Artifact Removal Or Suppression (e.g., Distortion Correction) Patents (Class 382/275)
-
Patent number: 9594534Abstract: An information processing apparatus includes a download unit to download, in accordance with an instruction of a user, a print target image from a server accessible by a third party using an SNS (Social Networking Service) via a network, different from the user. A processor obtains subjective evaluation information of the third party for the print target image included in a tag added to the print target image downloaded by the download unit, evaluates the print target image, based on the subjective evaluation information of the third party, and performs image processing for the downloaded print target image in accordance with a result of the evaluation. An output unit outputs image data that has undergone the image processing of the processor.Type: GrantFiled: August 19, 2015Date of Patent: March 14, 2017Assignee: CANON KABUSHIKI KAISHAInventors: Takeru Sasaki, Takashi Nakamura, Kiyoshi Umeda, Hiroyasu Kunieda
-
Patent number: 9569853Abstract: Light field images of a three-dimensional scene are transformed from an (image,view) domain to an (image,scale,depth) domain. Processing then occurs in the (image,scale,depth) domain.Type: GrantFiled: February 19, 2016Date of Patent: February 14, 2017Assignee: Ricoh Company, Ltd.Inventors: Ivana To{hacek over (s)}ić, Kathrin Berkner
-
Patent number: 9557565Abstract: In embodiments of the invention, an apparatus may include a display comprising a plurality of pixels. The apparatus may further include a computer system coupled with the display and operable to instruct the display to display a deconvolved image corresponding to a target image, wherein when the display displays the deconvolved image while located within a near-eye range of an observer, the target image may be perceived in focus by the observer.Type: GrantFiled: December 19, 2012Date of Patent: January 31, 2017Assignee: NVIDIA CORPORATIONInventors: David Patrick Luebke, Douglas Lanman, Thomas F. Fox, Gerrit Slavenburg
-
Patent number: 9547669Abstract: Disclosed is a server that can perform a visual search using at least one rectified image. A method implemented at a server includes storing a plurality of images with the server, receiving at least one rectified image having at least one potential object of interest from a computing device for a visual search, and extracting descriptors representing features of the at least one rectified image. The extracted descriptors of the at least one rectified image are designed to be invariant to rotation, scale, and lighting without needing to be invariant to perspective or affine distortion.Type: GrantFiled: May 13, 2015Date of Patent: January 17, 2017Assignee: QUALCOMM INCORPORATEDInventors: Daniel Wagner, Qi Pan
-
Patent number: 9549157Abstract: A defective pixel of an imaging device is detected. An output pixel value of the defective pixel is corrected to generate an output image. An imaging device, and a signal processing unit for analyzing an output signal from the imaging device and detecting a defective pixel are included. The imaging device receives incident light via, for example, a microlens placed in front of a pixel, inputs the same subject light on a local area basis including a plurality of pixels of the imaging device, and acquires an image signal lower than a pixel resolving power corresponding to the pixel density of the imaging device. The signal processing unit compares the pixel values of the same color pixels included in a local area on a local area basis including a cluster of the plurality of pixels of the imaging device, detects the defective pixel based on the comparison result, and corrects and outputs a pixel value of a pixel determined to be a defective pixel.Type: GrantFiled: September 24, 2013Date of Patent: January 17, 2017Assignee: Sony Semiconductor Solutions CorporationInventor: Hirotaka Shinozaki
-
Patent number: 9544475Abstract: A data transfer apparatus includes a cache memory having a storing portion for writing and reading data at a higher speed than an image data storing portion which stores image data GD of an input image, and data transfer request means for outputting, to the cache memory, a transfer request for image data in a certain region of the input image. The cache memory reads unstored image data from the image data storing portion beyond a reading region corresponding to a transfer request every pixel row if image data in a pixel row included in the reading region is not stored in the storing portion of the cache memory. Moreover, the data transfer request means sequentially gives, in arrangement order in a horizontal direction of an input image, a transfer request for image data in each of reading regions arranged in the horizontal direction.Type: GrantFiled: March 5, 2013Date of Patent: January 10, 2017Assignee: MegaChips CorporationInventor: Kazuma Takahashi
-
