Image Segmentation Using Color Patents (Class 382/164)
-
Patent number: 9947087Abstract: Systems and methods are provided for determining the safety of an image, which may be used to determine whether an image is appropriate for a given purpose or for use in a given context. Determining the safety of the image may include analyzing the image to determine the amount of skin exposed in various key body areas of each human represented in the image, such as a photograph.Type: GrantFiled: May 27, 2016Date of Patent: April 17, 2018Assignee: GumGum, Inc.Inventor: Daniel Scott Rosen
-
Patent number: 9928598Abstract: A depth measurement apparatus that calculates depth information of an object based on a first color image and a second color image. A depth calculator calculates depth information of a target pixel in a color plane, using the two color images. An evaluator calculates, for each color plane, an evaluation value to indicate a confidence coefficient of the depth information in the target pixel. The depth calculator (i) determines, based on the evaluation value, a color plane from which the depth information of the target pixel is calculated, (ii) calculates a correlation value in one color plane between the two color images, to calculate the depth information from the correlation value using a conversion table or a conversion formula that is different for each color plane, and (iii) calculates the depth information of the target pixel using a color plane of which a correlation value is a threshold or less.Type: GrantFiled: October 23, 2015Date of Patent: March 27, 2018Assignee: Canon Kabushiki KaishaInventor: Satoru Komatsu
-
Patent number: 9922681Abstract: Techniques are disclosed for adding interactive features to videos to enable users to create new media using a dynamic blend of motion and still imagery. The interactive techniques can include allowing a user to change the starting time of one or more subjects in a given video frame, or only animate/play a portion of a given frame scene. The techniques may include segmenting each frame of a video to identify one or more subjects within each frame, selecting (or receiving selections of) one or more subjects within the given frame scene, tracking the selected subject(s) from frame to frame, and alpha-matting to play/animate only the selected subject(s). In some instances, segmentation, selection, and/or tracking may be improved and/or enhanced using pixel depth information (e.g., using a depth map).Type: GrantFiled: April 29, 2016Date of Patent: March 20, 2018Assignee: INTEL CORPORATIONInventors: Daniel C. Middleton, Oscar Nestares, Lucas B. Ainsworth
-
Patent number: 9906840Abstract: A system and method is provided where, in one aspect, a user signals that the user is interested in a particular image being displayed as part of a video, wherein objects in the image are detected and recognized, and wherein an action is taken based on information associated with the recognized objects. By way of example only, the actions may include recording a show (with or without a user's prior confirmation) or displaying information about a product in the image.Type: GrantFiled: October 3, 2016Date of Patent: February 27, 2018Assignee: Google LLCInventor: Nik Clayton
-
Patent number: 9892524Abstract: Image displaying methods, devices, and computer-readable non-transitory storage media containing instructions for implementing the displaying methods are disclosed. In one embodiment, a method includes acquiring an image upon receipt of a request for displaying the image, locating in the image an image region composed of at least three adjoining monochromatic sections, when a difference in color value between any two adjacent ones of the adjoining monochromatic sections in the image region is less than a threshold value, calculating one or more target color values using color values of the monochromatic sections in the image region, replacing color values of the image region with the target color values to generate a target image, and displaying the target image.Type: GrantFiled: April 6, 2016Date of Patent: February 13, 2018Assignee: Xiaomi Inc.Inventors: Chao Xu, Xingmin Wang, Kangxi Tan
-
Patent number: 9872040Abstract: In palette-based coding, a video coder may form a so-called “palette” as a table of colors representing the video data of a given block. The video coder may code index values for one or more pixels values of a current block of video data, where the index values indicate entries in the palette that represent the pixel values of the current block. A method includes determining a number of entries in a palette, and determining whether a block of video data includes any escape pixels not associated with any entry in the palette. The method includes responsive to determining that the number of entries is one, and that the block does not include any escape pixels, bypassing decoding index values for the pixel values of the block, and determining the pixel values of the block to be equal to the one entry in the palette.Type: GrantFiled: December 30, 2014Date of Patent: January 16, 2018Assignee: QUALCOMM IncorporatedInventors: Wei Pu, Marta Karczewicz, Joel Sole Rojals, Liwei Guo, Rajan Laxman Joshi, Feng Zou
-
