Image Segmentation Using Color Patents (Class 382/164)
  • Patent number: 10715801
    Abstract: A method of palette management for palette coding in a video coding system receives input data associated with a current block in a high-level picture structure and initializes a palette predictor in the high-level picture structure before a corresponding palette of a first palette-coded block in the high-level picture structure is coded. If a palette mode is selected for the current block, the method applies the palette coding to the current block using a current palette and updates the palette predictor based on the current palette to generate an updated palette predictor for a next block coded in the palette mode.
    Type: Grant
    Filed: May 18, 2017
    Date of Patent: July 14, 2020
    Assignee: HFI Innovation Inc.
    Inventors: Wang-Lin Lai, Yu-Chen Sun, Shan Liu, Xiaozhong Xu, Tzu-Der Chuang, Ding-Yun Chen, Yu-Wen Huang
  • Patent number: 10713456
    Abstract: Signal detection and recognition employees coordinated illumination and capture of images under to facilitate extraction of a signal of interest. Pulsed illumination of different colors facilitates extraction of signals from color channels, as well as improved signal to noise ratio by combining signals of different color channels. The successive pulsing of different color illumination appears white to the user, yet facilitates signal detection, even for lower cost monochrome sensors, as in barcode scanning and other automatic identification equipment.
    Type: Grant
    Filed: March 4, 2019
    Date of Patent: July 14, 2020
    Assignee: Digimarc Corporation
    Inventors: Jacob L. Boles, Alastair M. Reed, John D. Lord
  • Patent number: 10707895
    Abstract: Methods for converting an n-bit number into an m-bit number for situations where n>m and also for situations where n<m, where n and m are integers. The methods use truncation or bit replication followed by the calculation of an adjustment value which is applied to the replicated number.
    Type: Grant
    Filed: June 28, 2019
    Date of Patent: July 7, 2020
    Assignee: Imagination Technologies Limited
    Inventor: Simon Fenney
  • Patent number: 10701241
    Abstract: An image processing apparatus includes a detection unit, a determination unit, a decision unit, and a processing unit. The detection unit detects an isolated pixel included in an image. The determination unit determines whether the isolated pixel detected by the detection unit changes brighter or darker by edge enhancement processing. The decision unit decides an edge enhancement amount of the isolated pixel based on a determination result of the determination unit. The processing unit performs the edge enhancement processing on the isolated pixel, based on the edge enhancement amount decided by the decision unit.
    Type: Grant
    Filed: September 28, 2017
    Date of Patent: June 30, 2020
    Assignee: Canon Kabushiki Kaisha
    Inventor: Hirokazu Tamura
  • Patent number: 10685446
    Abstract: A system, article, and method of recurrent semantic segmentation for image processing by factoring historical semantic segmentation.
    Type: Grant
    Filed: January 12, 2018
    Date of Patent: June 16, 2020
    Assignee: Intel Corporation
    Inventors: Shahar Fleishman, Naomi Ken Korem, Mark Kliger
  • Patent number: 10685443
    Abstract: Techniques for cloud detection and cloud coverage determination are described herein. The disclosed techniques include detecting a plurality of color clusters among a plurality of data elements of an image, associating at least one of the plurality of color clusters with a cloud based on a characteristic color of the cloud, and determining a number of data elements within the at least one of the plurality of color clusters associated with the cloud. The disclosed techniques also include detecting a location of an object indicative of a cloud in the image based at least in part on training data and a plurality of features extracted from the image, detecting an edge of the object indicative of the cloud at the location, and determining a number of data elements within the edge of the object indicative of the cloud.
    Type: Grant
    Filed: April 20, 2018
    Date of Patent: June 16, 2020
    Assignee: WEATHER INTELLIGENCE TECHNOLOGY, INC
    Inventors: Simeng Yan, Juntao Xiao
  • Patent number: 10686927
    Abstract: A non-transitory computer-readable medium having a computer program readable by a computer of a portable device connectable to an image input device and image output device and including a memory storing external programs activated by the computer program, the computer program causes the portable device to perform: receiving a user operation on a first screen including first objects corresponding to the external programs; determining the designated program when the first object is designated; when the designated program has a first function of executing processing for the input data, instructing the image input device to execute an input operation and performing first post-processing; and when the designated program has the second function of enabling a user to designate the output data, performing pre-processing and controlling the image output device to execute output operation for the output data.