Patent number: 9544463Abstract: An information processing apparatus includes an image acquisition unit that acquires an initial image to be output by an image output apparatus; an image determining unit that determines, based on an output condition to be implemented by the image output apparatus upon outputting the initial image and image data of the initial image, whether to change the initial image to a substitute image having a higher image quality than the initial image; an image searching unit that searches for the substitute image in a case where a determination is made by the image determining unit to change the initial image to the substitute image; an output data generating unit that generates output data including image data of the substitute image found by the image searching unit; and a transmitting unit configured to transmit the output data to the image output apparatus.Type: GrantFiled: March 11, 2016Date of Patent: January 10, 2017Assignee: Ricoh Company, Ltd.Inventors: Tomoaki Okamura, Yasushi Yanagida
-
Patent number: 9535993Abstract: A search engine server supports crawling of third party servers communicatively coupled to the search engine server to gather vectors to web content, wherein the search engine server delivers a report to registered creative work owners by identifying vectors to web content that contain similarities to their works and by providing protection to the copyrighted creative works. The search engine server has components that identify similarities to the works of the registered owners of the creative works and provide protection by reporting to the registered owners as well as host third party servers, in case of textual, image, audio and video creative works. This service is an added value based service of the search engine server to the registered owners of the creative works upon service charge basis.Type: GrantFiled: June 11, 2009Date of Patent: January 3, 2017Assignee: ENPULZ, LLCInventor: James D. Bennett
-
Patent number: 9508129Abstract: Methods and systems for dehazing images with increased accuracy and reduced error enhancement. In particular, one or more embodiments estimate a transmission map representing an amount of unscattered light reflected from objects in an input image. One or more embodiments refine the transmission map to obtain transmission information consistent with a depth of the objects in the input image. One or more embodiments also determine a radiance gradient for the input image. One or more embodiments generate an output image from the input image by removing haze based on the refined transmission map and preventing error enhancement based on the determined radiance gradient.Type: GrantFiled: November 6, 2015Date of Patent: November 29, 2016Assignee: ADOBE SYSTEMS INCORPORATEDInventors: Jue Wang, Chen Chen
-
Patent number: 9497468Abstract: Blur is one of the most important features related to video quality. Accurate estimating the blur level of a video is a great help to accurately evaluate the video quality. An improved method is provided for estimating the blur level of videos that are compressed by a block based codec, such as H.264/AVC, MPEG2, etc. According to the invention, local blur detection is based on macroblock (MB) edges, a content dependent weighting scheme is employed to decrease the influence from texture and when detecting local blur, the spreading of detection will stop at local minimum and maximum luminance positions.Type: GrantFiled: February 26, 2010Date of Patent: November 15, 2016Assignee: Thomson LicensingInventors: De Bing Liu, Zhi Bo Chen, Xiao Dong Gu, Feng Xu
-
Patent number: 9478171Abstract: A display device includes a plurality of pixels. The display device further includes a plurality of gate lines. The display device further includes a gate driver configured provide a plurality of gate signals through the plurality of gate lines to the plurality of pixels according to at least one of a discharge signal and a scanning start signal for controlling the plurality of pixels, the gate driver being configured to provide a plurality of gate-off signals through the plurality of gate lines to the plurality of pixels according to the discharge signal. The display device further includes a signal provider configured to provide the discharge signal to the gate driver when the signal provider determines that an image signal is abnormal.Type: GrantFiled: September 6, 2013Date of Patent: October 25, 2016Assignee: SAMSUNG DISPLAY CO., LTD.Inventors: Jun Yong Song, Myeong Su Kim, Jae Hoon Lee, Jeong Bong Lee
-
Patent number: 9478054Abstract: Implementations generally relate to image overlay compositing. In some implementations, a method includes receiving a first image and a second image. The method further includes determining one or more attributes of each of the first image and the second image, where the one or more attributes includes one or more image types. The method further includes determining one or more compositing techniques combine the first image and the second image based on one or more of the attributes.Type: GrantFiled: November 9, 2013Date of Patent: October 25, 2016Assignee: Google Inc.Inventors: Justin Lewis, Gavin James