Patent number: 9852159Abstract: An image recognition apparatus is provided which comprises a first extracting means for extracting, from every registration image previously registered, a set of registration partial images of a predetermined size, and a second extracting means for extracting, from an input new image, a set of new partial images of a predetermined size. The apparatus further comprises a discriminating means for discriminating an attribute of the new partial image based on a rule formed by dividing the set of the registration partial images extracted by the first extracting means, and a collecting means for deriving a final recognition result of the new image by collecting discrimination results by the discriminating means at the time when the new partial images as elements of the set of the new partial images are input.Type: GrantFiled: June 15, 2010Date of Patent: December 26, 2017Assignee: CANON KABUSHIKI KAISHAInventors: Hiroto Yoshii, Masakazu Matsugu
-
Patent number: 9849589Abstract: A mobile robot employing a method and a system for localizing the mobile robot using external surveillance cameras acquires images from the surveillance cameras installed indoors adjacent to each other, recognizes objects included in the images by removing shadows from the images and performing a homography scheme, and avoids the recognized objects. The mobile robot employing the method and the system for localizing the mobile robot using the external surveillance cameras enables rapider localization and lower price as compared with a conventional image-based autonomous robot, so that the commercialization of a service robot is accelerated.Type: GrantFiled: June 21, 2016Date of Patent: December 26, 2017Assignee: Gachon University of Industry-Academic Cooperation FoundationInventor: Young-Im Cho
-
Patent number: 9846924Abstract: In accordance with embodiments of the present disclosure, an information handling system may include a processor and a non-transitory computer-readable medium embodying a program of instructions. The program of instructions may be configured to, when read and executed by the processor, receive a visible-light image from a visible-light sensor, receive an infrared image from an active infrared sensor, and compare the visible-light image to the infrared image to determine shadow regions of the visible-light image having shadows.Type: GrantFiled: March 28, 2016Date of Patent: December 19, 2017Assignee: Dell Products L.P.Inventors: Roman Joel Pacheco, Abu Shaher Sanaullah
-
Patent number: 9830567Abstract: 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: GrantFiled: October 25, 2013Date of Patent: November 28, 2017Assignee: Location Labs, Inc.Inventor: Andrew Weiss
-
Patent number: 9824299Abstract: Various features described herein may include ways of processing multiple images to determine whether any duplicates are among the multiple images. A hashing algorithm may be used to create a hash key of an image. Multiple hash keys corresponding to multiple images may be compared to determine whether those images are duplicate images. A root mean square algorithm may be used to further identify whether multiple images are duplicate images. An image variation engine, which uses intensity coding, may be used to display differences between images. For example, similar areas in images may be drawn with low intensity or high opacity, while different areas in images may be drawn with high intensity or low opacity.Type: GrantFiled: January 4, 2016Date of Patent: November 21, 2017Assignee: Bank of America CorporationInventor: Shakti Suman
-
Patent number: 9818204Abstract: The present disclosure relates to a method for camera identification and detection on color features. In some aspects, the method comprises: 1) starting the camera, the image processing unit and the display unit at the beginning of testing; 2) using the camera to capture the color characteristic value; and 3) moving the untested object to the detection area of the camera for it to be detected, wherein the image processing unit extracts the mean color characteristic value from the color pixels of the detection area.Type: GrantFiled: September 25, 2015Date of Patent: November 14, 2017Assignee: CAPITALBIO CORPORATIONInventors: Yuan Xue, Guanbin Zhang, Cheng Chen
-
Patent number: 9773171Abstract: Disclosed are an event-specific taken picture arrangement device, a control method thereof and a control program thereof capable of efficiently observing the status of a change of a specific object by event. Multiple pictures P are divided into event picture groups ga1, gb1, gc1, and the like by event using a picture-taking date. The event picture groups ga1 and the like are further grouped into a plurality of groups of taken picture Ev1 to Ev6 by identical event. The taken pictures P of the identical event are consecutively arranged in an electronic album by identical event.Type: GrantFiled: March 2, 2016Date of Patent: September 26, 2017Assignee: FUJIFILM CorporationInventor: Makoto Yonaha
-
Patent number: 9749607Abstract: 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: GrantFiled: August 9, 2013Date of Patent: August 29, 2017Assignee: Digimarc CorporationInventors: Jacob L. Boles, Alastair M. Reed, John D. Lord
-
