Image Filter Patents (Class 382/260)
  • Patent number: 11521299
    Abstract: The present disclosure relates to an image retouching system that automatically retouches digital images by accurately correcting face imperfections such as skin blemishes and redness. For instance, the image retouching system automatically retouches a digital image through separating digital images into multiple frequency layers, utilizing a separate corresponding neural network to apply frequency-specific corrections at various frequency layers, and combining the retouched frequency layers into a retouched digital image. As described herein, the image retouching system efficiently utilizes different neural networks to target and correct skin features specific to each frequency layer.
    Type: Grant
    Filed: October 16, 2020
    Date of Patent: December 6, 2022
    Assignee: Adobe Inc.
    Inventors: Federico Perazzi, Jingwan Lu
  • Patent number: 11488279
    Abstract: An image processing apparatus includes an image acquisition unit configured to acquire a plurality of temporally different images each of which has degraded by a turbulence, a parameter acquisition unit configured to acquire a learned network parameter, and a measurement unit configured to measure a turbulence strength from the plurality of images using the network parameter and a neural network.
    Type: Grant
    Filed: November 19, 2019
    Date of Patent: November 1, 2022
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Yoshinori Kimura
  • Patent number: 11461632
    Abstract: Disclosed are a method and an apparatus for adapting parameters of a neural network. The method includes selecting one or more dimensions for a weight parameter of each of at least one layer of the neural network, determining a dimension value and a corresponding target value in each dimension of the weight parameter, and padding the weight parameter in a case where the dimension value in at least one dimension of the weight parameter is less than the corresponding target value, the dimension value in each dimension of the weight parameter after the padding being equal to the corresponding target value.
    Type: Grant
    Filed: April 23, 2018
    Date of Patent: October 4, 2022
    Assignee: Nanjing Horizon Robotics Technology Co., Ltd.
    Inventors: Kun Ling, Liang Chen, Jianjun Li, Delin Li, Chang Huang
  • Patent number: 11460855
    Abstract: Implementations described and claimed herein provide systems and methods for sensor calibration. In one implementation, an image and a depth map of a field around a mobile device are obtained. The image is captured using a first sensor, and the depth map is captured using a second sensor. A position and a reflected radiation intensity of a calibration surface are detected in the field using the depth map. A first portion and a second portion of the calibration surface representing a background color and a foreground color are isolated based on the reflected radiation intensity. The calibration surface is detected in the image using the position of the calibration surface in the depth map and a calibration transform between the first sensor and the second sensor. The calibration transform is optimized based on an overlap of the foreground color and/or the background color between the depth map and the image.
    Type: Grant
    Filed: March 30, 2020
    Date of Patent: October 4, 2022
    Inventors: Ying Yi Lim, Sasawat Prankprakma
  • Patent number: 11461940
    Abstract: The present application provides an imaging method and system, and a non-transitory computer-readable storage medium. The imaging method comprises preprocessing projection data to obtain a predicted image of a truncated portion; performing forward projection on the predicted image to obtain predicted projection data of the truncated portion; and performing image reconstruction using the projection data obtained by forward projection and projection data of an untruncated portion.
    Type: Grant
    Filed: May 4, 2020
    Date of Patent: October 4, 2022
    Assignee: GE Precision Healthcare LLC
    Inventors: Xueli Wang, Ximiao Cao, Bingjie Zhao, Weiwei Xing
  • Patent number: 11448503
    Abstract: A method to correct a digital image to reverse the effect of signal diffusion among pixels of the digital image. For a target pixel j of the digital image, a set of signal values and a set of signal amplitudes are received, each corresponding to a set of kernel pixels i surrounding and including the target pixel j. For each kernel pixel i, a weighting coefficient is computed based on the signal amplitude of that kernel pixel i and on the signal amplitude of the target pixel j. A linear combination of signal values corresponding to the set of kernel pixels i is computed, wherein the signal value for each pixel i is weighted by the weighting coefficient corresponding to that pixel i. The linear combination is stored in volatile memory of an electronic device as a corrected signal value for the target pixel j.
    Type: Grant
    Filed: September 26, 2019
    Date of Patent: September 20, 2022
    Assignee: Microsoft Technology Licensing, LLC
    Inventor: Sergio Ortiz Egea
  • Patent number: 11438544
    Abstract: The present application discloses an image transmission device and method. The image transmission device includes a receiver configured to receive pixel data in image data from a camera in sequence and buffer the pixel data into a memory, and determine, upon reception of a line of pixel data, a line number of the line of pixel data in the image data and a frame number of the image data; and a processor configured to obtain the line of pixel data, the line number of the line of pixel data and the frame number of the image data from the receiver, package the obtained line of pixel data, line number of the line of pixel data and frame number of the image data into a data packet, and transmit the data packet to a server.