-
Patent number: 9473725Abstract: An image-processing device includes an image acquiring device, an encoded aperture pattern setting device configured to set encoded aperture patterns for multiple pupil images of the main lens, respectively, a calculation device configured to perform a weighted product-sum calculation between the pupil image for each lens of the lens array in the image acquired from the image sensor and the encoded aperture pattern set by the encoded aperture pattern setting device, and an image generating device configured to generate an image based on a calculation result by the calculation device.Type: GrantFiled: March 25, 2015Date of Patent: October 18, 2016Assignee: FUJIFILM CorporationInventor: Shuji Ono
-
Patent number: 9459103Abstract: A non-transitory computer readable medium stores a movement situation determining program for causing a computer to function as a two-axial direction correlation value calculating portion that calculates a correlation value indicating a relationship between motions in two axial directions of a plurality of axial directions on the basis of information obtained by detecting motions of a moving target in the plurality of axial directions, and a movement situation determining portion that determines a movement situation of the moving target on the basis of the correlation value.Type: GrantFiled: July 3, 2012Date of Patent: October 4, 2016Assignee: FUJI XEROX CO., LTD.Inventors: Masahiro Sato, Takayuki Takeuchi, Kyotaro Tomoda, Minoru Mitsui, Tsutomu Ishii, Shigehiko Sasaki, Akira Ichiboshi, Takao Naito
-
Patent number: 9443294Abstract: This invention is concerning an image correction system that includes an image-capturing unit configured to acquire a captured image by capturing a subject; a tilt recognition unit configured to recognize tilt of an image-capturing direction of the image-capturing unit relative to an image-capturing direction in which the image-capturing unit being directly opposite to the subject captures the subject; a first correction unit configured to generate a corrected image by correcting distortion in the captured image due to the tilt; and a second correction unit configured to acquire a corrected captured image by correcting non-linear distortion in the corrected image.Type: GrantFiled: November 18, 2013Date of Patent: September 13, 2016Assignee: RICOH COMPANY, LIMITEDInventor: Shinichi Sumiyoshi
-
Patent number: 9445052Abstract: Metadata associated with a first image and that specifies an alignment reference line for the first image is accessed. Based on the accessed metadata associated with the first image, a layout for concurrently displaying the first image and a second image at a location is defined that substantially aligns the alignment reference line of the first image with an aspect of the second image.Type: GrantFiled: August 31, 2011Date of Patent: September 13, 2016Assignee: Hewlett-Packard Development Company, L.P.Inventors: Mark E. Gorzynski, Michael D. Derocher
-
Patent number: 9438832Abstract: A first region that includes a target pixel and extends in a first direction, and multiple regions and that are obtained by shifting the first region by a predetermined amount in direction perpendicular to the first direction are set. A first correction value is obtained using multiple pixel values selected in the regions based on correlation values indicating a degree of correlation with the target pixel. The value of the target pixel is corrected using a correction value obtained from the first correction value and the pixel value selected in the first region, with a weight based on the sizes of the correlation value corresponding to the first correction value and the correlation value corresponding to the pixel value selected in the first region.Type: GrantFiled: June 26, 2015Date of Patent: September 6, 2016Assignee: Canon Kabushiki KaishaInventor: Yoshiaki Honda
-
Patent number: 9435731Abstract: A state determination method is provided that is capable of determining at least one of the state of degradation of oil in a machine and the state of breakage of the machine with higher accuracy than conventional methods. A state determination method for determining the state of degradation of lubricating oil in a speed reducer and the state of breakage of the speed reducer is characterized by: transmitting white light emitted by a white LED through the lubricating oil, causing an RGB sensor to detect the color of the light transmitted through the lubricating oil by the white LED, and calculating the brightness of the color detected by the RGB sensor (S201); calculating a color component maximum difference that is the difference between a maximum value and a minimum value among the R value, G value, and B value of the color detected by the RGB sensor (S202); and determining the states on the basis of the brightness calculated in S201 and the color component maximum difference calculated in S202 (S203, S207).Type: GrantFiled: October 22, 2015Date of Patent: September 6, 2016Assignee: NABTESCO CORPORATIONInventors: Yoshinori Ohnuma, Takuya Shirata, Yasuhito Ida