Patent number: 9665943Abstract: Systems, apparatuses, and/or methods may provide for segmenting an image by generating a histogram of its pixel values, dividing the histogram into class intervals, and then iteratively computing new, shifted weighted means and shifted class interval boundaries for the class intervals until a predetermined level of convergence to a limit is obtained. The pixels may then be updated to a last weighted mean for class intervals to which they belong, providing segmentation. Similarly, any data may be segmented to provide computational efficiency.Type: GrantFiled: September 25, 2015Date of Patent: May 30, 2017Assignee: INTEL CORPORATIONInventors: Gilad Baruch, Doron Dag
-
Patent number: 9659224Abstract: Disclosed are techniques for merging optical character recognized (OCR'd) text from frames of image data. In some implementations, a device sends frames of image data to a server, where each frame includes at least a portion of a captured textual item. The server performs optical character recognition (OCR) on the image data of each frame. When OCR'd text from respective frames is returned to the device from the server, the device can perform matching operations on the text, for instance, using bounding boxes and/or edit distance processing. The device can merge any identified matches of OCR'd text from different frames. The device can then display the merged text with any corrections.Type: GrantFiled: March 31, 2014Date of Patent: May 23, 2017Assignee: Amazon Technologies, Inc.Inventors: Matthew Joseph Cole, Sonjeev Jahagirdar, Matthew Daniel Hart, David Paul Ramos, Ankur Datta, Utkarsh Prateek, Emilie Noelle McConville, Prashant Hegde, Avnish Sikka
-
Patent number: 9646056Abstract: Described is a system for rank-ordered and cognitive saliency schema-based object selection. The system receives a set of unnormalized probabilities corresponding to a set of objects competing for attentional selection in a current environment. Each unnormalized probability in the set of unnormalized probabilities is based on a likelihood estimation of encountering the corresponding object in the current environment. The set of objects is ranked based on a set of cognitive saliency values corresponding to the set of objects to generate a rank-ordered list of cognitive saliency values. The rank-ordered list of cognitive saliency values is analyzed to detect a schema of the current environment by which the set of objects is ranked. The schema is learned and stored along with a reward measure of the schema's utility. A maximum saliency object in the set of objects is selected based on the rank-ordered list of cognitive saliency values.Type: GrantFiled: July 17, 2014Date of Patent: May 9, 2017Assignee: HRL Laboratories, LLCInventors: Matthew E. Phillips, Matthias Ziegler, Rajan Bhattacharyya
-
Patent number: 9633614Abstract: According to an aspect, a display device includes an image display panel and a signal processing unit. The signal processing unit derives a generation signal for a fourth sub-pixel in each of pixels based on an input signal for a first sub-pixel, an input signal for a second sub-pixel, an input signal for a third sub-pixel, and an extension coefficient. The signal processing unit derives a correction value based on a hue of an input color corresponding to a color to be displayed based on the input signal for the first sub-pixel, the input signal for the second sub-pixel, and the input signal for the third sub-pixel. The signal processing unit derives the output signal for the fourth sub-pixel in each of the pixels based on the generation signal for the fourth sub-pixel and the correction value and outputs the output signal to the fourth sub-pixel.Type: GrantFiled: December 17, 2015Date of Patent: April 25, 2017Assignee: Japan Display Inc.Inventors: Masaaki Kabe, Fumitaka Gotoh, Kazuhiko Sako, Toshiyuki Nagatsuma, Kojiro Ikeda, Tsutomu Harada
-
Patent number: 9633444Abstract: The present disclosure provides an image segmentation method and device. The image segmentation method comprises: establishing a saliency model of an image; obtaining foreground sample points and background sample points of the image according to the saliency model; establishing a foreground and background classification model according to the saliency model, the foreground sample points and the background sample points; and segmenting the image according to a predefined graph cut algorithm which segments the image by using the foreground and background classification model and edge information related to pixels in the image. A problem that a user needs to manually and roughly select the foreground sample points and the background sample points and thus the segmentation efficiency is low for segmenting a large number of images is solved.Type: GrantFiled: December 29, 2014Date of Patent: April 25, 2017Assignee: XIAOMI INC.Inventors: Lin Wang, Qiuping Qin, Zhijun Chen
-
Patent number: 9619897Abstract: Blotches may be identified and processed to reduce or eliminate the blotch. The blotch may be in just one of several separations and multiple separations may be used, for example, to identify the blotch. An implementation (i) compares a first component image of an image with a first component image of a reference image, (ii) compares a second component image of the image with a second component image of the reference image, and (iii) determines based on these comparisons whether the first component image of the image includes a blotch. Multiple image separations also, or alternatively, may be used, for example, to modify the blotch, as well as to evaluate whether a modification is beneficial.Type: GrantFiled: January 15, 2016Date of Patent: April 11, 2017Assignee: Warner Bros. Entertainment Inc.Inventors: Keren O. Perlmutter, Sharon M. Perlmutter