    Type: Grant
    Filed: August 10, 2020
    Date of Patent: September 6, 2022
    Assignee: BEIJING TUSEN WEILAI TECHNOLOGY CO., LTD.
    Inventors: Ming Wang, Jie Sun
  • Patent number: 11405611
    Abstract: An example device for filtering a decoded block of video data includes one or more processing units configured to construct a plurality of filters for classes of blocks of a current picture of video data. To construct the plurality of filters for each of the classes, the processing units are configured to determine a value of a flag that indicates whether a fixed filter is used to predict a set of filter coefficients of the class, and in response to the fixed filter being used to predict the set of filter coefficients, determine an index value into a set of fixed filters and predict the set of filter coefficients of the class using a fixed filter of the set of fixed filters identified by the index value.
    Type: Grant
    Filed: February 14, 2017
    Date of Patent: August 2, 2022
    Assignee: QUALCOMM Incorporated
    Inventors: Marta Karczewicz, Wei-Jung Chien, Li Zhang
  • Patent number: 11405116
    Abstract: A method of optimizing at least one IQMC parameter value for an IQMC includes: generating a set of tested IQMC candidate parameter values by performing an iterative method including selecting a first IQMC candidate parameter value for the at least one parameter of the IQMC; determining, using the first IQMC candidate parameter value, a performance metric value that comprises at least one of (i) an image rejection ratio (IRR) value, (ii) a signal-to-interference-plus-noise ratio (SINR) value, or (iii) a signal-to-image ratio (SImR) value; and determining a second IQMC candidate parameter value that is an update to the first IQMC candidate parameter value. The method of optimizing at least one IQMC parameter value for an IQMC further includes determining an IQMC candidate parameter value of the set of tested IQMC candidate parameter values that optimizes the performance metric.
    Type: Grant
    Filed: December 10, 2020
    Date of Patent: August 2, 2022
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Elina Nayebi, Pranav Dayal, Kee-Bong Song
  • Patent number: 11380026
    Abstract: The present application provides a method and device for obtaining a predicted image of a truncated portion, an imaging method and system, and a non-transitory computer-readable storage medium. The method for obtaining a predicted image of a truncated portion comprises preprocessing projection data to obtain, by reconstruction, an initial image of the truncated portion; and calibrating the initial image based on a trained learning network to obtain the predicted image of the truncated portion.
    Type: Grant
    Filed: May 5, 2020
    Date of Patent: July 5, 2022
    Assignee: GE Precision Healthcare LLC
    Inventors: Xueli Wang, Bingjie Zhao, Shiyu Li, Dan Liu
  • Patent number: 11366581
    Abstract: Disclosed is a display apparatus displays a first image selected based on a user input, obtains, from a server, a second image having a transfer style, the transfer style preferred by a user from among a plurality of transfer styles, and displays the second image.
    Type: Grant
    Filed: October 8, 2019
    Date of Patent: June 21, 2022
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Jeongrok Jang, Kwansik Yang, Jaehwang Lee
  • Patent number: 11348204
    Abstract: The present invention discloses an image adaptive noise reduction method and a device thereof. The method includes: dividing an original image into a plurality of sub-blocks; performing a space conversion for all the sub-blocks; performing a significance analysis to obtain a significant characteristic map; performing a threshold segmentation on all the significant characteristic maps by a significant standard value to obtain a significant characteristic region and a non-significant characteristic region; performing adaptive filtering on the significant characteristic region and maxing an original image in the non-significant characteristic region to obtain a mixed image; and performing an image space inverse conversion for the mixed image, and outputting a final image. The present invention uses the method of dividing the image, based on the significant characteristics of the image, reducing noise reduction in the non-significant characteristic region, saving algorithm running time and hardware resources.
    Type: Grant
    Filed: January 10, 2020
    Date of Patent: May 31, 2022
    Assignee: TCL CHINA STAR OPTOELECTRONICS TECHNOLOGY CO., LTD.
    Inventor: Yunna Chen
  • Patent number: 11336819
    Abstract: Methods and apparatus to capture photographs using mobile devices are disclosed. An example apparatus includes a photograph capturing controller to capture a first photograph. The apparatus further includes a blurriness analyzer to determine a probability of blurriness of the first photograph. The probability of blurriness is based on an analysis of a portion of the first photograph, the portion excluding a region of the first photograph associated with an auto-focus operation. The example apparatus also includes a photograph capturing interface to prompt a user to capture a new photograph to replace the first photograph when the probability of blurriness exceeds a blurriness threshold.
    Type: Grant
    Filed: July 17, 2020
    Date of Patent: May 17, 2022
    Assignee: The Nielsen Company (US), LLC
    Inventors: Diego García Morate, Antonio Hurtado Garcia, Javier Tovar Velasco, Carlos Barrales Ruiz
  • Patent number: 11301957
    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: July 22, 2019
    Date of Patent: April 12, 2022
    Assignee: Sentera, Inc.