-
Patent number: 9420198Abstract: Some embodiments provide a method of operating a device to capture an image of a high dynamic range (HDR) scene. Upon the device entering an HDR mode, the method captures and stores multiple images at a first image exposure level. Upon receiving a command to capture the HDR scene, the method captures a first image at a second image exposure level. The method selects a second image from the captured plurality of images. The method composites the first and second images to produce a composite image that captures the HDR scene. In some embodiments, the method captures multiple images at multiple different exposure levels.Type: GrantFiled: November 10, 2014Date of Patent: August 16, 2016Assignee: Apple Inc.Inventors: Guy Cote, Garrett M. Johnson, James Edmund Orr, IV
-
Patent number: 9396523Abstract: Image restoration cascades are described, for example, where digital photographs containing noise are restored using a cascade formed from a plurality of layers of trained machine learning predictors connected in series. For example, noise may be from sensor noise, motion blur, dust, optical low pass filtering, chromatic aberration, compression and quantization artifacts, down sampling or other sources. For example, given a noisy image, each trained machine learning predictor produces an output image which is a restored version of the noisy input image; each trained machine learning predictor in a given internal layer of the cascade also takes input from the previous layer in the cascade. In various examples, a loss function expressing dissimilarity between input and output images of each trained machine learning predictor is directly minimized during training. In various examples, data partitioning is used to partition a training data set to facilitate generalization.Type: GrantFiled: July 24, 2013Date of Patent: July 19, 2016Assignee: Microsoft Technology Licensing, LLCInventors: Jeremy Jancsary, Reinhard Sebastian Bernhard Nowozin, Carsten Curt Eckard Rother
-
Patent number: 9392267Abstract: Embodiments of the invention include a system and method to generate a quality rating prediction, such as MOS, of a video under test without using a second video as a reference. Instead of using a reference video, embodiments of the invention generate a pseudo reference video from measuring local impairments of the video under test. The local impairments are then accumulated to create a difference image. The difference image is then subtracted from the video under test to create the pseudo reference, to which the video under test is compared to generate the quality prediction rating. In some embodiments the local impairments may be measured by separating high frequency noise from the video under test from the video itself. Once separated, the noise is then measured and bandwidth compensated to generate the measured local impairments.Type: GrantFiled: December 15, 2010Date of Patent: July 12, 2016Assignee: TEKTRONIX, INC.Inventor: Kevin M. Ferguson
-
Patent number: 9377855Abstract: A portable terminal device and methods are disclosed A portable terminal comprises: a touch panel that detects a position of a touch, if an operator touches a display unit displaying an image, and outputs the position of the touch; a vibrator; an edge detector that detects an edge in the image; and a controller that determines whether the position of the touch corresponds with a position of the detected edge, causes the vibrator to start vibrating if the position of the touch corresponds with the position of the edge, and inhibits the vibrator from vibrating if the position of the touch does not correspond with the position of the edge.Type: GrantFiled: March 18, 2013Date of Patent: June 28, 2016Assignee: KYOCERA CorporationInventor: Shinya Okada
-
Patent number: 9373161Abstract: An image processing device adapted to correct a keystone distortion of an image projected on a region where a first plane and a second plane intersect with each other at a predetermined angle includes a transformation section adapted to calculate a first coordinate to be referred to in a first coordinate transformation for correcting the keystone distortion and a second coordinate to be referred to in a second coordinate transformation for correcting the keystone distortion, a combination section adapted to generate a composite coordinate obtained by combining the first coordinate and the second coordinate calculated by the transformation section, and a correction section adapted to perform a coordinate transformation for correcting the keystone distortion using the composite coordinate generated by the combination section.Type: GrantFiled: February 24, 2014Date of Patent: June 21, 2016Assignee: SEIKO EPSON CORPORATIONInventor: Manabu Saigo
-
