The apparatus comprises a first unit (101) configured for decomposing the medical image (IM) into at least one band pass image (Bdl) and a low pass image (L); a user interface (102) arranged for enabling a user to specify an enhancement curve (EC) for the radiographic image (IM) based on at least one of (i) a metric structure length (l), (ii) a structure selectivity (s) and (iii) a structure enhancement strength (a); a second unit (103) configured for applying the enhancement curve (EC) to the at least one band pass image (Bdl) for generating at least one enhanced band pass image EBdl; and a third unit (105) configured for composing an enhanced medical image (EIM) based on the at least one enhanced band pass image (EBdl) and the low pass image (L). The invention also relates to a corresponding method of processing a medical image (IM).
    Type: Grant
    Filed: November 17, 2016
    Date of Patent: May 19, 2020
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Mathias Schlueter, Andre Goossen
  • Patent number: 10650750
    Abstract: Sub-pixel compensation is described. In at least some implementations, a computing device includes a plurality of sub-pixels within a pixel which may generate an alternating display to approximate the display of a single sub-pixel. In other implementations, a voltage is applied to sub-pixels of a color such that a voltage across a first sub-pixel is proportional to a voltage across one or more additional sub-pixels. In other implementations, a change in a voltage drop across a sub-pixel is detected, and the change is compensated for by altering a voltage of a second sub-pixel within the pixel.
    Type: Grant
    Filed: March 8, 2018
    Date of Patent: May 12, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Rajesh Manohar Dighde, Ying Zheng
  • Patent number: 10652465
    Abstract: Systems, methods, and non-transitory computer-readable media can capture media content including an original set of frames. A plurality of subsets of frames can be identified, based on a subset selection input, out of the original set of frames. An orientation-based image stabilization process can be applied to each subset in the plurality of subsets of frames to produce a plurality of stabilized subsets of frames. Multiple frames within each stabilized subset in the plurality of stabilized subsets of frames can be combined to produce a plurality of combined frames. Each stabilized subset of frames can be utilized to produce a respective combined frame in the plurality of combined frames. A time-lapse media content item can be provided based on the plurality of combined frames.
    Type: Grant
    Filed: July 31, 2017
    Date of Patent: May 12, 2020
    Assignee: Facebook, Inc.
    Inventors: Alexandre Karpenko, Thomas Dimson
  • Patent number: 10613231
    Abstract: A method for using a GNSS device to determine a position of an unknown point includes determining positions of a first point, a second point, and a third point using the GNSS device. A first image is captured of the first point using an image sensor, the image includes the unknown point and at least one of the second point or the third point. A second image is captured from the second point; the second image includes the unknown point and at least one of the second point or the third point. A third image is captured from the third point; the third image includes the unknown point and at least one of the second point or the first point. A position of the unknown point is calculated based on the first, second, and third images and the first, second, and third positions.
    Type: Grant
    Filed: December 18, 2015
    Date of Patent: April 7, 2020
    Assignee: JAVAD GNSS, INC.
    Inventor: Javad Ashjaee
  • Patent number: 10607114
    Abstract: A generative network is used for lung lobe segmentation or lung fissure localization, or for training a machine network for lobar segmentation or localization. For segmentation, deep learning is used to better deal with a sparse sampling of training data. To increase the amount of training data available, an image-to-image or generative network localizes fissures in at least some of the samples. The deep-learnt network, fissure localization, or other segmentation may benefit from generative localization of fissures.
    Type: Grant
    Filed: January 16, 2018
    Date of Patent: March 31, 2020
    Assignee: Siemens Healthcare GmbH
    Inventors: Carol L. Novak, Benjamin L. Odry, Atilla Peter Kiraly, Jiancong Wang
  • Patent number: 10606918
    Abstract: Embodiments of the present disclosure relate to a configurable convolution engine that receives configuration information to perform convolution or its variant operations on streaming input data of various formats. To process streaming input data, input data of multiple channels are received and stored in an input buffer circuit in an interleaved manner. Data values of the interleaved input data are retrieved and forwarded to multiplier circuits where multiplication with a corresponding filter element of a kernel is performed. Varying number of kernels with different sizes and sparsity can also be used for the convolution operations.
    Type: Grant
    Filed: October 25, 2019
    Date of Patent: March 31, 2020
    Assignee: Apple Inc.
    Inventors: Suk Hwan Lim, Junji Sugisawa, Muge Wang
  • Patent number: 10600165
    Abstract: An image processing apparatus operable to perform development processing by performing at least a tone conversion on RAW image data that is inputted image data, the image processing apparatus comprising: a setting unit configured to set a first tone conversion curve corresponding to a dynamic range of the image data; an adjusting unit configured to generate a second tone conversion curve by adjusting the first tone conversion curve so that luminance changes of a bright portion and a dark portion of the image data are visually equivalent; and a tone conversion unit configured to perform a tone conversion of the image data by using the second tone conversion curve.