    Type: Grant
    Filed: February 27, 2019
    Date of Patent: June 16, 2020
    Assignee: Brother Kogyo Kabushiki Kaisha
    Inventor: Norihiko Asai
  • Patent number: 10657603
    Abstract: A system and method classify insurance documents. The system and method receive a request to access documents from an assessment queue stored in a memory of a device where each of the documents contain insurance data and have an associated destination and associated metadata. The system and method convert the set of documents encoded in a first file format to a second file format to remove the metadata. The system and method partition each document of the set of documents into separate stand-alone documents and converts each of the partitioned documents into separate recognition vectors. The system and method classifies the partitioned documents through an additive learning algorithm in which routing data is embedded in second metadata and merge the classified partitioned documents. The merged documents are routed to a remote destination independent of the originally intended destination and the associated metadata.
    Type: Grant
    Filed: April 3, 2019
    Date of Patent: May 19, 2020
    Assignee: Progressive Casualty Insurance Company
    Inventors: Jarrod D. Harding, Rick A. Bliss
  • Patent number: 10650333
    Abstract: A task management system and method that enables task assignment, that supports task monitoring, that produces task reminders, that verifies task completion, and that assigns rewards or penalties based on task performance. The task management system implements a method of receiving an indication of a particular task to be completed and first image data that corresponds to the particular task. The method further includes receiving second image data that corresponds to a second image, and processor comparing the first image data and the second image data. The processor can determine whether the particular task is completed based on comparing the first image data and the second image data. A notification indicating whether the particular task is completed is then sent.
    Type: Grant
    Filed: November 22, 2017
    Date of Patent: May 12, 2020
    Assignee: Location Labs, Inc.
    Inventor: Andrew Weiss
  • Patent number: 10638131
    Abstract: A content providing apparatus is disclosed. The content providing apparatus comprises: a communication unit for communicating with an external apparatus; an image processing unit for generating a compressed image by image-processing an input original image; and a control unit for controlling the communication unit to divide the original image into one or more regions based on the image quality, to obtain characteristic information for each region from the respective regions, and to transmit the obtained characteristic information for each region together with the compressed image to the external apparatus. As the result, the display apparatus may perform image quality improvement operation so that the image quality is close to the original quality level by extracting information required for improving the image quality and transmitting the same together with a compressed image in production and encoding steps before transmitting the image.
    Type: Grant
    Filed: December 7, 2015
    Date of Patent: April 28, 2020
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Woo-seok Kang, Bong-joe Kim, Se-hyeok Park, Jong-sul Min
  • Patent number: 10628708
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for utilizing a deep neural network-based model to identify similar digital images for query digital images. For example, the disclosed systems utilize a deep neural network-based model to analyze query digital images to generate deep neural network-based representations of the query digital images. In addition, the disclosed systems can generate results of visually-similar digital images for the query digital images based on comparing the deep neural network-based representations with representations of candidate digital images. Furthermore, the disclosed systems can identify visually similar digital images based on user-defined attributes and image masks to emphasize specific attributes or portions of query digital images.
    Type: Grant
    Filed: May 18, 2018
    Date of Patent: April 21, 2020
    Assignee: ADOBE INC.
    Inventors: Zhe Lin, Xiaohui Shen, Mingyang Ling, Jianming Zhang, Jason Kuen, Brett Butterfield
  • Patent number: 10628713
    Abstract: A mobile terminal includes a memory and a processor coupled to the memory, wherein the processor executes a process including acquiring a frame acquired by image capturing, detecting document position data of a document from the frame, determining a document type of the document, calculating image quality of document image data of the document on the basis of the document position data and the document type, determining whether the image quality is at a character recognizable level, and acquiring a frame acquired by the image recapturing when it is determined that the image quality is not at the character recognizable level.
    Type: Grant
    Filed: May 31, 2018
    Date of Patent: April 21, 2020
    Assignee: PFU Limited
    Inventors: Masayoshi Hayashi, Kiyoto Kosaka
  • Patent number: 10614118
    Abstract: Images are encoded into multidimensional vectors in a high-dimensional space utilizing an image model and textual content utilizing a text model. At least one of the image model and/or the text model are tuned such that the point within the multidimensional space pointed to by a vector encoded from an image is proximate to, as determined within the context of that multidimensional space, a point pointed to by a vector encoded from correlated textual content. Received images and textual content are encoded into image vectors and text vectors, respectively, and stored in an image graph and text graph, respectively. An input image can then be encoded as an input image vector and utilized to find close vectors in both the image graph and the text graph, thereby enabling an input image to be utilized to search textual content without using classifiers to deduce textual content therefrom.