    Inventors: Eric Taipale, Andrew Muehlfeld
  • Patent number: 11282173
    Abstract: A non-local means method is insufficient in its noise reduction effect or edge retainability due to a perfect match between blocks in a case where a reference pixel matches a target pixel. Therefore, information on a target region and plural reference regions is obtained for the target pixel. Whether the target region matches any one of the reference regions is determined from the obtained information. Switching between weight derivation methods based on similarity between the target region and the reference region is performed according to a determined result.
    Type: Grant
    Filed: November 8, 2019
    Date of Patent: March 22, 2022
    Assignee: CANON KABUSHIKI KAISHA
    Inventors: Kazuhiro Yahata, Yoshitaka Sasaki
  • Patent number: 11275495
    Abstract: User interactions with information handling systems can be improved by providing real-time feedback to the user during use of an application on the information handling system. A user's focused attention can be determined and the user interface elements in an application window be customized to the user. The user's focus attention thus changes the display of user interface elements on the screen. Using such a technique, user interface elements of lower importance can be de-emphasized or removed from the application window, which improves the user's access to user interface elements of greater importance.
    Type: Grant
    Filed: January 28, 2020
    Date of Patent: March 15, 2022
    Assignee: Dell Products L.P.
    Inventors: Marc Randall Hammons, Erik Summa, David Joseph Zavelson
  • Patent number: 11272146
    Abstract: Methods and apparatus for providing adaptive lens shading correction in at least a portion of a shaded image frame perform luminance lens shading correction for a portion of the shaded image frame and detect a color flat area in the shaded image. The methods and apparatus generate a frequency-based color shading profile that includes color shading parameters including an amplitude parameter and phase parameter corresponding to hue distributions from experimental shading data and generate an unshaded image by performing color shading correction on the detected color flat areas of the shaded image frame using the color shading parameters.
    Type: Grant
    Filed: September 16, 2020
    Date of Patent: March 8, 2022
    Assignee: ADVANCED MICRO DEVICES, INC.
    Inventor: JinYun Pan
  • Patent number: 11257510
    Abstract: Isolating and amplifying a conversation between selected participants is provided. A plurality of spectral masks is received. Each spectral mask in the plurality corresponds to a respective participant in a selected group of participants included in a conversation. A composite spectral mask is generated by additive superposition of the plurality of spectral masks. The composite spectral mask is applied to sound captured by a microphone to filter out sounds that do not match the composite spectral mask and amplifying remaining sounds that match the composite spectral mask.
    Type: Grant
    Filed: December 2, 2019
    Date of Patent: February 22, 2022
    Assignee: International Business Machines Corporation
    Inventors: Jeb R. Linton, Jonathan Samn, Poojitha Bikki, Minsik Lee, Satya Sreenivas
  • Patent number: 11244428
    Abstract: An image processing apparatus includes a correction unit configured to correct first image data acquired via an image pickup optical system and to generate second image data using a filter generated based on a characteristic of the image pickup optical system, a decomposition unit configured to decompose each of the first image data and the second image data into a first frequency component and a second frequency component, a combination unit configured to combine the first frequency component of the first image data and the first frequency component of the second image data with each other, and a generation unit configured to generate third image data based on a frequency component including the first frequency component combined by the combination unit and the second frequency component of the second image data.
    Type: Grant
    Filed: June 9, 2020
    Date of Patent: February 8, 2022
    Assignee: Canon Kabushiki Kaisha
    Inventor: Kazuya Tsuyama
  • Patent number: 11238563
    Abstract: The present invention discloses a noise processing method and apparatus. The method includes: selecting a pixel in an area array, which is formed by arranging a plurality of pixels in a matrix; obtaining pre-stored depth information corresponding to the pixel; performing pixel dispersion calculation according to the depth information corresponding to the pixel, to obtain at least one dispersion of the pixel, the dispersion being used to indicate a degree of dispersion between the pixel and another pixel in the area array; and identifying the pixel as a noise and removing the pixel from the area array when the at least one dispersion of the pixel is greater than a preset threshold.
    Type: Grant
    Filed: January 10, 2020
    Date of Patent: February 1, 2022
    Assignee: AUTEL ROBOTICS CO., LTD.
    Inventor: Yupeng Jian
  • Patent number: 11238297
    Abstract: In one implementation, a method includes: obtaining an input image, wherein the input image is captured by an image sensor having a rotational orientation with respect to a direction of gravity; obtaining a gravity direction estimation associated with the rotational orientation of the sensor; generating, from the input image, a rotationally preprocessed input image by applying one or more transformations to the input image based on the gravity direction estimation; providing the rotationally preprocessed input image to the machine learning sub-system; and identifying, using the machine learning sub-system, a visual feature within the rotationally preprocessed input image.