    Type: Grant
    Filed: October 5, 2018
    Date of Patent: March 24, 2020
    Assignee: Canon Kabushiki Kaisha
    Inventor: Hiroaki Nashizawa
  • Patent number: 10593249
    Abstract: A display apparatus is provided. The display apparatus includes a display panel comprising a plurality of pixels, a panel driver configured to drive the display panel, a storage configured to store information regarding a color gamut of each of the plurality of pixels, and a processor configured to determine a target color gamut of each of the plurality of pixels so that a difference in color gamut from at least one adjacent pixel is equal to or less than a predetermined threshold value, and to drive the panel driver for each of the plurality of pixels to have a grayscale value based on the target color gamut.
    Type: Grant
    Filed: June 4, 2019
    Date of Patent: March 17, 2020
    Assignee: Samsung Electrons Co., Ltd.
    Inventors: Seung-ryong Han, Byung-chul Kim, Jin-sung Lee, Ho-young Lee
  • Patent number: 10593289
    Abstract: An image processing apparatus including a selection section which, by selecting an electricity consumption minimum value where electricity consumption of a display section, which performs a display based on a value out of a plurality of values which are present within a predetermined distance from a pixel value of an image in a uniform color space, is a minimum as a pixel value of the image after color conversion, generates an image after the color conversion.
    Type: Grant
    Filed: February 12, 2015
    Date of Patent: March 17, 2020
    Assignee: SONY CORPORATION
    Inventor: Hideyuki Ichihashi
  • Patent number: 10578560
    Abstract: An inspection apparatus and method comprising a unit for acquiring an optical image of an object to be inspected by irradiating the object with light, wherein the unit includes a line sensor comprising a plurality of sensors linearly arranged in a row, a generating unit for generating a reference image from design data of the object to be inspected, a comparing unit for comparing the optical image with the reference image, a unit for storing data of three lines acquired by the line sensor, and calculating differences between a gradation value of a pixel on a center line and each gradation value of the eight pixels adjacent to the pixel determining if the pixel is a defect if all of the eight differences of the adjacent pixels are more than a predetermined threshold.
    Type: Grant
    Filed: April 5, 2012
    Date of Patent: March 3, 2020
    Assignee: NuFlare Technology, Inc.
    Inventors: Hiroteru Akiyama, Ikunao Isomura
  • Patent number: 10565685
    Abstract: According to one implementation, an image rendering system includes a computing platform having a hardware processor and a system memory storing an image denoising software code. The hardware processor executes the image denoising software code to receive an image file including multiple pixels, each pixel containing multiple depth bins, and to select a pixel including a noisy depth bin from among the pixels for denoising. The hardware processor further executes the image denoising software code to identify a plurality of reference depth bins from among the depth bins contained in one or more of the pixels, for use in denoising the noisy depth bin, and to denoise the noisy depth bin using an average of depth bin values corresponding respectively to each of the reference depth bins.
    Type: Grant
    Filed: June 27, 2017
    Date of Patent: February 18, 2020
    Assignee: Disney Enterprises, Inc.
    Inventors: David M. Adler, Delio Aleardo Vicini, Brent Burley, Jan Novak, Fabrice Pierre Armand Rousselle
  • Patent number: 10567605
    Abstract: An image forming apparatus includes: an image former that forms a document image including a correction image; an image reader; and a calibrator, and performing correction, wherein the document image is designed so that main register marks and a subsidiary register mark are provided, and the calibrator includes a four-corner detector that detects four corners of a sheet of paper, a main register mark reference position detector that detects reference positions of the main register marks, a subsidiary register mark prediction position determiner that predicts and determines prediction positions of the subsidiary register marks, a subsidiary register mark reference position detector that detects a reference position of the subsidiary register mark, a correction image prediction position determiner that predicts and determines a prediction position of the correction image, a measured value obtainer, and a correction value calculator.
    Type: Grant
    Filed: March 21, 2018
    Date of Patent: February 18, 2020
    Assignee: Konica Minolta, Inc.
    Inventor: Mieko Mita
  • Patent number: 10552460
    Abstract: A sensor data management apparatus according to an embodiment stores pieces of sensor data in data areas provided corresponding to prescribed data units and manages the pieces of sensor data. The pieces of sensor data have been input from a plurality of sensors. The sensor data management apparatus includes a group determining unit and a data storing unit. The group determining unit is configured to analyze the pieces of stored sensor data and determine groups of sensors based on a result of the analysis. The data storing unit is configured to determine a storage location of a newly input piece of sensor data to store pieces of sensor data from sensors belonging to the same one of the groups in the same one of the data areas, and store the piece of sensor data at the storage location.