    Type: Grant
    Filed: February 28, 2018
    Date of Patent: April 7, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Jia He, Ruofei Zhang, Keng-Hao Chang, Xiaozong Wang
  • Patent number: 10607318
    Abstract: Systems, methods, and non-transitory computer-readable media can generate an initial alpha mask for an image based on machine learning techniques. A plurality of uncertain pixels is defined in the initial alpha mask. For each uncertain pixel in the plurality of uncertain pixels, a binary value is assigned based on a nearest certain neighbor determination.
    Type: Grant
    Filed: December 20, 2017
    Date of Patent: March 31, 2020
    Assignee: Facebook, Inc.
    Inventors: Jason George McHugh, Michael F. Cohen, Johannes Peter Kopf, Piotr Dollar
  • Patent number: 10595020
    Abstract: A content providing apparatus is disclosed. The content providing apparatus comprises: a communication unit for communicating with an external apparatus; an image processing unit for generating a compressed image by image-processing an input original image; and a control unit for controlling the communication unit to divide the original image into one or more regions based on the image quality, to obtain characteristic information for each region from the respective regions, and to transmit the obtained characteristic information for each region together with the compressed image to the external apparatus. As the result, the display apparatus may perform image quality improvement operation so that the image quality is close to the original quality level by extracting information required for improving the image quality and transmitting the same together with a compressed image in production and encoding steps before transmitting the image.
    Type: Grant
    Filed: December 7, 2015
    Date of Patent: March 17, 2020
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Woo-seok Kang, Bong-joe Kim, Se-hyeok Park, Jong-sul Min
  • Patent number: 10592742
    Abstract: Described is a multiple-camera system and process for re-identifying an agent located in a materials handling facility based on anterior views of agents. An anterior view of a newly detected agent may be partitioned and color signatures generated for each partition. Likewise, stored anterior views of agents (candidate agents) that may potentially be the newly detected agent are partitioned and color signatures generated for each partition. Based on the color signatures, a similarity between the anterior view of the newly detected agent and the candidate agents is determined. The similarity may be used to either determine that the newly detected agent is one of the candidate agents or reduce the set of candidate agents that are considered during a manual review.
    Type: Grant
    Filed: September 28, 2015
    Date of Patent: March 17, 2020
    Assignee: Amazon Technologies, Inc.
    Inventors: Gang Hua, Gerald Guy Medioni
  • Patent number: 10573276
    Abstract: The invention includes a method including the steps of obtaining a plurality of images, each of the images in the plurality having at least one corresponding region, generating a merged image, the merged image also having the corresponding region. The step of generating includes selecting an image source from the plurality of images to source image data for the corresponding region in the merged image by comparing attributes of the corresponding regions of the plurality of images to identify the image source having preferred attributes.
    Type: Grant
    Filed: June 20, 2018
    Date of Patent: February 25, 2020
    Assignee: Hologic, Inc.
    Inventors: Kevin Kreeger, Andrew P. Smith, Ashwini Kshirsagar, Jun Ge, Yiheng Zhang, Haili Chui, Christopher Ruth, Xiangwei Zhang, Liyang Wei, Jay Stein
  • Patent number: 10516808
    Abstract: A scanner reads an original and generates a read image, specifies a first region having a pattern on a wrinkle and a second region having a wrinkle and no pattern from the read image, and performs a wrinkle reduction process in which the wrinkle is not reduced in the first region and the wrinkle is reduced in the second region, included in the read image.
    Type: Grant
    Filed: September 12, 2018
    Date of Patent: December 24, 2019
    Assignee: Seiko Epson Corporation
    Inventor: Tomohiro Nakamura
  • Patent number: 10516889
    Abstract: The precision of up-sampling operations in a layered coding system is preserved when operating on video data with high bit-depth. In response to bit-depth requirements of the video coding or decoding system, scaling and rounding parameters are determined for a separable up-scaling filter. Input data are first filtered across a first spatial direction using a first rounding parameter to generate first up-sampled data. First intermediate data are generated by scaling the first up-sampled data using a first shift parameter. The intermediate data are then filtered across a second spatial direction using a second rounding parameter to generate second up-sampled data. Second intermediate data are generated by scaling the second up-sampled data using a second shift parameter. Final up-sampled data may be generated by clipping the second intermediate data.