-
Patent number: 9619729Abstract: According to an embodiment, a density measuring device includes a first calculator, a second calculator, and a first generator. The first calculator calculates, from an image including objects of a plurality of classes classified according to a predetermined rule, for each of a plurality of regions formed by dividing the image, density of the objects captured in the region. The second calculator calculates, from the density of the objects captured in each of the regions, likelihood of each object class captured in each of the regions. The first generator generates density data, in which position corresponding to each of the regions in the image is assigned with the density of the object class having at least the higher likelihood than the lowest likelihood from among likelihoods calculated for object classes captured in the corresponding region.Type: GrantFiled: November 11, 2015Date of Patent: April 11, 2017Assignee: Kabushiki Kaisha ToshibaInventor: Quoc Viet Pham
-
Patent number: 9603300Abstract: Some embodiments described herein include a method for generating scaled terrain information with an unmanned autonomous gardening vehicle. In some embodiments the gardening vehicle includes a driving unit comprising a set of at least one drive wheel and a motor connected to the at least one drive wheel for providing movability of the gardening vehicle, a gardening-tool and a camera for capturing images of a terrain, the camera being positioned and aligned in known manner relative to the gardening vehicle. In context of the method the gardening vehicle is moved in the terrain while concurrently generating a set of image data by capturing an image series of terrain sections so that at least two (successive) images of the image series cover an amount of identical points in the terrain, wherein the terrain sections are defined by a viewing area of the camera at respective positions of the camera while moving.Type: GrantFiled: December 8, 2014Date of Patent: March 28, 2017Assignee: HEXAGON TECHNOLOGY CENTER GMBHInventor: Bo Pettersson
-
Patent number: 9609296Abstract: 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: GrantFiled: August 9, 2013Date of Patent: March 28, 2017Assignee: Digimarc CorporationInventors: Jacob L. Boles, Alastair M. Reed, John D. Lord
-
Patent number: 9600738Abstract: A system and method enable similarity measures to be computed between pairs of images and between a color name and an image in a common feature space. Reference image representations are generated by embedding color name descriptors for each reference image in the common feature space. Color name representations for different color names are generated by embedding synthesized color name descriptors in the common feature space. For a query including a color name, a similarity is computed between its color name representation and one or more of the reference image representations. For a query which includes a query image, a similarity is computed between a representation of the query image and one or more of reference image representations. The method also enables combined queries which include both a query image and a color name to be performed. One or more retrieved reference images, or information based thereon, is then output.Type: GrantFiled: April 7, 2015Date of Patent: March 21, 2017Assignee: XEROX CORPORATIONInventors: Naila Murray, Florent C. Perronnin
-
Patent number: 9602793Abstract: Disclosed is a method for processing sensor data in an image processor that implements at least one image enhancement process, the method comprising: a) performing a skin tone detection operation to identify skin tone areas in the sensor data; b) selectively modifying at least one image enhancement process for the identified skin tone areas; and c) applying the at least one modified image enhancement process to the identified skin tone areas.Type: GrantFiled: December 9, 2009Date of Patent: March 21, 2017Assignee: Imagination Technologies LimitedInventor: Hugh Phu Nguyen
-
Patent number: 9595085Abstract: First RGB image signals are inputted. Color difference signals Cr and Cb are calculated from the first RGB image signals. In a feature space formed by the color difference signals Cr and Cb, a first process is performed such that coordinates corresponding to a second observation area are moved to a reference area containing the origin point while coordinates corresponding to first and third observation areas are maintained unchanged. A second process is performed to move the coordinates corresponding to the first observation area and the coordinates corresponding to the third observation area away from each other.Type: GrantFiled: June 26, 2015Date of Patent: March 14, 2017Assignee: FUJIFILM CorporationInventors: Masayuki Kuramoto, Makoto Sugizaki
-