    Type: Grant
    Filed: September 24, 2019
    Date of Patent: February 1, 2022
    Assignee: APPLE INC.
    Inventors: Oliver Thomas Ruepp, Vimal Thilak
  • Patent number: 11227365
    Abstract: Various techniques are provided for reducing noise in captured image frames. In one example, a method includes determining row values for image frames comprising scene information and noise information. The method also includes performing first spectral transforms in a first domain on corresponding subsets of the row values to determine first spectral coefficients. The method also includes performing second spectral transforms in a second domain on corresponding subsets of the first spectral coefficients to determine second spectral coefficients. The method also includes selectively adjusting the second spectral coefficients. The method also includes determining row correction terms based on the adjusted second spectral coefficients to reduce the noise information of the image frames. Additional methods and systems are also provided.
    Type: Grant
    Filed: November 20, 2019
    Date of Patent: January 18, 2022
    Assignee: FLIR Systems, Inc.
    Inventors: Stephanie Lin, Nicholas Högasten
  • Patent number: 11195326
    Abstract: Described herein are techniques for improving the effectiveness of depth culling. In a first technique, a binner is used to sort primitives into depth bins. Each depth bin covers a range of depths. The binner transmits the depth bins to the screen space pipeline for processing in near-to-far order. Processing the near bins first results in the depth buffer being updated, allowing fragments for the primitives in the farther bins to be culled more aggressively than if the depth binning did not occur. In a second technique, a buffer is used to initiate two-pass processing through the screen space pipeline. In the first pass, primitives are sent down to update the depth block and are then culled. The fragments are processed normally in the second pass, with the benefit of the updated depth values.
    Type: Grant
    Filed: September 21, 2018
    Date of Patent: December 7, 2021
    Assignee: Advanced Micro Devices, Inc.
    Inventors: Ruijin Wu, Young In Yeo, Sagar S. Bhandare, Vineet Goel, Martin G. Sarov, Christopher J. Brennan
  • Patent number: 11188790
    Abstract: Methods are provided for training and validating deep learning models for visual search and related tasks as they pertain to fashion items such as garments. The methods presented address the special needs of visual search as it pertains to fashion and related industries by generating large numbers of synthetic images or videos for training deep learning models, and also for validating those models. Given a 3D model of a target garment, the methods select appropriate 3D models for humans and scenes, and also selects various values for the customizable parameters of each of the 3D models, and then renders an image or video. A dataset comprising such synthetic images can be blended with real-world tagged images to create composite datasets for training.
    Type: Grant
    Filed: March 6, 2019
    Date of Patent: November 30, 2021
    Inventors: Rajesh Kumar, Sridhar Manthani
  • Patent number: 11176428
    Abstract: A method and apparatus is provided to reduce the noise in medical imaging by training a deep learning (DL) network to select the optimal parameters for a convolution kernel of an adaptive filter that is applied in the data domain. For example, in X-ray computed tomography (CT) the adaptive filter applies smoothing to a sinogram, and the optimal amount of the smoothing and orientation of the kernel (e.g., a bivariate Gaussian) can be determined on a pixel-by-pixel basis by applying a noisy sinogram to the DL network, which outputs the parameters of the filter (e.g., the orientation and variances of the Gaussian kernel). The DL network is trained using a training data set including target data (e.g., the gold standard) and input data. The input data can be sinograms generated by a low-dose CT scan, and the target data generated by a high-dose CT scan.
    Type: Grant
    Filed: April 1, 2019
    Date of Patent: November 16, 2021
    Assignee: CANON MEDICAL SYSTEMS CORPORATION
    Inventors: Tzu-Cheng Lee, Jian Zhou, Zhou Yu
  • Patent number: 11170554
    Abstract: Techniques for reconstructing three-dimensional face images are described herein. The disclosed techniques include acquiring a real two-dimensional face key point and a predicted two-dimensional face key point; solving a first loss function consisting of the real two-dimensional face key point, the predicted two-dimensional face key point and a preset additional regular constraint term to iteratively optimize an expression coefficient, where the additional regular constraint term is used for constraining the expression coefficient such that the expression coefficient represents a real state of a face; and reconstructing a three-dimensional face image based on the expression coefficient.
    Type: Grant
    Filed: November 27, 2018
    Date of Patent: November 9, 2021
    Assignee: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD.
    Inventor: Zhixing Chen
  • Patent number: 11164297
    Abstract: To improve image quality of an image after correction, An image processing device 100 includes: a correction unit 110 for generating a plurality of correction images from an image by using a plurality of correction methods; an evaluation unit 120 for evaluating the image or each of the plurality of correction images for each of areas constituting the image or the correction image; and a synthesis unit 130 for synthesizing the plurality of correction images according to an evaluation result by the evaluation unit 120.