    Type: Grant
    Filed: October 23, 2018
    Date of Patent: December 24, 2019
    Assignee: Dolby Laboratories Licensing Corporation
    Inventors: Peng Yin, Taoran Lu, Tao Chen
  • Patent number: 10482360
    Abstract: Provided is a method by which an image forming apparatus forms an image, the method including detecting a boundary area in a portion of image data; determining a direction of the boundary area, a dominant color of the boundary area, and an edge intensity of the boundary area; determining enhancement information with respect to the boundary area based on the direction, the dominant color, and the edge intensity; and forming an image with respect to the image data based on the determined enhancement information.
    Type: Grant
    Filed: December 8, 2015
    Date of Patent: November 19, 2019
    Assignee: Samsung Electronics Co.,, Ltd
    Inventors: Seul-ki Jang, Ji-young Yi
  • Patent number: 10437930
    Abstract: The present disclosure provides a system and method of semiotic digital encoding, transfer, and decoding of semiotic data. In an embodiment, the present disclosure teaches a process and method of taking semantic knowledge/information and converting it into a digital format, allowing that digital format to be transmitted or communicated to a receiver and processing the digital format back to the semantic knowledge/information.
    Type: Grant
    Filed: January 18, 2018
    Date of Patent: October 8, 2019
    Assignee: Bevilacqua Research Corporation
    Inventor: Andy Bevilacqua
  • Patent number: 10402680
    Abstract: A method and an apparatus for extracting a saliency map are provided in the embodiment of the present application, the method includes: conducting first convolution processing, first pooling processing and normalization processing on an original image via a prediction model to obtain eye fixation information from the original image, where the eye fixation information is used for indicating a region at which human eye gaze; conducting second convolution processing and second pooling processing on the original image via the prediction model to obtain semantic description information from the original image; fusing the eye fixation information and the semantic description information via element-wise summation function; and conducting detection processing on the fused eye fixation information and semantic description information via the prediction model to obtain a saliency map from the original image. It is used for improving the efficiency of extracting the saliency map from image.
    Type: Grant
    Filed: August 22, 2017
    Date of Patent: September 3, 2019
    Assignee: BEIHANG UNIVERSITY
    Inventors: Xiaowu Chen, Anlin Zheng, Jia Li, Qinping Zhao, Feng Lu
  • Patent number: 10397438
    Abstract: The present disclosure relates to systems and methods for causing an action to be executed based on whether a detected person is physically present. In one implementation, such a system may include a wearable image sensor configured to capture a plurality of images from the environment of the user of the wearable apparatus and at least one processing device. The at least one processing device may be programmed to analyze at least one of the plurality of images to detect the person; analyze at least one of the plurality of images to determine whether the detected person is physically present in the environment of the user; select at least one action based on whether the detected person is physically present in the environment of the user; and cause the selected at least one action to be executed.
    Type: Grant
    Filed: October 25, 2017
    Date of Patent: August 27, 2019
    Assignee: ORCAM TECHNOLOGIES LTD.
    Inventors: Yonatan Wexler, Amnon Shashua
  • Patent number: 10375275
    Abstract: An image processing apparatus specifies, from among target pixels in a target image, first pixels related to a first color, and determines whether a specific condition is met for each peripheral pixel of the target pixel. The specific condition includes a condition that each peripheral pixel is a candidate for a pixel representing one of colors different from the first color. The apparatus specifies, as a second pixel related to a second color, each peripheral pixel meeting the specific condition. The apparatus performs an image process on target image data by using specified first and second pixels to generate processed image data. In a processed image, first processed pixels correspond to the specified first pixels and have the first color, and second processed pixels correspond to the specified second pixels and have the second color.
    Type: Grant
    Filed: March 23, 2018
    Date of Patent: August 6, 2019
    Assignee: BROTHER KOGYO KABUSHIKI KAISHA
    Inventor: Ryuji Yamada
  • Patent number: 10339636
    Abstract: An image processing apparatus performs: acquiring target image data representing a target image including a plurality of pixels, the target image data including a plurality of pixel values each having a plurality of component values; generating image data, the image data being one of first and second component data respectively including a plurality of first and second pixel values, each of the plurality of first and second pixel values being respectively related to maximum and minimum values among the plurality of component values of corresponding one of the plurality of pixels; calculating a plurality of edge strengths corresponding to respective ones of the plurality of pixels using the image data to generate edge strength data including the plurality of edge strengths; and specifying a plurality of edge pixels included in the target image. The specifying includes binarizing the edge strength data to generate binary image data.