Patent number: 9547885Abstract: Provided are an image restoration method and device. The method comprises: processing image blocks, which are initially registered, to acquire connection curves among the image blocks; constructing an ambient field of images to be restored by means of the connection curve; by minimizing energy of the connection curve in the ambient field, registering the image blocks; and performing image filling on the registered image blocks to acquire a restored image. The device comprises: a processing unit used for processing the image blocks, which are initially registered, to acquire the connection curve among the image blocks; an ambient field construction unit used for constructing the ambient field of the image to be restored by means of the connection curve; a registering unit used for registering the image blocks by minimizing the energy of the connection curve in the ambient field; and a filling unit used for performing image filling on the registered image blocks to acquire the restored image.Type: GrantFiled: September 13, 2013Date of Patent: January 17, 2017Assignee: Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesInventors: Hui Huang, Kangxue Yin, Minglun Gong, Baoquan Chen, Yunhai Wang
-
Patent number: 9524559Abstract: An image processing device includes: an image acquiring unit for acquiring an image containing pixels; a picture searching unit for searching for a picture region in the image; a background acquiring unit for performing a background connected region acquiring operation on a non-picture region of the image in which the picture region is not included and the picture region respectively, to obtain a non-picture background connected region and a picture background connected region respectively; a foreground acquiring unit for removing the non-picture background connected region and the picture background connected region from the non-picture region and the picture region respectively, to obtain a non-picture foreground region of the non-picture region and a picture foreground region of the picture region respectively; and a merging unit for merging the non-picture foreground region of the non-picture region and the picture foreground region of the picture region to obtain an ultimate image foreground region.Type: GrantFiled: November 19, 2015Date of Patent: December 20, 2016Assignee: FUJITSU LIMITEDInventors: Shufu Xie, Wei Liu, Wei Fan, Jun Sun
-
Patent number: 9501837Abstract: A method and apparatus for unsupervised segmentation of an image is provided. In some exemplary embodiments, the method adjusts a segmentation parameter of a traditional graph-based segmentation algorithm along the image to generate a segmentation map that is perceptually reasonable for a human observer. In some embodiments, the method reduces over-segmentation and under-segmentation of the image.Type: GrantFiled: April 24, 2015Date of Patent: November 22, 2016Assignee: Lyrical Labs Video Compression Technology, LLCInventors: Iuri Frosio, Edward Ratner
-
Patent number: 9483825Abstract: Disclosed are an apparatus and method for estimating a distance using a dual off-axis color filter aperture (DCA). An object detection unit is configured to detect an object from an image taken by a camera having the DCA equipped with a first filter having a first color and a second filter having a second color complementary to the first color. A color shifting value calculation unit is configured to calculate a color shifting value (CSV) using a color shift property between color channels of the image in a region corresponding to the detected object. A distance estimation unit is configured to estimate a distance from the camera to each point of the object based on the calculated CSV and camera parameters including a focal distance of the camera, a focal plane of the camera, and a position of the aperture.Type: GrantFiled: September 24, 2014Date of Patent: November 1, 2016Assignee: CHUNG-ANG UNIVERSITY INDUSTRY-ACADEMY COOPERATIONInventors: Joon-Ki Paik, Seung-Won Lee
-
Patent number: 9462350Abstract: A system and method is provided where, in one aspect, a user signals that the user is interested in a particular image being displayed as part of a video, wherein objects in the image are detected and recognized, and wherein an action is taken based on information associated with the recognized objects. By way of example only, the actions may include recording a show (with or without a user's prior confirmation) or displaying information about a product in the image.Type: GrantFiled: December 11, 2015Date of Patent: October 4, 2016Assignee: Google Inc.Inventor: Nik Clayton
-
Patent number: 9449029Abstract: A system and a method for diet management based on image analysis are provided. The system includes a database and a comparison device. The comparison device is coupled to the database. The comparison device performs similarity comparison in the database based on a supervector related to at least one diet image so as to find out at least one similar population and provides information related to the at least one similar population.Type: GrantFiled: April 2, 2013Date of Patent: September 20, 2016Assignee: Industrial Technology Research InstituteInventors: Chuan-Wei Ting, Ching-Yao Wang, Ju-Chin Chen
-