    Type: Grant
    Filed: August 9, 2017
    Date of Patent: November 2, 2021
    Assignee: NEC CORPORATION
    Inventor: Eiji Kaneko
  • Patent number: 11164320
    Abstract: A corresponding region movement amount calculation unit calculates the amount of movement of each of a plurality of corresponding characteristic regions between a reference image and a base image. A clustering processing unit groups one or more characteristic regions exhibiting a substantially identical tendency in the calculated amounts of movement as belonging to a plane group located on the same plane, and classifies the plurality of characteristic regions in one or more plane groups. A projection transform matrix calculation unit calculates one or more projection transform matrices, by using the amounts of movement of the characteristic regions and the result of the grouping performed by the clustering processing unit.
    Type: Grant
    Filed: June 12, 2020
    Date of Patent: November 2, 2021
    Assignee: OLYMPUS CORPORATION
    Inventor: Atsuro Okazawa
  • Patent number: 11164293
    Abstract: A level of detail-transformation adaptive enhancement method for image contrast includes: dividing a remote sensing image into a plurality images of different levels of detail, the lowest level of detail defined as L and the highest level of detail defined as H, and gradually transforming an image Imagei of an arbitrary level of detail i between the image ImageH of the highest level of detail H and the image ImageL of the lowest level of detail L from ImageL to ImageH through the following equation: Imagei=Ri×ImageH+(1?Ri)×ImageL. The image ImageH of the highest level of detail H is an image ImageACE produced with adaptive contrast enhancement processing, or an image produced with a contrast enhancement method such as Gaussian or histogram equalization; the image ImageL of the lowest level of detail L is an image ImageLCE produced by common linear contrast enhancement.
    Type: Grant
    Filed: January 22, 2020
    Date of Patent: November 2, 2021
    Assignee: NATIONAL CHENG KUNG UNIVERSITY
    Inventor: Cheng-Chien Liu
  • Patent number: 11155725
    Abstract: A method and system for protecting video and image files processes from original files to detect skin tones of persons appearing in the media. Pixels determined to contain skin tones are blurred or blacked out, and the pixel locations and their original color values are stored in a metadata file. The metadata file is encrypted and stored with the redacted video file. Thereafter, when an authorized person wants to see an unredacted version of the video, the system decrypts the metadata and reconstituted the video, replacing the redacted pixels with their original color values, and inserting a unique watermark into the video that identifies the requesting person. The watermarked video is then provided to the requesting person.
    Type: Grant
    Filed: March 22, 2019
    Date of Patent: October 26, 2021
    Assignee: NOA, INC.
    Inventors: Jaime A. Borras, Siddharth Roheda
  • Patent number: 11151696
    Abstract: An image processing apparatus for obtaining an output image by performing a filter processing of an input image, includes a setting unit configured to set a plurality of local regions in the input image, a deriving unit configured to derive a plurality of coefficients corresponding to each of the plurality of local regions based on statistics indicating variations in pixel values in the plurality of local regions, and a filter processing unit configured to obtain an output pixel value by performing a liner transformation of the input image based on the plurality of the coefficients, wherein the plurality of local regions include a region that is partitioned diagonally to a raster scan direction; wherein the filter processing unit performs the liner transformation of the input image based on a coefficient adaptively selected from the plurality of coefficients.
    Type: Grant
    Filed: December 18, 2019
    Date of Patent: October 19, 2021
    Assignee: MORPHO, INC.
    Inventor: Hiroshi Koyama
  • Patent number: 11145032
    Abstract: A noise reduction unit reduces color noise of an input image to generate a noise-reduced image. A first generation unit generates a color difference signal from the noise-reduced image. A reduction processing unit generates hierarchical images including at least two or more reduced images from the noise-reduced image. A second generation unit generates coloring-suppressed color difference signals from the reduced images. A combining unit combines the color difference signal generated by the first generation unit with each of the color difference signals generated by the second generation unit. The second generation unit selects one of the color difference signals of the reduced images for each pixel based on magnitude of each of the color difference signals of the reduced images, to generate the coloring-suppressed color difference signals.
    Type: Grant
    Filed: October 10, 2019
    Date of Patent: October 12, 2021
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Atsushi Takahama
  • Patent number: 11128822
    Abstract: An “Adaptive Exposure Corrector” performs automated real-time exposure correction of individual images or image sequences of arbitrary length. “Exposure correction” is defined herein as automated adjustments or corrections to any combination of shadows, highlights, high-frequency features, and color saturation of images. The Adaptive Exposure Corrector outputs perceptually improved images based on image ISO and camera ISO capabilities in combination with camera noise characteristics via exposure corrections by a variety of noise-aware image processing functions. An initial calibration process adapts these noise aware image processing functions to noise characteristics of particular camera models and types in combination with particular camera ISO settings. More specifically, this calibration process precomputes a Noise Aware Scaling Function (NASF) and a Color Scalar Function (CSF).