    Type: Grant
    Filed: March 7, 2017
    Date of Patent: February 4, 2020
    Assignee: KABUSHIKI KAISHA TOSHIBA
    Inventor: Yosuke Kuroda
  • Patent number: 10555006
    Abstract: A device for decoding video data determines mode information for a current block of a current picture of the video data; derives weights for use in a bilateral filter based on the mode information for the current block; applies the bilateral filter to a current sample of the current block by assign the weights to neighboring samples of the current sample of the current block and the current sample of the current block and modifying a sample value for the current sample based on sample values of the neighboring samples, the weights assigned to the neighboring samples, the sample value for the current sample, and the weight assigned to the current sample; and based on the modified sample value for the current sample, outputs a decoded version of the current picture.
    Type: Grant
    Filed: December 21, 2017
    Date of Patent: February 4, 2020
    Assignee: QUALCOMM Incorporated
    Inventors: Li Zhang, Wei-Jung Chien, Marta Karczewicz
  • Patent number: 10521888
    Abstract: An aerothermal-radiation correction method, including: using a Gaussian surface to approximate a thermal radiation noise, performing a Fourier transform on the Gaussian surface so as to obtain a centralized spectrum of the thermal radiation noise, constructing a filter function H based on the centralized spectrum of the thermal radiation noise; performing a Fourier transform on the aerothermal-radiation degraded image f so as to obtain a centralized spectrum F, taking dot product of F and H to obtain a filtered spectrum G; and performing an inverse Fourier transform on filtered spectrum G to obtain a modulus, and acquire a corrected image. The method effectively removes background noise generated by aerothermal radiation, greatly improves image quality and image signal-to-noise ratio. The method features reduced computational complexity and a shorter operation time, and is suited for real-time processing.
    Type: Grant
    Filed: March 20, 2019
    Date of Patent: December 31, 2019
    Assignee: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY
    Inventors: Tianxu Zhang, Xuan Hou, Chuan Zhang, Li Liu, Quan Chen, Ao Zhong, Mingxing Xu, Yutian Zhou
  • Patent number: 10482585
    Abstract: The present disclosure provides an image recording device and an image processing method. The tone adjusting unit includes plural preset tone mapping adjusting curves. The auto exposure unit compares and obtains the nearest brightness interval from plural brightness intervals according to the image information of the original dynamic image. The tone adjusting unit chooses the corresponding tone mapping adjusting curve from the plural tone mapping adjusting curves to adjust the brightness of the original dynamic image according to the brightness interval. Therefore, the image recording device and the image processing method of the present disclosure takes different tone mapping adjusting curves to adjust the brightness of the original dynamic image according to different brightness of the original dynamic image. The image recording device of the present disclosure adjusts the brightness according to different brightness of the original dynamic image.
    Type: Grant
    Filed: November 1, 2018
    Date of Patent: November 19, 2019
    Assignee: COMPAL ELECTRONICS, INC.
    Inventor: Chung-Hsiang Lin
  • Patent number: 10475215
    Abstract: A method for multi-dimensional image processing obtains a multi-dimensional image having a plurality of data elements, each data element having a corresponding data value. The method forms a reduced noise image by repeated iterations of a process that adjusts the data value for one or more data elements p of the obtained image by: for each data element k in a group of data elements in the image, calculating a weighting factor for the data element k as a function of the difference between an estimated data value for data element p and the corresponding data value of data element k, updating the estimated data value for the data element p according to the combined calculated weighting factors and the data value of the data element k; and displaying, storing, or transmitting the reduced noise image.
    Type: Grant
    Filed: July 28, 2017
    Date of Patent: November 12, 2019
    Assignee: Carestream Health, Inc.
    Inventors: Edward B. Gindele, Richard A. Simon
  • Patent number: 10467496
    Abstract: An image processing pipeline may perform temporal filtering on independent color channels in image data. A filter weight may be determined for a given pixel received at a temporal filter. The filter weight may be determined for blending a value of a channel in a full color encoding of the given pixel with a value of the same channel for a corresponding pixel in a previously filtered reference image frame. In some embodiments, the filtering strength for the channel may be determined independent from the filtering strength of another channel in the full color encoding of the given pixel. Spatial filtering may be applied to a filtered version of the given pixel prior to storing the given pixel as part of a new reference image frame.
    Type: Grant
    Filed: August 31, 2015
    Date of Patent: November 5, 2019
    Assignee: Apple Inc.