    Type: Grant
    Filed: February 21, 2018
    Date of Patent: July 2, 2019
    Assignee: Brother Kogyo Kabushiki Kaisha
    Inventor: Ryuji Yamada
  • Patent number: 10311327
    Abstract: An image processing apparatus comprises: a colored level calculation unit configured to calculate, for a first region in an image, an index indicating a strength of color; a feature amount calculation unit configured to calculate a first feature amount relating to luminance components in each of the first region and a second region, and a second feature amount relating to color components in the regions; an interest level calculation unit configured to calculate an interest level for the first region based on a difference for the first feature amount between the regions, a difference for the second feature amount between the regions, and an importance for each of the differences; and a region of interest detection unit; wherein the interest level calculation unit determines the importance for the differences based on the index.
    Type: Grant
    Filed: September 29, 2016
    Date of Patent: June 4, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Satoru Kobayashi
  • Patent number: 10303967
    Abstract: Techniques for detecting an active area of interest within video data are disclosed. A videoconferencing system may include a sensor configured to capture sequential frames of video image data during a videoconference, and a processing subsystem. The processing subsystem may be configured to, for a given frame, apply filter(s) to individual pixels of the given frame to identify one or more pixels of interest within the given frame, where the filter(s) include a motion detection filter. The processing subsystem may further apply a multidimensional filter to the one or more pixels of interest, the multidimensional filter specifying one or more programmable density thresholds. The processing subsystem may further designate at least one group of pixels of interest that satisfies the one or more programmable density thresholds as an active area of interest; and control an aspect of the videoconference based at least in part upon the active area of interest.
    Type: Grant
    Filed: August 7, 2018
    Date of Patent: May 28, 2019
    Assignee: LIFESIZE, INC.
    Inventors: Stephen Flosdorf, Sulanka Goonetilleke
  • Patent number: 10248887
    Abstract: An object tracking device and method and image shooting apparatus are provided. The object tracking device includes a processor and a memory, wherein the processor includes an image preprocessing module; a super-pixel matching module; and a background masking module configured to mask a super-pixel image having a matching area, in order to obtain a super-pixel masked image whose background area outside of the matching area is masked. The present invention is able to eliminate obstacles from a output area by a way of background masking, accurately and stably tracking the object.
    Type: Grant
    Filed: April 5, 2017
    Date of Patent: April 2, 2019
    Assignee: SONY CORPORATION
    Inventor: Yoichiro Sato
  • Patent number: 10235785
    Abstract: A storage (240) of an image processing device (100) stores a background image (2410) and a first image (2420) and a second image (2430) that are foreground images with respect to the background image (2410), and a first basic mask image (the first basic mask image (2450) formed from pixels having a pixel value of ‘1’ indicating opacity and pixels having a pixel value of ‘0’ indicating transparence. An acquirer (250) acquires each of these images. An image generator (220) generates a first intermediate image by compositing the first image (2420) onto the background image (2410) only in pixels that are in the same positions as the pixels in the first basic mask image (2450) having the pixel value of ‘1’. The image generator (220) then generates a first composite image by overwriting the second image (2430) onto the first intermediate image only in the pixels that are in the same positions as the pixels in the first basic mask image (2450) having the pixel value of ‘1’.
    Type: Grant
    Filed: October 27, 2014
    Date of Patent: March 19, 2019
    Assignee: LIVE2D INC.
    Inventors: Tetsuya Nakajo, Masayuki Todate
  • Patent number: 10229337
    Abstract: The present invention concerns a method of segmenting a media item comprising media elements.
    Type: Grant
    Filed: February 16, 2016
    Date of Patent: March 12, 2019
    Assignee: ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE (EPFL)
    Inventor: Radhakrishna Shri Venkata Achanta
  • Patent number: 10204438
    Abstract: In some embodiments, the present invention provides for a computer system that may include a camera component configured to acquire a visual content, where the visual content includes a plurality of frames having a visual representation of a person's face; and a processor configured to: train a face detection regressor with a synthetic face model database to obtain a face detection trained regressor; apply, for each frame, the face detection trained regressor to detect or to track the face based on facial features, local features, and a pre-defined hyperparameter; construct an intermediate multi-dimensional face model; apply machine learning to determine features of an intermediate multi-dimensional head model; construct a multi-dimensional avatar; and utilize the multi-dimensional avatar to perform an activity associated with the person.
    Type: Grant
    Filed: April 18, 2018
    Date of Patent: February 12, 2019
    Assignee: Banuba Limited
    Inventors: Yury Hushchyn, Dzmitry Kachatkou
  • Patent number: 10204413
    Abstract: The present invention provides a system and method that uses polar dynamic programming PDP (PDP) method to generate a segmented image of a shape.