    Type: Grant
    Filed: July 26, 2016
    Date of Patent: September 21, 2021
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Lu Yuan, Sing Bing Kang, Chintan A. Shah
  • Patent number: 11074678
    Abstract: Embodiments relate to biasing an image noise filter to reduce edge and texture blurring of image data. Pixel values used to determine photometric coefficients for a bilateral filter are modified by offset values. The offset value for a pixel value is determined by applying a high pass filter to the pixel (referred to as the center pixel) and neighboring pixels of the center pixel. By adding the offset value to the center pixel value, the pixel value difference between the neighboring pixels and the center pixel becomes smaller for pixels on the same side of an edge as the center pixel. Thus, pixels on the same side of the edge get more weight in the bilateral noise filter. Conversely, pixels on the opposite side of the edge as the center pixel get less weight in the bilateral filter. As a result, the biased bilateral filter reduces blurring of edges and increases preservation of texture in the image data.
    Type: Grant
    Filed: April 24, 2019
    Date of Patent: July 27, 2021
    Assignee: Apple Inc.
    Inventors: Sheng Lin, Wu Cheng, Maxim Smirnov
  • Patent number: 11068694
    Abstract: A system and method for analyzing images using a non-transitory programmable device is disclosed. A user interface generator operating on the non-transitory programmable device receives specifications of a first image of a biological sample and a first image analysis step. A sequencer operating on the non-transitory programmable device applies the first image analysis step to the first image to develop annotated training data, and a machine learning system trainer operating on the non-transitory programmable device trains an untrained machine learning system to develop a trained machine learning system. When the trained machine learning system is presented with the first image as an input, the trained machine learning system develops a prediction of the annotated training data.
    Type: Grant
    Filed: January 23, 2019
    Date of Patent: July 20, 2021
    Assignee: Molecular Devices, LLC
    Inventors: Avrum Cohen, Dihui Hong, Stephen Rhein
  • Patent number: 11055877
    Abstract: A gradient calculation unit calculates an image gradient on a pixel-by-pixel basis in each of a plurality of images. A scale search unit calculates a scale score based on degree of spatial frequency components for each pixel in each of the images. A gradient score calculation unit calculates, for each pixel, a gradient score on the basis of the image gradient and the scale score. A gradient finalization unit calculates, using the gradient score and, as a target gradient, an image gradient of each pixel in a combined image. On the basis of the target gradient, a coefficient calculation unit calculates, for each pixel of the combined image, a coefficient of base vectors constituting a preset base vector group in the combined image. A combining unit generates the combined image through linear combination of the base vectors based on the calculated coefficients.
    Type: Grant
    Filed: July 13, 2017
    Date of Patent: July 6, 2021
    Assignee: NEC CORPORATION
    Inventor: Takashi Shibata
  • Patent number: 11030715
    Abstract: An image processing method includes obtaining a difference map of an original image, obtaining an edge feature parameter of a first pixel in an intermediate image based on a pixel value of a pixel in the difference map, obtaining an edge feature parameter of a second pixel in a target image based on the edge feature parameter, and obtaining the target image based on the edge feature parameter of the second pixel.
    Type: Grant
    Filed: August 19, 2019
    Date of Patent: June 8, 2021
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventor: Chenglin Zheng
  • Patent number: 11022633
    Abstract: Systems and methods relating to fault detection and diagnosis. Signals received from sensors are first filtered to remove noise and are then analyzed using wavelet packet transform (WPT) based PCA. The results of the PCA analysis are then automatically classified to thereby quickly and easily determine what issues there may be in a finished product or in a machine being monitored.
    Type: Grant
    Filed: April 28, 2017
    Date of Patent: June 1, 2021
    Assignee: McMaster University
    Inventors: Mahmoud Ismail, Saeid Habibi, Samir Ziada
  • Patent number: 11017541
    Abstract: Techniques related to detecting texture content in an input image are discussed. Such techniques include accumulating pixel-wise directional gradient counts for positive and negative gradients for a first direction and positive and negative gradients for a second direction for pixels in a pixel window. A texture value for the target pixel of the window is determined based on a sum of a minimum of the positive and negative gradients for a first direction and a minimum of the positive and negative gradients for a second direction.