Patent number: 9449248Abstract: In various implementations, a computing device is configured to provide a live preview of salient contours generated on a live digital video feed. In particular, a designer can use a computing device with a camera, such as a smart phone, to view a real-time preview of salient contours generated from edges detected in frames of a live digital video feed prior to capture, thereby eliminating the unpredictability of salient contours generated from a previously captured image. In some implementations, the salient contours are overlaid on a greyscale conversion of the live digital video feed for improved processing and visual contrast. Other implementations modify aspects of edge-detecting or post-processing filters for improved performance on mobile computing devices.Type: GrantFiled: March 12, 2015Date of Patent: September 20, 2016Assignee: Adobe Systems IncorporatedInventors: Atishay Jain, Shamit Kumar Mehta, Stakshi Jindal Garg, Geoffrey Charles Dowd, Arian Behzadi, Joseph Michael Andolina, David Ericksen
-
Patent number: 9436715Abstract: A data management method including accepting a request of polygon data including data pertaining to latitude/longitude of each vertex of a polygon, specifying a minimum unit rectangle matching a minimum bounding rectangle of the polygon or including the minimum bounding rectangle from plural unit rectangles formed by recursively dividing a two-dimensional space including a latitude/longitude range and being equally divided in X and Y directions in the same number, generating a character string by assigning values to the minimum unit rectangle or all unit rectangles including the minimum unit rectangle in correspondence with the number of divided parts of the two-dimensional space in the X and Y directions, and alternately arranging the values, in the X or Y direction, starting from values corresponding to a large unit rectangle among the unit rectangles, and storing the polygon data in correspondence with a key including the character string.Type: GrantFiled: March 15, 2013Date of Patent: September 6, 2016Assignee: FUJITSU LIMITEDInventors: Toshifumi Obayashi, Mio Okunishi, Kyohei Tamai
-
Patent number: 9412175Abstract: In an example embodiment, a method, apparatus and computer program product are provided. The method includes facilitating receipt of a plurality of superpixels of an input image and an object selection input for selecting part of a foreground object in the input image. The method includes determining first set of superpixels as first set of foreground seeds and second set of superpixels as first set of background seeds. The method includes filtering the first set of background seeds to generate second set of background seeds based on geodesic distances. The method includes adding superpixels of first set of unclassified superpixels to the second set of background seeds to generate third set of background seeds, and adding superpixels of second set of unclassified superpixels to the third set of background seeds to generate fourth set of background seeds based on applying a classifier on the second set of unclassified superpixels.Type: GrantFiled: December 30, 2014Date of Patent: August 9, 2016Assignee: Nokia Technologies OyInventor: Tinghuai Wang
-
Patent number: 9384557Abstract: According to an embodiment, an information processing device includes: a first division unit divides an image into a text containing region and a background region other than the text containing region; a second division unit divides a text containing region into a character region constituted by lines forming characters and a character background region other than the character region; a calculator calculates a first representative value of an attribute of the character region, a second representative value of the attribute of the character background region, and a third representative value of the attribute of the background region; a modification unit makes modification so that a first difference based on the first and third representative values, a second difference based on the first and second representative values, and a third difference based on the second and third representative values become larger; and an output unit outputs a modified image.Type: GrantFiled: September 4, 2015Date of Patent: July 5, 2016Assignee: Kabushiki Kaisha ToshibaInventors: Shihomi Takahashi, Tomoyuki Shibata, Kaoru Suzuki, Yojiro Tonouchi, Kazunori Imoto, Isao Mihara
-
Patent number: 9361700Abstract: A soft, weighted constraint imposed upon image locations can be used to provide a more accurate segregation of an image into intrinsic material reflectance and illumination components. The constraint is arranged to constrain all color band variations between the image locations into one integral constraining relationship.Type: GrantFiled: May 8, 2014Date of Patent: June 7, 2016Assignee: Tandent Vision Science, Inc.Inventors: Andrew Neil Stein, Kshitiz Garg
-