    Inventors: Suk Hwan Lim, D. Amnon Silverstein, Sheng Lin
  • Patent number: 10460429
    Abstract: A portable image enhancement device comprising an optical image sensor, a rangefinder, a parametric control, a central processing unit (CPU), and a user interface. The sensor receives image data for a target object in a tactical scene. The rangefinder continually measures distance from the device to the target object, which may be in motion relative to each other. The parametric control tunes a parametric variable (e.g., spatial frequency, filter shape, orientation) that the CPU uses, along with the potentially-changing target distance, to create custom spatial filters and apply them to create a filtered scene from the tactical scene. Each spatial filter is of a two-dimensional (2D) Fourier-domain type (e.g., high-pass, low-pass, band-pass, band-stop, orientation). A spatial filter, target distance, and parametric variable combination may be stored as a preset filter for subsequent retrieval and application to a newly-input tactical scene. The user interface displays dynamically-tunable filtered scene(s).
    Type: Grant
    Filed: January 3, 2018
    Date of Patent: October 29, 2019
    Inventors: Alan R Pinkus, David W Dommett, Allan Pantle, Jordan M Haggit
  • Patent number: 10445861
    Abstract: Systems and method for refining a depth map of a scene based upon a captured image of the scene. A captured depth map of the scene may contain outage areas or other areas of low confidence. The depth map may be aligned with a color image of the scene, and the depth values of the depth map may be adjusted based upon corresponding color values of the color image. An amount of refinement for each depth value of the aligned depth map is based upon the confidence value of the depth value and a smoothing function based upon a corresponding location of the depth value on the color image.
    Type: Grant
    Filed: February 14, 2017
    Date of Patent: October 15, 2019
    Assignee: QUALCOMM Incorporated
    Inventors: Hasib Siddiqui, Kalin Atanassov, James Nash
  • Patent number: 10416790
    Abstract: A user-facing front end screen display of an illustrative digital image painting application includes a bucket tool which enables a user to apply a selected color to a selected area of an uploaded digital image such as a wall of a room, a paint brush tool to fill in missed areas, an eraser tool is to remove misapplied color, masking tools to mask off selected areas, and a tolerance slider tool to assist in properly filling in painted areas. Improved image preprocessing methods enable better definition of areas of the image to be painted the same color.
    Type: Grant
    Filed: November 22, 2017
    Date of Patent: September 17, 2019
    Assignee: Behr Process Corporation
    Inventors: Damien Reynolds, Douglas Milsom, Vincent Giosa
  • Patent number: 10409853
    Abstract: An image filtering method is provided, including: acquiring a sample characteristic value of a sample image; ranking images to be filtered in a specific chronological order; acquiring characteristic values of the images to be filtered; comparing the characteristic values of the images to be filtered with that of the sample image, selecting, from the images, filtered images conforming to preset conditions, storing the filtered images in the specific chronological order, and displaying the filtered images. Accordingly, a user is enabled to easily find identical or similar images amongst a large number of images.
    Type: Grant
    Filed: October 16, 2015
    Date of Patent: September 10, 2019
    Assignee: HUIZHOU TCL MOBILE COMMUNICATION CO., LTD.
    Inventors: Yu Zheng, Zongmin Ye
  • Patent number: 10410326
    Abstract: The present invention discloses an image anti-aliasing system, which comprises an edge detection unit, a directional filter, a low-angle directional filter, a directional filtering fusion unit and a result fusion unit; the edge detection unit outputs the edge direction and edge confidence according to an input image, the directional filter outputs a directional filtering result based on the input image and the edge direction, the low-angle directional filter outputs a low-angle directional filtering result according to the input image and the edge direction; the directional filtering fusion unit weights and combines the result output from the directional filter and the result output from the low-angle directional filter according to the edge direction, and outputs a result of weighted combination of two directional filtering results; the result fusion unit outputs an optimized image according to the edge confidence, the input image and the result of the directional filtering fusion unit.
    Type: Grant
    Filed: April 16, 2015
    Date of Patent: September 10, 2019
    Assignee: Institute of Automation Chinese Academy of Sciences
    Inventors: Ruoshan Guo, Rui Han, Renjun Tang
  • Patent number: 10402942
    Abstract: Aerial imagery may be captured from an unmanned aircraft or other aerial vehicle. The use of aerial vehicle imagery provides greater control over distance from target and time of image capture, and reduces or eliminates imagery interference caused by clouds or other obstacles. Images captured by the aerial vehicle may be analyzed to provide various agricultural information, such as vegetative health, plant counts, population counts, plant presence estimation, weed presence, disease presence, chemical damage, wind damage, standing water presence, nutrient deficiency, or other agricultural or non-agricultural information. Georeference-based mosaicking may be used to process and combine raw image files into a direct georeferenced mosaic image.
    Type: Grant
    Filed: September 28, 2017
    Date of Patent: September 3, 2019
    Assignee: Sentera, Inc.