    Type: Grant
    Filed: June 30, 2017
    Date of Patent: February 12, 2019
    Assignee: Arizona Board of Regents on Behalf of the University of Arizona
    Inventors: Jose Rosado-Toro, Jeffrey J. Rodriguez, Ryan Avery, Aiden Abidov
  • Patent number: 10198823
    Abstract: Devices and techniques are generally described for segmentation of object image data from background image data. In some examples, the segmentation of object image data may comprise capturing image data comprising color data and depth data. In some examples, the segmentation of object image data may further include separating the depth data into a plurality of clusters of image data, wherein each cluster is associated with a respective range of depth values. In various examples, the segmentation of object image data may comprise selecting a main cluster of image data as corresponding to an object of interest in the image data. In various other examples, the segmentation of object image data may comprise identifying pixels of the main cluster that correspond to the object of interest.
    Type: Grant
    Filed: August 23, 2018
    Date of Patent: February 5, 2019
    Assignee: AMAZON TECHNOLOGIES, INC.
    Inventors: Amit Kumar Agrawal, Abhishek Singh, Visesh Uday Kumar Chari, Lelin Zhang, Qiang Liu, Rohith Mysore Vijaya Kumar, David Ting-Yu Wu
  • Patent number: 10186087
    Abstract: Techniques for occluding augmented reality objects are described in various implementations. In one example implementation, a method may include receiving an image captured by an image capture device and identifying a foreground object depicted in the image. The foreground object may be free of fiducial markers and may be positioned between the image capture device and a background depicted in the image. The method may also include generating an augmented reality image depicting an augmented reality object at least partially occluded by the foreground object such that, when the augmented reality image is displayed, the augmented reality object appears to be positioned behind the foreground object.
    Type: Grant
    Filed: December 6, 2013
    Date of Patent: January 22, 2019
    Assignee: Hewlett-Packard Development Company, L. P.
    Inventors: Stephen Davis, George Saklatvala
  • Patent number: 10184837
    Abstract: The present invention relates to charts, stacks and methods for evaluating skin color of a mammalian subject. The chart may include a substrate and an indicia visible from a first side of the substrate that includes a plurality of images of mammalian skin tones having varying degrees of yellowness, wherein each indicia is correlated with an index value. Also, the present invention relates to packaged topical cosmetic products that include a skin chart as well as to methods for evaluating anti-aging and skin lightening products.
    Type: Grant
    Filed: November 22, 2016
    Date of Patent: January 22, 2019
    Assignee: ACCESS BUSINESS GROUP INTERNATIONAL LLC
    Inventors: Di Qu, Yulia Park
  • Patent number: 10176196
    Abstract: An image processing system for recognizing the scene type of an input image generates an image distance metric from a set of images. The image processing system further extracts image features from the input image and each image in the set of images. Based on the distance metric and the extracted image features, the image processing system computes image feature distances for selecting a subset of images. The image processing system derives a scene type from the scene type of the subset of images. In one embodiment, the image processing system is a cloud computing system.
    Type: Grant
    Filed: June 23, 2015
    Date of Patent: January 8, 2019
    Assignee: Amazon Technologies, Inc.
    Inventors: Yi Li, Tianqiang Liu, Hao Chen, Meng Wang
  • Patent number: 10163244
    Abstract: Methods and systems for creating animation elements from digital drawings. In particular, one or more embodiments detect a digital drawing input stream including a plurality of strokes. One or more embodiments identify a plurality of stroke points for each stroke from the plurality of strokes, and determine a plurality of timestamps for the plurality of stroke points. One or more embodiments generate an animation element based on the plurality of stroke points and the plurality of timestamps. One or more embodiments also receive a selection to insert the animation element into a user interface, and insert the animation element with associated drawing time information and stroke point information into the user interface in response to the received selection.
    Type: Grant
    Filed: February 3, 2016
    Date of Patent: December 25, 2018
    Assignee: ADOBE SYSTEMS INCORPORATION
    Inventors: Sriraj Banerjee, Karnati Penchala Charith Chowdary, Ashish Garg
  • Patent number: 10152653
    Abstract: Examples relate to providing spatial analysis using attribute graphs. In one examples, there are a number of spatial points that each represent characteristics in a dimensional space. Non-data points are generated in the dimensional space, and a Delaunay triangulation is performed using the spatial points and the non-data points to generate a plurality of edges, where interior points of the plurality of non-data points that are in an interior space of the plurality of spatial points are excluded from the Delaunay triangulation. Next, spatial edges from the plurality of edges that each connect a spatial point that is connected to a first mixed edge to another spatial point that is connected to a second mixed edge are identified, where the spatial edges are used to generate a robust contour of a cluster of the spatial points.