Patent number: 9356913Abstract: The authorizing of transformation chain instances of different transformation chain classes to join so as to act as a compound transformation chain instance. Class-level authorized dependencies are identified between transformation chain classes. Then, instance-level authorization is performed in accordance with one or more joining criteria, presuming that the instances are of appropriate classes that may be joined. The joining allows the instances to act as a single compound transformation chain whereby data is permitted to flow across the boundaries of the constituent transformation chain instances. New transformation chain instances may be joined to the compound transformation chain instances, and transformation chain instances may be removed from the compound transformation chain instance, thereby dynamically changing the compound application.Type: GrantFiled: June 30, 2014Date of Patent: May 31, 2016Assignee: Microsoft Technology Licensing, LLCInventors: Vijay Mital, Darryl Rubin
-
Patent number: 9355328Abstract: The present invention discloses an image foreground matting method based on neighborhood and non-neighborhood smoothness priors. The method primarily comprises the steps of: interactively marking foreground points and background points; initializing ? values of each unmarked pixel of the input image by a color sampling method, calculating confidence degree of the pixel, and admitting ? values of pixels of which confidence degree is larger than a given threshold as known pixels; calculating data term weights, neighborhood smoothness constraint term weights and non-neighborhood smoothness constraint term weights of each pixel in the input image to construct graph patterns of all pixels of the input image; and according to ? values of the known pixels, under the constraint of the graph patterns, solving probabilities that each pixel belongs to the foreground by minimizing the energy equation so as to obtain alpha mattes.Type: GrantFiled: April 24, 2013Date of Patent: May 31, 2016Assignee: Beihang UniversityInventors: Xiaowu Chen, Dongqing Zou, Qinping Zhao, Feng Ding
-
Patent number: 9330315Abstract: A computer identifies a proto-object in a digital image using a background subtraction method, the proto-object being associated with a lighting artifact in the surveillance region. The background subtraction method preserves boundary details and interior texture details of proto-objects associated with lighting artifacts. A plurality of characteristics of the proto-object digital data are determined, the characteristics, individually or in combination, distinguish a proto-object related to a lighting artifact from its background. A learning machine, trained with the plurality of characteristics of proto-objects classified as either foreground or not foreground, determines a likelihood that the plurality of characteristics is associated with a foreground object.Type: GrantFiled: August 22, 2012Date of Patent: May 3, 2016Assignee: International Business Machines CorporationInventors: Quanfu Fan, Sharathchandra U. Pankanti
-
Patent number: 9305329Abstract: A first image at a first resolution is received, the first image having a first hole therein. Based on the first image, a second image is generated at a second resolution lower than the first resolution, the second image having a second hole therein corresponding to the first hole. In the second image, one or more second-image source patches for the second hole are identified. At least one first-image source patch in the first image is identified based on a location of the identified second-image source patch. The identified at least one first-image source patch are stored in memory. Fill content are identified in the at least one first-image source patch stored in the memory. The identified fill content are placed in the first hole.Type: GrantFiled: July 23, 2014Date of Patent: April 5, 2016Assignee: Adobe Systems IncorporatedInventors: Dan Goldman, Elya Shechtman
-
Patent number: 9280830Abstract: An image processing apparatus for extracting an area of a detection target from an image includes an image input section that acquires an image, an image generation section that generates a plurality of images with different resolutions from the image, and a segmentation section that performs segmentation using the plurality of images with the different resolutions. The segmentation section segments an image with a low resolution and then segmenting an image with a high resolution using, as a processing target area, an area in the image with the high resolution corresponding to an area near a boundary resulting from processing of the segmentation of the image with the low resolution.Type: GrantFiled: February 4, 2015Date of Patent: March 8, 2016Assignee: OMRON CorporationInventors: Atsushi Irie, Hiromatsu Aoki, Takahiro Sato
-
Patent number: 9280811Abstract: A method of large-radius edge-preserving low-pass filtering a digital signal having data points, including computing weighted averages of a signal layer at vertices in at least two grids, the vertices in each grid being a different subset of the data points such that in each grid an amount of the vertices is less than an amount of the data points; and producing, for each of the data points, a large-radius edge-preserving low-pass filtered signal based on the weighted averages of the signal layer at vertices in the at least two grids neighboring the data point.Type: GrantFiled: March 6, 2014Date of Patent: March 8, 2016Assignee: Samsung Electronics Co., Ltd.Inventor: Nathan Henri Levy
-