    Inventors: Eric Taipale, Andrew Muehlfeld
  • Patent number: 10360666
    Abstract: An input HDR image may be represented using an SDR image and a modulation value. For the SDR image to be viewable and representative of the HDR image, we propose a mid-tone optimization technique to calculate the modulation value. In particular, we use two conditions when deriving the modulation value: (1) the blacks are not clipped down to zero too aggressively; and (2) the number of codewords in the SDR image used to represent the mid-tone range of the HDR image is maximized. The modulation value can further be clipped to avoid over-shooting in both very dark images and very bright images. Temporal stabilization can also be used to smooth temporal variations of the luminosity in the SDR video. After the modulation value is determined, the SDR image can be obtained based on the HDR image and the modulation value.
    Type: Grant
    Filed: January 26, 2016
    Date of Patent: July 23, 2019
    Assignee: InterDigital VC Holdings, Inc.
    Inventors: Sebastien Lasserre, Fabrice Leleannec, Philippe Bordes
  • Patent number: 10348989
    Abstract: The present technology relates to an image processing device, an image processing method, and an image processing system capable of improving detection accuracy of a defective pixel. Provided is an image processing device including a defective pixel estimation unit that estimates a defect of a pixel of interest in an image captured by a solid-state imaging device that contains a two-dimensional array of color pixels, and high-sensitivity pixels having higher sensitivity than sensitivities of the color pixels. The defect of the pixel of interest is estimated on the basis of a correlation between pixel values of the high-sensitivity pixels, and pixel values of the color pixels. The image processing device further includes a defective pixel correction unit that corrects the pixel of interest when it is estimated that the pixel of interest is a defective pixel. The present technology is applicable to an image processing device which corrects a defective pixel by signal processing, for example.
    Type: Grant
    Filed: August 14, 2015
    Date of Patent: July 9, 2019
    Assignee: SONY SEMICONDUCTOR SOLUTIONS CORPORATION
    Inventor: Kazuhide Fujita
  • Patent number: 10319276
    Abstract: A display apparatus is provided. The display apparatus includes a display panel comprising a plurality of pixels, a panel driver configured to drive the display panel, a storage configured to store information regarding a color gamut of each of the plurality of pixels, and a processor configured to determine a target color gamut of each of the plurality of pixels so that a difference in color gamut from at least one adjacent pixel is equal to or less than a predetermined threshold value, and to drive the panel driver for each of the plurality of pixels to have a grayscale value based on the target color gamut.
    Type: Grant
    Filed: April 11, 2017
    Date of Patent: June 11, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Seung-ryong Han, Byung-chul Kim, Jin-sung Lee, Ho-young Lee
  • Patent number: 10319076
    Abstract: In one embodiment, a method includes accessing a plurality of generative adversarial networks (GANs) that are each applied to a particular level k of a Laplacian pyramid. Each GAN may comprise a generative model Gk and a discriminative model Dk. At each level k, the generative model Gk may take as input a noise vector zk and may output a generated image {tilde over (h)}k. At each level k, the discriminative model Dk may take as input either the generated image {tilde over (h)}k or a real image hk, and may output a probability that the input was the real image hk. The method may further include generating a sample image ?k from the generated images {tilde over (h)}k, wherein the sample image is based on the probabilities outputted by each of the discriminative models Dk and the generated images {tilde over (h)}k. The method may further include providing the sample image ?k for display.
    Type: Grant
    Filed: June 15, 2017
    Date of Patent: June 11, 2019
    Assignee: Facebook, Inc.
    Inventors: Emily Denton, Soumith Chintala, Arthur David Szlam, Robert D. Fergus
  • Patent number: 10313603
    Abstract: A photograph generation apparatus that controls a light source and corrects a picture using an illuminance sensor and a transparent liquid crystal, the photograph generation apparatus includes: a camera part configured to take a photographed picture of a user using the photograph generation apparatus; a lighting part configured to provide lighting for an object to be photographed using the photograph generation apparatus; an illuminance sensor part configured to measure an illuminance within a predetermined range of the photograph generation apparatus to use the measured illuminance in controlling the lighting of the lighting part; and a transparent liquid crystal panel mounted at a front surface of the camera part and configured to control an amount of a light source radiated to the camera part when the picture is being taken.
    Type: Grant
    Filed: December 6, 2017
    Date of Patent: June 4, 2019
    Assignee: I-AURORA CO., LTD.
    Inventors: Young Su Chang, Hye Kyung Kim, Hoon Kim, Tae Sung Kim, Hye Young Kim, Han Soo Lee
  • Patent number: 10311884
    Abstract: The present document relates an audio encoding and decoding system (referred to as an audio codec system). In particular, the present document relates to a transform-based audio codec system which is particularly well suited for voice encoding/decoding. A quantization unit configured to quantize a first coefficient of a block of coefficients is described. The block of coefficients comprises a plurality of coefficients for a plurality of corresponding frequency bins. The quantization unit is configured to provide a set of quantizers. The set of quantizers comprises a plurality of different quantizers associated with a plurality of different signal-to-noise ratios, referred to as SNR, respectively. The plurality of different quantizers includes a noise-filling quantizer; one or more dithered quantizers; and one or more un-dithered quantizers.