    Type: Grant
    Filed: June 18, 2019
    Date of Patent: May 25, 2021
    Assignee: Intel Corporation
    Inventors: Rony Zatzarinni, Mor Hadar, Anatoly Litvinov
  • Patent number: 11010880
    Abstract: An image processing apparatus includes an input unit for inputting an image, a division unit for dividing the inputted image into a plurality of divided regions, an obtaining unit for obtaining a feature amount of the image for each of the divided regions, a generation unit for generating a compression curve for each divided region, and a compression unit for generating an output image by performing compression of a dynamic range using the compression curve for each of the divided regions. The generation unit generates the compression curve for each of the divided regions so that a slope of the compression curve for each of the divided regions matches in a range from a luminance of a dark region of the image to a luminance of a predetermined brightness.
    Type: Grant
    Filed: July 1, 2019
    Date of Patent: May 18, 2021
    Assignee: Canon Kabushiki Kaisha
    Inventors: Maya Yazawa, Tetsuya Suwa, Hidetsugu Kagawa, Shuhei Ogawa
  • Patent number: 11012626
    Abstract: An electronic device is provided. The electronic device includes a camera, a display, a memory, a communication module, and a processor configured to identify a plurality of parameter sets related to image capturing from an external device using the communication module, provide, in a first preview, at least part of one or more images using the display during at least part of obtaining the one or more images using the camera, generate one or more first corrected images to which a first parameter set among the plurality of parameter sets is applied, using the one or more images, generate one or more second corrected images to which a second parameter set among the plurality of parameter sets is applied, using the one or more images, identify priority for the plurality of parameter sets, and provide, in a second preview, one or more among the one or more first corrected images and the one or more second corrected images according to the priority during at least part of providing the first preview.
    Type: Grant
    Filed: June 5, 2019
    Date of Patent: May 18, 2021
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Junghoon Kim, Hongsuk Choi
  • Patent number: 11010873
    Abstract: Embodiments relate to enhancing local contrast in an image. A bilateral high pass filter generates a high frequency value for each pixel of an input image, based on a convolution using photometric kernel coefficients associated with other pixels around the pixel. A noise control circuit generates a modulated high frequency value for the pixel based on a noise model for the image defining a noise threshold value for modifying the high frequency value. The modulated high frequency value for the pixel is then combined with a pixel value of the pixel to generate an enhanced value for the pixel. Enhanced values for pixels of the image may be generated to provide the local contrast enhancement for the input image.
    Type: Grant
    Filed: May 12, 2020
    Date of Patent: May 18, 2021
    Assignee: Apple Inc.
    Inventor: Maxim Smirnov
  • Patent number: 11003931
    Abstract: The present application discloses a vehicle monitoring method and apparatus, processor, and image acquisition device. The method includes: identifying a vehicle window area image in a vehicle image obtained through monitoring; performing feature identification on the vehicle window area image to obtain an identification result of a target feature; performing human eye sensory processing on the vehicle image and the vehicle window area image respectively, and stitching the processed vehicle image and the processed vehicle window area image to obtain a processed image; and outputting the identification result of the target feature and the processed image. The present application solves the technical problem of relatively low identification rate in vehicle monitoring by image detection.
    Type: Grant
    Filed: May 25, 2016
    Date of Patent: May 11, 2021
    Assignee: Hangzhou Hikvision Digital Technology Co., Ltd.
    Inventors: Qun Wang, Jun Chen, Jinhong Qi, Binghua Luo
  • Patent number: 11004179
    Abstract: Image blurring methods and apparatuses, storage media, and electronic devices. The method can be carried out by the apparatuses, media and devices, and includes: generating a second image having second pixel points corresponding to first pixel points of a first image; determining, according to blurring desired data of the first pixel points, respective initial blurring weight values of the corresponding second pixel points; performing at least one update on at least one of the second pixel points, the update including: updating, based on a first pixel value of the first pixel point and a current blurring weight value of the second pixel point corresponding to the based first pixel point, a current pixel value and a current blurring weight value of at least one neighboring second pixel point of the based corresponding second pixel point; and obtaining a blurring result of the first image according to the updated second image.
    Type: Grant
    Filed: December 27, 2018
    Date of Patent: May 11, 2021
    Assignee: SHENZHEN SENSETIME TECHNOLOGY CO., LTD.
    Inventor: Qiong Yan
  • Patent number: 11004225
    Abstract: A self-contained, low-cost, low-weight guidance system for vehicles is provided. The guidance system can include an optical camera, a case, a processor, a connection between the processor and an on-board control system, and computer algorithms running on the processor. The guidance system can be integrated with a vehicle control system through “plug and play” functionality or a more open Software Development Kit. The computer algorithms re-create 3D structures as the vehicle travels and continuously updates a 3D model of the environment. The guidance system continuously identifies and tracks terrain, static objects, and dynamic objects through real-time camera images. The guidance system can receive inputs from the camera and the onboard control system. The guidance system can be used to assist vehicle navigation and to avoid possible collisions. The guidance system can communicate with the control system and provide navigational direction to the control system.