Patent number: 9369742Abstract: System and method to calculate video frame delay in a video stream received by a telecommunications endpoint, the method including: locating reference features characteristic of content in the received video stream; calculating, by use of a processor, reduced reference features from the located reference features; receiving reduced reference features of a transmitted video stream, the transmitted video stream corresponding to the received video stream; calculating, by use of a processor, a received trajectory of the reduced reference features from the received video stream; calculating, by use of a processor, a transmitted trajectory of the reduced reference features from the transmitted video stream; and calculating, by use of a processor, video frame delay as a time shift between the received trajectory and the transmitted trajectory.Type: GrantFiled: December 6, 2012Date of Patent: June 14, 2016Assignee: Avaya Inc.Inventor: Bengi Karacali-Akyamac
-
Patent number: 9361734Abstract: The present technique relates to an image processing device and an image processing method for realizing high-precision image generation of predetermined viewpoints by using depth images on the receiving end when the depth images with reduced resolutions are transmitted. A parallax image resolution increasing unit increases the resolution of each of the parallax images of auxiliary images having half the resolution of a compatible image. A parallax image warping unit generates parallax images of virtual viewpoints by performing a warping operation on the parallax images of the auxiliary images with the increased resolutions based on the positions of the virtual viewpoints. A smoothing unit corrects the parallax values of the occlusion regions in the parallax images of the virtual viewpoints. The present technique can be applied to decoding devices that decode glasses-free 3D images, for example.Type: GrantFiled: February 16, 2012Date of Patent: June 7, 2016Assignee: SONY CORPORATIONInventors: Shinobu Hattori, Yoshitomo Takahashi
-
Patent number: 9349174Abstract: Multiple images of a scene are captured while a phase-shifted fringe embedded with a secondary pattern is projected onto the scene. A wrapped phase map is generated based on the captured images, and a continuous region mask is determined to segment the wrapped phase map into multiple continuous regions. A period disparity of the fringe is determined for each region based at least in part on the embedded secondary pattern, and the regional period disparities are applied to a spatially unwrapped phase map to produce an absolute phase map and finally a depth map.Type: GrantFiled: May 31, 2013Date of Patent: May 24, 2016Assignee: Microsoft Technology Licensing, LLCInventors: Zhiwei Xiong, Feng Wu, Yueyi Zhang
-
Patent number: 9324133Abstract: A system for determining a high resolution image includes receiving a low resolution image and determining a vector of a patch of the low resolution image based upon a low resolution dictionary. The system includes determining a high resolution patch based upon a high resolution dictionary and the vector and determining the high resolution image based upon the high resolution patch.Type: GrantFiled: January 4, 2012Date of Patent: April 26, 2016Assignee: Sharp Laboratories of America, Inc.Inventors: Anustup Kumar Choudhury, Christopher Andrew Segall, Petrus J. L. Van Beek
-
Patent number: 9300846Abstract: In certain low-light or other poor image capture conditions, the camera capture settings may create noise fitting a known profile, including certain specific color ranges and signal frequencies, in the captured image. A pre-processor may identify frequency bands and DC offsets that may indicate noise in an image captured with known settings. Then the areas of the image containing the identified frequencies and offsets may be analyzed spatially and temporally to confirm that the identified regions are noise and not part of the scene and an appropriate filter defined.Type: GrantFiled: January 18, 2013Date of Patent: March 29, 2016Assignee: Apple Inc.Inventors: Douglas Price, Xiaosong Zhou, Hsi-Jung Wu
-
Patent number: 9288377Abstract: Imaging systems may be provided with stacked-chip image sensors and adjustable lens systems. A stacked-chip image sensor may include a vertical chip stack that includes an array of image pixels and processing circuitry. The adjustable lens system may pass light from a scene onto the image pixels at a number of focus positions. The image pixels may capture a focus bracket of image frames at a capture frame rate for light passed by the adjustable lens system at two or more of the focus positions. The processing circuitry may combine a set of image frames in the focus bracket to generate a focused image. The focused image may have one or more portions of the captured scene in focus. The processing circuitry may output the focused image to off-chip image processing circuitry at an output frame rate that is less than the capture frame rate.Type: GrantFiled: April 25, 2013Date of Patent: March 15, 2016Assignee: Semiconductor Components Industries, LLCInventor: Honghong Peng
-