    Type: Grant
    Filed: July 31, 2014
    Date of Patent: December 11, 2018
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: Nathan Moroney, Jun Zeng
  • Patent number: 10147288
    Abstract: An alarm method is disclosed. The method may comprise acquiring a monitoring video, detecting whether the monitoring video contains a moving target, determining whether the moving target is a preset object if it is detected that the monitoring video contains the moving target, and forbidding sending corresponding alarm information to a terminal if the moving target is determined to be the preset object.
    Type: Grant
    Filed: March 17, 2016
    Date of Patent: December 4, 2018
    Assignee: Xiaomi Inc.
    Inventors: Tao Zhang, Zhijun Chen, Pingze Wang
  • Patent number: 10147390
    Abstract: This application discloses a sub-pixel rendering method, and relates to the field of displaying. It is capable of making improvement with respect to the problem of distortion in the boundary region of the displayed image while ensuring a relatively high resolution of the display. The sub-pixel rendering method comprises: receiving a digital image; dividing, according to color values of image pixels in the digital image, the image pixels into boundary region pixels and continuous region pixels; generating a plurality of screen pixels on a screen, each screen pixel at least including one red sub-pixel, one blue sub-pixel, and one green sub-pixel, one of the plurality of screen pixels being used for correspondingly displaying one of the image pixels; wherein adjacent screen pixels for displaying the continuous region pixels share sub-pixels, and each screen pixel for displaying the boundary region pixels exclusively uses its sub-pixels.
    Type: Grant
    Filed: April 8, 2016
    Date of Patent: December 4, 2018
    Assignees: BOE Technology Group Co., Ltd., Beijing BOE Optoelectronics Technology Co., Ltd.
    Inventors: Kai Yang, Peng Liu, Renwei Guo, Hao Zhang
  • Patent number: 10142520
    Abstract: The present disclosure discloses methods and systems for generating a mixed raster content (MRC) format file for single background color image document. The method includes receiving an input document at an image capturing device. The input document is segmented into an image layer and a text layer. Then it is determined whether the image layer including a single background color. Upon affirmative determination, a new text layer with a background color mask is generated. The text layer and the new text layer is compressed using a compression scheme. The compressed text layer and the new text layer are integrated to generate an image data in the MRC file format. The generated image data is stored in a memory device.
    Type: Grant
    Filed: June 28, 2017
    Date of Patent: November 27, 2018
    Assignee: XEROX CORPORATION
    Inventors: Sainarayanan Gopalakrishnan, Rajasekar Kanagasabai, Vignesh Doss
  • Patent number: 10134116
    Abstract: In one embodiment, a method includes a computing device accessing a deconvolution function for a point spread function describing at least part of a user's eyesight. The computing device applies the deconvolution function to an image to be displayed on a display to the user. The computing device then displays on the display the image as deconvolved.
    Type: Grant
    Filed: October 8, 2012
    Date of Patent: November 20, 2018
    Assignee: Facebook, Inc.
    Inventor: Benoit M. Schillings
  • Patent number: 10121251
    Abstract: A method for controlling tracking using a color model is disclosed. The method includes obtaining a window in a second frame of a video image corresponding to a window in a first frame of the video image using a tracking algorithm in a tracking mode, wherein each pixel in the video image has at least one color component. The method further includes defining a background area around the window in the first frame, assigning a pixel confidence value for each pixel in the second frame according to a color model, assigning a window confidence value for the window in the second frame according to the pixel confidence values of pixels in the window in the second frame, if the window confidence value is greater than a first confidence threshold, selecting the tracking mode, and if the window confidence value is not greater than the first confidence threshold, selecting a mode different from the tracking mode.
    Type: Grant
    Filed: July 8, 2016
    Date of Patent: November 6, 2018
    Assignee: Thomson Licensing
    Inventors: Fabrice Urban, Lionel Oisel, Tomas Enrique Crivelli
  • Patent number: 10114808
    Abstract: A method for updating automated annotations for a paper-based document is provided. The method may include receiving an image of the paper-based document, the image of the paper-based document including a plurality of highlighted annotations having at least one edited annotation. The method may also include extracting the at least one edited annotation from the received image of the paper-based document. The method may further include adding the extracted at least one edited annotation of the paper-based document to a data retention system.