    Type: Grant
    Filed: March 25, 2019
    Date of Patent: May 11, 2021
    Assignee: Iris Automation, Inc.
    Inventors: Alexander Harmsen, James Howard, Patricio Alejandro Galindo
  • Patent number: 10997501
    Abstract: In some embodiments, noise data may be used to train a neural network (or other prediction model). In some embodiments, input noise data may be obtained and provided to a prediction model to obtain an output related to the input noise data (e.g., the output being a prediction related to the input noise data). One or more target output indications may be provided as reference feedback to the prediction model to update one or more portions of the prediction model, wherein the one or more portions of the prediction model are updated based on the related output and the target indications. Subsequent to the portions of the prediction model being updated, a data item may be provided to the prediction model to obtain a prediction related to the data item (e.g., a different version of the data item, a location of an aspect in the data item, etc.).
    Type: Grant
    Filed: February 10, 2020
    Date of Patent: May 4, 2021
    Assignee: Aivitae LLC
    Inventors: Bob Sueh-chien Hu, Joseph Yitang Cheng
  • Patent number: 10972672
    Abstract: A method of generating an image from multiple cameras having different focal lengths is described. The method comprising receiving a wide image and a tele image; aligning the wide image and the tele image to overlap a common field of view; correcting for photometric differences between the wide image and the tele image; selecting a stitching seam for the wide image and the tele image; and joining the wide image and the tele image to generate a composite image, wherein a first portion of the composite image on one side of the stitching seam is from the wide image and a second portion of the composite image on the other side of the stitching seam is from the tele image. An electronic device for generating an image is also described.
    Type: Grant
    Filed: February 17, 2018
    Date of Patent: April 6, 2021
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Ruiwen Zhen, John W. Glotzbach, Raja Bala, Hamid Rahim Sheikh
  • Patent number: 10970894
    Abstract: A method for rendering a computer image includes, for each pixel of a plurality of N×M pixels forming a tile, determining a plurality of masks for the pixel, wherein N and M denote integers larger than 1, and wherein each mask identifies a respective subset of the pixels that are equidistant from the pixel and located at a respective distance from the pixel. The method further includes: determining an active mask for the tile, the active mask identifying active pixels of the pixels, each of the active pixels being determined as having color information; based on the active mask, identifying an empty pixel of the pixels, the empty pixel lacking color information; and determining at least a first nearest active pixel that is nearest to the empty pixel. The determining includes comparing the active mask with at least one mask of the masks for the empty pixel.
    Type: Grant
    Filed: December 16, 2019
    Date of Patent: April 6, 2021
    Inventor: Toshiaki Kato
  • Patent number: 10962630
    Abstract: A system and method for calibrating sensors may include one or more processors, a first sensor configured to obtain a two-dimensional image, a second sensor configured to obtain three-dimensional point cloud data, and a memory device. The memory device stores a data collection module and a calibration module. The data collection module has instructions that configure the one or more processors to obtain the two-dimensional image and the three-dimensional point cloud data. The calibration module has instructions that configure the one or more processors to determine and project a three-dimensional point cloud edge of the three-dimensional point cloud data onto the two-dimensional image edge, apply a branch-and-bound optimization algorithm to a plurality of rigid body transforms, determine a lowest cost transform of the plurality of rigid body transforms using the branch-and-bound optimization algorithm, and calibrate the first sensor with the second sensor using the lowest cost transform.
    Type: Grant
    Filed: October 18, 2019
    Date of Patent: March 30, 2021
    Assignees: Toyota Research Institute, Inc., The Regents of the University of Michigan
    Inventors: Jeffrey M. Walls, Steven A. Parkison, Ryan W. Wolcott, Ryan M. Eustice
  • Patent number: 10957025
    Abstract: Aspects vary object illumination values within a digital photograph in response to relocating light-emitting objects. Embodiments generate a three-dimensional model of a digital photograph defined by pixel data that plots a representation of a light source at a first location in a three-dimensional physical space relative to plotted locations of remaining other digital photograph pixels; relocate the representation of the light source within the three-dimensional model to a different, second location within the model three-dimensional physical space; revise a brightness value of a first pixel in proportion to an amount of a change in distance from the first pixel to the second location, relative to a distance to the first, plotted light source location; and generate a revised version of the photograph from the pixel data inclusive of the revised brightness value of the first pixel.
    Type: Grant
    Filed: December 3, 2018
    Date of Patent: March 23, 2021
    Assignee: International Business Machines Corporation
    Inventors: Sarbajit K. Rakshit, James E. Bostick, Martin G. Keen, John M. Ganci, Jr.