Patent number: 9277162Abstract: A keystone correction apparatus and method of curved display are provided. The apparatus includes a curved screen that displays an image and a projector that has an infrared lighting device to irradiate infrared light to the curved screen. An infrared imaging device is configured to capture infrared light reflected from the curved screen. A controller is configured to determine whether the curved screen is distorted using an infrared image captured by the infrared imaging device and perform a keystone correction.Type: GrantFiled: December 29, 2013Date of Patent: March 1, 2016Assignee: Hyundai Motor CompanyInventor: Jong Bok Lee
-
Patent number: 9268921Abstract: A computing system selects a portion of data of an unknown work and detects each event in the portion of data of the unknown work. An event is a perceptual occurrence in a work successively positioned in time. The system determines an event metric between each successive event in the portion of data in the unknown work and generates a list of event metrics between the events for the unknown work. The system compares the list of event metrics for the unknown work to a list of event metrics for a known work and determines the unknown work is a copy of the known work responsive to a match between the list of event metrics of the unknown work and the list of event metrics for the known work.Type: GrantFiled: April 4, 2014Date of Patent: February 23, 2016Assignee: Audible Magic CorporationInventor: Erling Wold
-
Patent number: 9269130Abstract: An image correction method arranged for processing an original image to obtain a corrected image includes steps: receiving the original image from an image sensor; regarding each pixel of the original image, calculating a horizontal distance and a vertical distance between the pixel and a reference point in the original image; determining a horizontal ratio parameter and a vertical ratio parameter according to the horizontal distance and the vertical distance between the pixel and the reference point in the original image; and performing an approximately non-linear regression calculation on the horizontal ratio parameter, the vertical ratio parameter and a coordinate of the pixel to obtain a position of the pixel in the corrected image.Type: GrantFiled: April 8, 2013Date of Patent: February 23, 2016Assignee: Realtek Semiconductor Corp.Inventors: Shih-Tse Chen, Hao-Tien Chiang
-
Patent number: 9225986Abstract: The present invention provides a unique intra prediction process which improves the efficiency of video coding. H.264/AVC uses reference pixels in a horizontal boundary located immediately above a target block to be predicted and reference pixels in a vertical boundary located immediately left of the target block. In the present invention, at least some of one of an array of horizontal boundary pixels and an array of vertical boundary pixels are retrieved. Then, the retrieved pixels are added to the other boundary pixels to extend the array thereof. Intra prediction is performed, based solely on the extended array of boundary pixels.Type: GrantFiled: July 14, 2011Date of Patent: December 29, 2015Assignee: NTT DOCOMO, INC.Inventors: Frank Jan Bossen, Thiow Keng Tan
-
Patent number: 9219827Abstract: There is provided an image inspection system. An image reading unit reads a formed image which is formed on a recording medium based on original image data to generate read image data. A determination unit compares the read image data and the original image data to determine whether or not the formed image includes a defective region. An extraction unit extracts an image of characters present around the defective region from the read image data. An image display device displays the image of the characters and an image of the defective region such that both the images overlap with each other.Type: GrantFiled: September 19, 2013Date of Patent: December 22, 2015Assignee: FUJI XEROX CO., LTD.Inventors: Takashi Hiramatsu, Kiyofumi Aikawa, Michio Kikuchi
-
Patent number: 9218649Abstract: An image processing apparatus includes a receiving unit, a specifying unit, a controlling unit, and an outputting unit. The receiving unit receives image data. The specifying unit specifies a correction amount of the image data for keystone correction processing. The controlling unit controls, based on the correction amount specified by the specifying unit, the keystone correction processing, filter processing for reducing a predetermined high frequency component, and edge enhancement processing. The outputting unit outputs processed image data which is processed based on the controlling by the controlling unit.Type: GrantFiled: December 18, 2013Date of Patent: December 22, 2015Assignee: Canon Kabushiki KaishaInventor: Shinichi Uemura
-