    Type: Grant
    Filed: May 7, 2014
    Date of Patent: October 30, 2018
    Assignee: International Business Machines Corporation
    Inventors: Varun Bhagwan, Daniel F. Gruhl, Neal R. Lewis, Steven R. Welch
  • Patent number: 10089554
    Abstract: A set of data comprising at least a first tile and a second tile is received. A determination of a measure is made, for a first pixel location included in both the first tile and the second tile, of whether the first pixel location corresponds to a boundary. A boundary map is generated as output. The boundary map can be used, in conjunction with an image, to regularize pixel brightness values of the image.
    Type: Grant
    Filed: March 30, 2017
    Date of Patent: October 2, 2018
    Assignee: Descartes Labs, Inc.
    Inventor: Rick S. Chartrand
  • Patent number: 10062195
    Abstract: A method for processing a picture comprising at least one face is provided. The method comprises: —obtaining (S10) a cropping window in the picture; —processing (S18) the picture by cropping the picture part delimited by the cropping window; wherein the method further comprises detecting (S12) the at least one face, determining (S14) a weight for the detected at least one face and modifying (S16) the position of the cropping window in the picture based on the weight, wherein the weight is determined at least based on the size of the corresponding detected face.
    Type: Grant
    Filed: February 26, 2015
    Date of Patent: August 28, 2018
    Assignee: THOMSON Licensing
    Inventors: Jean-Claude Chevet, Fabrice Urban, Christel Chamaret
  • Patent number: 10019463
    Abstract: An image processing system for recognizing the scene type of an input image generates an image distance metric from a set of images. The image processing system further extracts image features from the input image and each image in the set of images. Based on the distance metric and the extracted image features, the image processing system computes image feature distances for selecting a subset of images. The image processing system derives a scene type from the scene type of the subset of images. In one embodiment, the image processing system is a cloud computing system.
    Type: Grant
    Filed: June 23, 2015
    Date of Patent: July 10, 2018
    Assignee: Amazon Technologies, Inc.
    Inventors: Yi Li, Tianqiang Liu, Hao Chen, Meng Wang
  • Patent number: 10021275
    Abstract: An image processing apparatus includes a control circuit and an image processing circuit. The control circuit divides a target image stored in a memory into predetermined units to generate a plurality of block image, generates rendering determination information for each of the plurality of block images, and stores the rendering determination information in the memory. The rendering determination information indicates whether the block image has a pixel value to be rendered. The image processing circuit acquires the generated rendering determination information for at least one block image of the target image from the memory, acquires, if the rendering determination information indicates that the block image has the pixel value to be rendered, the block image corresponding to the rendering determination information from the memory, and performs image processing on the acquired target image to generate rendering information for rendering the target image.
    Type: Grant
    Filed: February 29, 2016
    Date of Patent: July 10, 2018
    Assignee: Ricoh Company, Ltd.
    Inventor: Naoto Shiraishi
  • Patent number: 9996900
    Abstract: Methods and systems are presented for converting a mosaiced image in which, for each pixel, a single color intensity value is defined for only one corresponding color, into a full color image in which, for each pixel, color intensity values are defined for each of three colors. For each color, the intensity values of the mosaiced image are interpolated, and regression filtering is performed using the intensity values of one or both of the other colors. Residual values are found as the difference between the result of the regression filtering and the mosaiced image, and these are interpolated, and added to the output of the regression, to form a full color image. The process may be iterated. In each iteration, the regression is performed using the refined channel images generated in the previous iteration.
    Type: Grant
    Filed: February 5, 2015
    Date of Patent: June 12, 2018
    Assignee: NANYANG TECHNOLOGICAL UNIVERSITY
    Inventors: Kai-Kuang Ma, Wei Ye
  • Patent number: 9972067
    Abstract: A method for three-dimensional point cloud registration includes generating a first upsampled three-dimensional point cloud by identifying at least one missing point in the three-dimensional point cloud, determining an intensity of neighboring pixels, filling the at least one missing point in the three-dimensional point cloud with a filler point using depth information from depth values in the three-dimensional point cloud that correspond with the neighboring pixels, generating a second upsampled three-dimensional point cloud by determining at least one local area of the first upsampled three-dimensional point cloud, determining entropies of pixels in the two-dimensional image that correspond with the at least one local area, adding at least one point to the at least one local area based on the entropies of pixels in the two-dimensional image and a scaled entropy threshold, and registering the second upsampled three-dimensional point cloud with a predetermined three-dimensional model.
    Type: Grant
    Filed: October 11, 2016
    Date of Patent: May 15, 2018
    Assignee: The Boeing Company
    Inventors: Hyukseong Kwon, Kyungnam Kim