    Type: Grant
    Filed: March 22, 2018
    Date of Patent: June 4, 2019
    Assignee: Dolby International AB
    Inventors: Janusz Klejsa, Lars Villemoes, Per Hedelin
  • Patent number: 10311546
    Abstract: An edge detection apparatus according to the present invention, includes: a detection unit configured to detect a dispersion degree of gradation values of input image data; a determination unit configured to determine detection sensitivity, which is edge detectability, based on the dispersion degree detected by the detection unit; and an edge detection unit configured to detect an edge from an input image based on the input image data, at the detection sensitivity determined by the determination unit, wherein in a case where the dispersion degree is low, the determination unit determines a lower detection sensitivity, compared with a case where the dispersion degree is high.
    Type: Grant
    Filed: November 28, 2016
    Date of Patent: June 4, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Masaharu Yamagishi
  • Patent number: 10282844
    Abstract: A system and method for image segmentation are provided. A three-dimensional image data set representative of a region including at least one airway may be acquired. The data set may include a plurality of voxels. A first-level seed within the region may be identified. A first-level airway within the region may be identified based on the first-level seed. A second-level airway may be identified within the region based on the first-level airway. The first-level airway and the second-level airway may be fused to form an airway tree.
    Type: Grant
    Filed: May 5, 2016
    Date of Patent: May 7, 2019
    Assignee: SHANGHAI UNITED IMAGING HEALTHCARE CO., LTD.
    Inventors: Lilong Wang, Lijia Wang, Yufei Mao, Xiaolin Meng, Xiaodong Wang, Cheng Li
  • Patent number: 10282823
    Abstract: An image processing method and related apparatus. An image is decomposed into spatial frequency components images. The spatial frequency component images are normalized relative to specific noise models, remapped by a noise reduction function and are then combined to obtain a noise reduced version of the image.
    Type: Grant
    Filed: November 19, 2015
    Date of Patent: May 7, 2019
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Mathias Schlüter, Hanns-Ingo Maack, Bernd Lundt
  • Patent number: 10282824
    Abstract: A method of eliminating stripe noise for infrared images including: selecting a specific row of data from an to-be-filtered image Aim, and obtaining a stripe width N1 from information of a frequency spectrum of the data; intercepting (N1+1) new sequences of different lengths from a specific row sequence of the image according to the stripe width N1, and obtaining an optimal interception length N by analyzing information of amplitude spectrum of each new sequence; splitting the to-be-filtered image Aim with a size of M×Nn into a pair of optimum to-be-filtered sub-images Bim and Cim with a size of M×N according to the length N; obtaining two sub-images Bimf and Cimf after using a notch-comb filter to filter the two optimum to-be-filtered sub-images Bim and Cim; carrying out a brightness adjustment and a combination process to the two sub-image Bimf and Cimf to obtain an image Aimf.
    Type: Grant
    Filed: December 12, 2017
    Date of Patent: May 7, 2019
    Assignee: SHENZHEN UNIVERSITY
    Inventors: Jihong Pei, Mi Zou, Weixin Xie, Xuan Yang
  • Patent number: 10275678
    Abstract: A biometric image processing apparatus including a memory and a processor coupled to the memory. The processor obtains a Y value, a U value and a V value in a YUV space from each pixel of an image, determines, for each pixel, whether or not the U value and the V value are in a range that is in accordance with the Y value, and extracts a pixel having been determined to be in the range.
    Type: Grant
    Filed: August 25, 2017
    Date of Patent: April 30, 2019
    Assignee: FUJITSU LIMITED
    Inventors: Soichi Hama, Hajime Nada, Satoshi Maeda, Satoshi Semba, Yukihiro Abiko, Shinji Egashira, Toshiaki Wakama, Rie Hasada
  • Patent number: 10268451
    Abstract: A method of performing an arithmetic operation by a processing apparatus includes determining a polynomial expression approximating an arithmetic operation to be performed on a variable; adaptively determining upper bits for addressing a look-up table (LUT) according to a variable section to which the variable belongs; obtaining coefficients of the polynomial expression from the LUT by addressing the LUT using a value of the upper bits; and performing the arithmetic operation by calculating a result value of the polynomial expression using the coefficients.
    Type: Grant
    Filed: March 21, 2016
    Date of Patent: April 23, 2019
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventor: Hyeongseok Yu
  • Patent number: 10262401
    Abstract: Embodiments of the present disclosure relate to performing noise reduction on an input image by first filtering the input image based on coarse noise models of pixels and then subsequently filtering the filtered input image based on finer noise models. The finer noise models use the same or more number of neighboring pixels than the coarse noise filters. The first filtering and subsequent filtering of a pixel in the input image use Mahalanobis distances between the pixel and its neighboring pixels. By performing iterations of filtering using more refined noise models, the noise reduction in the input image can be performed more efficiently and effectively.