Patent number: 9201957Abstract: The invention relates to processing of data during semantic analysis of text data and building of document semantic models. The method consists of two main steps. In step one, an ontology is extracted from external information sources that contain descriptions of particular domain objects. In step two, the text information in the document is linked to ontology concepts and a document semantic model is built. Electronic resources that may or may not be connected through a hyperlink structure are used as information sources. The technical result is achieved, in particular, by identifying all terms in the document and linking them to ontology concepts, so that each term correlates to one concept (its meaning), and then ranking term meanings by importance to the document.Type: GrantFiled: November 29, 2012Date of Patent: December 1, 2015Assignee: The Institute for System Programming of the Russian Academy of SciencesInventors: Denis Yurievich Turdakov, Yaroslav Rostislavovich Nedumov, Andrey Anatolyevich Sysoev
-
Patent number: 9202264Abstract: An image processing apparatus includes: a processor coupled to a memory, configured to: perform an analysis of resolution in at least two directions of an image which is taken from a subject having a radial pattern, and determine filter data containing an adjusted weight coefficient which is obtained by adjusting a weight coefficient in one of the two directions, whichever has lower resolution, based on a result of the analysis of the image corrected by filtering on the image in accordance with a blurring function of the image.Type: GrantFiled: May 23, 2013Date of Patent: December 1, 2015Assignee: FUJITSU LIMITEDInventors: Yukio Hirai, Hiroyasu Yoshikawa
-
Patent number: 9202266Abstract: In accordance with an example embodiment a method, apparatus and computer program product are provided. The method comprises determining a plurality of first pixels having resemblance with a second pixel associated with an image based on a depth information of the image. The method further comprises replacing the second pixel by at least one first pixel of the plurality of first pixels based on a determination that the at least one first pixel is not associated with the at least one image defect.Type: GrantFiled: December 23, 2013Date of Patent: December 1, 2015Assignee: Nokia Technologies OyInventors: Krishna Annasagar Govindarao, Gururaj Gopal Putraya, Mithun Uliyar, Basavaraja S V
-
Patent number: 9189679Abstract: Disclosed are novel techniques for high-precision sex determination and age estimation using facial images. The disclosed age estimation method includes: a step in which facial image data of a subject is acquired; a step in which spatial frequency intensities are calculated from the acquired facial image data; and a step in which the estimated age of the subject is calculated by applying the calculated spatial frequency intensities obtained from the facial image data.Type: GrantFiled: May 18, 2011Date of Patent: November 17, 2015Assignee: POLA CHEMICAL INDUSTRIES, INC.Inventors: Kazuhiro Yamazaki, Akihiro Tada, Mariko Hayashi, Miho Ohata, Sakura Torii
-
Patent number: 9191589Abstract: An image processing device 102 includes a background-object reference image estimation unit 1, a background-object optical flow calculation unit 2, moving-object reference image estimation units 4 and 9, moving-object heat-haze fluctuation calculation units 5, 6, 7, 10 and 11, and a motion correction unit 3. The image processing device 102 is configured such that optical flow of a background object and heat-haze fluctuation of a moving-object are obtained from input images inputted in succession, partial images of the input images are moved so as to cancel the heat-haze fluctuation, and a corrected image, which has the heat-haze fluctuation upon the background object and the moving-object within the input images removed, is generated.Type: GrantFiled: November 29, 2012Date of Patent: November 17, 2015Assignee: Hitachi Kokusai Electric Inc.Inventors: Munemitsu Kuwabara, Wataru Ito, Madoka Tanaka
-
Patent number: 9185318Abstract: A solid-state imaging device includes a pixel array section and a signal processing section. The pixel array section is configured to include a plurality of arranged rectangular pixels, each of which has different sizes in the vertical and horizontal directions, and a plurality of adjacent ones of which are combined to form a square pixel having the same size in the vertical and horizontal directions. The signal processing section is configured to perform a process of outputting, as a single signal, a plurality of signals read out from the combined plurality of rectangular pixels.Type: GrantFiled: October 7, 2014Date of Patent: November 10, 2015Assignee: SONY CORPORATIONInventor: Keiji Mabuchi
-
Patent number: 9179124Abstract: Provided are a method and apparatus for encoding and decoding a stereoscopic image. A stereoscopic image restoring method includes parsing a received data stream into image data of a stereoscopic image and information regarding the stereoscopic image; extracting a camera parameter depending on individual characteristics of each of one or more cameras which have captured the stereoscopic image; and decoding and restoring the image data of the stereoscopic image.Type: GrantFiled: February 25, 2009Date of Patent: November 3, 2015Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Yong-tae Kim, Gun-ill Lee, Dae-sik Kim