Patent number: 9269134Abstract: An inspection area setting method for setting inspection area-defining information defining an inspection area to an image inspecting device, the image inspecting device being configured to extract a portion constituting the inspection area as an inspection area image from an original image obtained by taking an image of an inspection object, and to inspect the inspection object by analyzing the inspection area image, includes an acquisition step of acquiring a sample image obtained by taking an image of a sample of the inspection object, an inspection area searching step, and a setting step.Type: GrantFiled: August 29, 2012Date of Patent: February 23, 2016Assignee: OMRON CorporationInventors: Yoshihisa Minato, Yukiko Yanagawa
-
Patent number: 9262826Abstract: A microprocessor is operably coupled to a camera from which patient vital signs are determined. A temporal variation of images from the camera is generated from multiple filters and then amplified from which the patient vital sign, such as heart rate or respiratory rate, can be determined and then displayed or stored.Type: GrantFiled: August 11, 2014Date of Patent: February 16, 2016Assignee: ARC Devices LimitedInventors: Mark Khachaturian, Michael G. Smith
-
Patent number: 9251613Abstract: Disclosed are systems and methods for automatically applying special effects based on media content characteristics. A digital image is obtained and depth information in the digital image is determined. A foreground region and a background region in the digital image are identified based on the depth information. First and second effects are selected from a grouping of effects, where the first effect is applied to at least a portion of the foreground region and the second effect is applied to at least a portion of the background region.Type: GrantFiled: April 8, 2014Date of Patent: February 2, 2016Assignee: CYBERLINK CORP.Inventor: Chen Yen Hsun
-
Patent number: 9240052Abstract: Blotches may be identified and processed to reduce or eliminate the blotch. The blotch may be in just one of several separations and multiple separations may be used, for example, to identify the blotch. An implementation (i) compares a first component image of an image with a first component image of a reference image, (ii) compares a second component image of the image with a second component image of the reference image, and (iii) determines based on these comparisons whether the first component image of the image includes a blotch. Multiple image separations also, or alternatively, may be used, for example, to modify the blotch, as well as to evaluate whether a modification is beneficial.Type: GrantFiled: March 9, 2015Date of Patent: January 19, 2016Assignee: Warner Bros. Entertainment Inc.Inventors: Keren O. Perlmutter, Sharon M. Perlmutter
-
Patent number: 9230332Abstract: An automated, computerized method is provided for processing an image. The method comprises the steps of providing a sequence of image files depicting images of a same scene, in a computer memory, determining correspondence information relevant to the same scene across the sequence of images, and generating individual intrinsic images for each one of the sequence of images, as a function of the correspondence information.Type: GrantFiled: November 1, 2013Date of Patent: January 5, 2016Assignee: Tandent Vision Science, Inc.Inventors: Casey Arthur Smith, Andrew Neil Stein, Bruce Allen Maxwell, Richard Mark Friedhoff
-
Patent number: 9183456Abstract: A method includes: acquiring a first level value in a first color area; acquiring a second level value in a second color area; calculating a first corrected level value by adding X % of a difference between the first level value and the second level value to the first level value; calculating a second corrected level value by subtracting Y % of the difference from the second level value; specifying a first corrected level position and a second corrected level position at a boundary between the first color area and the second color area; and measuring a bokeh amount of the image at the boundary between the first color area and the second color area by multiplying the distance between the specified first corrected level position and the specified second corrected level position by 100/(100?X?Y).Type: GrantFiled: May 15, 2014Date of Patent: November 10, 2015Assignee: Panasonic Intellectual Property Management Co., Ltd.Inventors: Hiroya Kusaka, Masamichi Ohara
-
Patent number: 9183643Abstract: According to one embodiment, an acquisition unit acquires a pixel block having a predetermined size from image data to be coded. A comparison unit calculates a distance between a color of a target pixel in the pixel block and each of a plurality of typical colors, and selects a typical color of which the distance is a minimum distance from the plurality of typical colors. A decision unit assigns a first index representing the selected typical color to the target pixel if the minimum distance is smaller than a first threshold, assigns a second index representing a new typical color to the target pixel if the minimum distance is larger than the first threshold, and adds the color of the target pixel as the new typical color when the second index is assigned. A coding unit codes the selected typical color, the new typical color, the first index and the second index.Type: GrantFiled: July 23, 2013Date of Patent: November 10, 2015Assignee: Kabushiki Kaisha ToshibaInventors: Atsushi Matsumura, Tatsuya Tanaka