    Type: Grant
    Filed: April 27, 2017
    Date of Patent: April 16, 2019
    Assignee: Apple Inc.
    Inventors: Maxim W. Smirnov, D. Amnon Silverstein
  • Patent number: 10255507
    Abstract: A system and method for determining an object in a distorted image. The method comprises detecting a location of a first part of the object on the distorted image; determining a corresponding location of the first part of the object on an undistorted image plane corresponding to the distorted image based on a plurality of calibration parameters; predicting a location of a second part of the object on the undistorted image plane based on the determined location of the first part on the undistorted image plane; determining a corresponding location of the second part of the object on the distorted image based on the predicted location of the second part of the object on the undistorted image plane and the calibration parameters; and determining the object based on the detected location of the first part of the object and the determined location of the second part in the distorted image.
    Type: Grant
    Filed: December 19, 2016
    Date of Patent: April 9, 2019
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Geoffrey Richard Taylor
  • Patent number: 10242453
    Abstract: A pair of video frames may be used for simultaneous localization and mapping (SLAM) initialization. The pair of frames may be determined according to a translation threshold. Whether the translation threshold is met may be determined by obtaining the pair of video frames and estimating the translation between the frames.
    Type: Grant
    Filed: April 30, 2014
    Date of Patent: March 26, 2019
    Assignee: LONGSAND LIMITED
    Inventors: Pashmina Cameron, George Saklatvala
  • Patent number: 10235607
    Abstract: A control device includes one or more processors. The processors detect a target captured in an image, and calculate likelihood indicating whether the target is concealed. The processors decide on an output method for outputting the target according to the likelihood. The processors generate a display image based on the image and the decided output method.
    Type: Grant
    Filed: February 23, 2017
    Date of Patent: March 19, 2019
    Assignee: Kabushiki Kaisha Toshiba
    Inventors: Hidetaka Ohira, Yuto Yamaji, Tomoyuki Shibata, Osamu Yamaguchi
  • Patent number: 10237523
    Abstract: A digital PSF for use in a dual modulation display. The invention allows the use of less than optimal point spread (PSF) functions in the optics between the pre-modulator and primary modulator of a dual modulation projection system. This technique uses multiple halftones per frame in the pre-modulator synchronized with a modified bit sequence in the primary modulator to produce a compensation image that reduces the errors produced by the sub-optimal PSF. The invention includes the application to dual modulation and dual modulated 3D viewing systems.
    Type: Grant
    Filed: April 30, 2014
    Date of Patent: March 19, 2019
    Assignee: Dolby Laboratories Licensing Corporation
    Inventor: Martin J. Richards
  • Patent number: 10218922
    Abstract: A solid-state imaging device includes a first semiconductor substrate to which light is incident; a second semiconductor substrate stacked to the first semiconductor substrate; n first photoelectric conversion devices periodically arranged in the first semiconductor substrate and generating first electric charge signals; n first reading circuits arranged in correspondence with the n first photoelectric conversion devices in the first semiconductor substrate, respectively, each of the n first reading circuits accumulating the first electric charge signal outputting a signal voltage corresponding to the accumulated first electric charge signal as a first pixel signal; a driving circuit sequentially outputting the first pixel signal; m second photoelectric conversion devices periodically arranged in one of the first/second semiconductor substrates and generating second electric charge signals; and m second reading circuits sequentially outputting a second pixel signal, wherein m and n are natural numbers equal t
    Type: Grant
    Filed: January 9, 2018
    Date of Patent: February 26, 2019
    Assignee: OLYMPUS CORPORATION
    Inventors: Toru Kondo, Kosei Tamiya, Nobuyuki Watanabe
  • Patent number: 10181182
    Abstract: The present disclosure relates to an image processing apparatus and an image processing method whereby a point spread function can be estimated with high precision. An exclusion unit excludes a repetitive pattern from a degraded image. An estimation unit estimates a point spread function by use of the degraded image from which the repetitive pattern has been excluded by the exclusion unit. The present disclosure can be applied to, for example, an image processing apparatus or the like that estimates a point spread function (PSF) from a degraded image and that performs a blind deconvolution using the point spread function to generate a restored image from the degraded image.
    Type: Grant
    Filed: May 20, 2015
    Date of Patent: January 15, 2019
    Assignee: SONY CORPORATION
    Inventor: Kazumi Fukuda
  • Patent number: 10165263
    Abstract: A method for estimating an optics point spread function (518) of a lens assembly (20) includes (i) providing a test chart (14); (ii) providing a capturing system (22); (iii) capturing a test chart image (316) of the test chart (14) with the capturing system (22) using the lens assembly (20) to focus light onto the capturing system (22); (iv) selecting an image area (490) from the test chart image (316); (v) dividing the image area (490) into a plurality of area blocks (494); and (vii) estimating an area point spread function (518) of the image area (490) using a PSF cost function that sums the fidelity terms of at least two of the area blocks (494).
    Type: Grant
    Filed: November 20, 2015
    Date of Patent: December 25, 2018
    Assignee: NIKON CORPORATION
    Inventor: Radka Tezaur
  • Patent number: 10163348
    Abstract: A drive assist devices include a display that displays an image around a vehicle imaged by an imaging device installed on the vehicle, a setting unit that sets a target designated by a user on the image as a recognition target, a detection unit that detects a state change of the recognition target on the image in a case where the recognition target is set, and a notification control unit that controls a notification device to notify the user of the detection result in a case where the state change of the set recognition target is detected.
    Type: Grant
    Filed: August 1, 2012
    Date of Patent: December 25, 2018
    Assignee: TOYOTA JIDOSHA KABUSHIKI KAISHA
    Inventors: Kentaro Ichikawa, Toshiki Kindo, Katsuhiro Sakai, Masahiro Harada, Hiromitsu Urano
  • Patent number: 10152781
    Abstract: A method for filtering a digital image, comprising segmenting the digital image into a plurality of tiles; computing tile histograms corresponding to each of the plurality of tiles; deriving a plurality of tile transfer functions from the tile histograms preferably using 1D convolutions; interpolating a tile transfer function from the plurality of tile transfer functions; and filtering the digital image with the interpolated tile transfer function. Many filters otherwise difficult to conceive or to implement are possible with this method, including an edge-preserving smoothing filter, HDR tone mapping, edge invariant gradient or entropy detection, image upsampling, and mapping coarse data to fine data.
    Type: Grant
    Filed: March 16, 2017
    Date of Patent: December 11, 2018
    Assignee: Google LLC
    Inventor: Nils Kokemohr
  • Patent number: 10142541
    Abstract: An image processing apparatus determines whether a feature amount in a partial region of an image satisfies a preset condition, selects a second image to be combined with a first image from a plurality of images based on the result of the determination, and performs a composition process on the aligned first image and second image based on a motion vector between these images. From the plurality of images, the image processing apparatus selects as the second image at least any one of an image having a partial region with the feature amount determined to satisfy the preset condition and an image corresponding to a partial region out of a plurality of partial regions set in the first image with the feature amount determined to satisfy the preset condition.
    Type: Grant
    Filed: February 16, 2017
    Date of Patent: November 27, 2018
    Assignee: Canon Kabushiki Kaisha
    Inventor: Hironori Kaida
  • Patent number: 10136100
    Abstract: There is provided a method performed by a device in a network camera system. First and second encoded image data representing the same scene are received (S02, SO4) over a network. The first and the second encoded image data are collected under the same light condition, albeit using different camera parameters. In particular, the second encoded image data is collected using camera parameters which simulate that the second encoded image data is collected under a darker light condition. A ratio of received data amount per time unit of the first encoded image data to received data amount per time unit of the second encoded image data is determined (S06) and the ratio is then used (S08) as an indication of a level of noise in the first encoded image data.
    Type: Grant
    Filed: April 27, 2017
    Date of Patent: November 20, 2018
    Assignee: Axis AB
    Inventor: Mikael Ranbro
  • Patent number: 10129437
    Abstract: An image processing apparatus includes a color separation unit separating image data into a luminance component and a color component; a processing unit generating second image data of the luminance component by manipulating pixel values of multi-resolution image data generated from first image data of the luminance component and reconstructing the manipulated multi-resolution image data; and a composition unit compositing the second image data of the luminance component with image data of the color component. Further, the processing unit generates the second image data of the luminance component based on pixel values which are adjusted by using parameters in accordance with pixel values of the image data of the color component.
    Type: Grant
    Filed: August 19, 2015
    Date of Patent: November 13, 2018
    Assignee: Ricoh Company, Ltd.
    Inventor: Kei Yasutomi
  • Patent number: 10127641
    Abstract: Disclosed in the present invention is a contrast constrained aerothermal radiation correction method. By analyzing features of images at different intensities of aerothermal radiation, it has been discovered that the stronger the aerothermal radiation effect is, the smaller the image contrast becomes, and when thermal radiation correction is performed using a gradient fitting algorithm, it has been discovered that time consumption thereof grows exponentially with an increase in a degree of a fitting surface and with an increase in an image size. The present invention can rapidly and effectively restore an aerothermal radiation image, remarkably improving a signal to noise ratio and quality of the image.
    Type: Grant
    Filed: April 13, 2016
    Date of Patent: November 13, 2018
    Assignee: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY
    Inventors: Tianxu Zhang, Chuan Zhang, Xuan Hou, Li Liu, Quan Chen, Ao Zhong, Mingxing Xu, Yutian Zhou