-
Patent number: 9165344Abstract: An image processing apparatus and method are disclosed.Type: GrantFiled: September 14, 2012Date of Patent: October 20, 2015Assignees: Kabushiki Kaisha Toshiba, Toshiba Medical Systems CorporationInventors: Pin Zhang, Hongfeng Ma
-
Patent number: 9165219Abstract: An image distortion correction method and an image distortion correction device are provided. The image distortion correction method uses a neural network model to perform a correcting operation on an original image so as to obtain a correction image with plural correction points. Firstly, a position coordinate of the correction point is inputted into the neural network model, so that a first direction coordinate correction amount is outputted from the neural network model. Then, the position coordinate of the correction point is inputted into the neural network model, so that a second direction coordinate correction amount is outputted from the neural network model. Afterwards, a pixel value of the original image corresponding to the first direction coordinate correction amount and the second direction coordinate correction amount is used as a pixel value of the correction point.Type: GrantFiled: February 7, 2014Date of Patent: October 20, 2015Assignee: NATIONAL CENTRAL UNIVERSITYInventors: Ching-Han Chen, Tun-Kai Yao
-
Patent number: 9165347Abstract: An apparatus, system, method, and article to continue border lines into an unknown region of an image from a known background; determine segments, based on the continued borders, for the unknown region of the image; and propagate pixels from a known area of the image to the unknown area based on the determined segments and continued borders.Type: GrantFiled: December 30, 2011Date of Patent: October 20, 2015Assignee: INTEL CORPORATIONInventors: Kirill Valerjevich Yurkov, Alexei Vladimirovich Belyakov
-
Patent number: 9167219Abstract: A method and an apparatus for automatic restoration of an image or a sequence of images, e.g. motion picture films, are disclosed, which facilitate removal of artifacts within the image or the sequence of images. The restoration is split into a detection process, a quality control process, and a removal process. In the detection process artifacts in the image or the sequence of images are detected and information about the detected artifacts is stored in a metadata database. In the subsequent quality control process the information about the detected artifacts is reviewed by an operator. In the removal process one or more of the detected artifacts are removed from the image or the sequence of images based on the information about the detected artifacts stored in the metadata database.Type: GrantFiled: June 8, 2011Date of Patent: October 20, 2015Assignee: Thomson LicensingInventors: Oliver Theis, Ralf Koehler, Oliver Kamphenkel
-
Patent number: 9153013Abstract: An image processing method comprising, dividing an input image into a plurality of divided images, calculating a difference image between a divided image before noise removal and a divided image after noise removal for each of the plurality of divided images, calculating a relative value between a pixel intensity in the divided image before noise removal and a pixel intensity in the difference image for each of the plurality of divided images, detecting a frequency distribution of relative values in a background area of the input image, contained in frequency distribution of relative values calculated with respect to the plurality of divided images, and estimating an intensity of noise in accordance with the frequency distribution of the relative values in the background area.Type: GrantFiled: June 17, 2013Date of Patent: October 6, 2015Assignee: PFU LIMITEDInventor: Du Jiyun
-
Patent number: 9148581Abstract: A multi-function control illumination device has a synchronization separator, a parameter setting device, a light emitting device, and a video processor. The synchronization separator connects with a video camera and the parameter setting device connecting with the light emitting device. The synchronization separator receives a video signal from the video camera, retrieves a synchronization signal from the video signal, and outputs the synchronization signal to the parameter setting device. The parameter setting device generates an electric signal corresponding to the synchronization signal according to at least one illumination parameter and outputs the electric signal to the light emitting device. The light emitting device emits toward a shooting direction of the video camera a light beam whose intensity periodically varies according to the electric signal.Type: GrantFiled: May 9, 2013Date of Patent: September 29, 2015Assignee: National Chiao Tung UniversityInventors: Jen-Hui Chuang, Wen-Chih Teng
-
Patent number: 9141869Abstract: A method of identifying anomalies in images produced using an imaging device (70). The method comprises receiving (10), (12) first and second pluralities of candidate anomalies, the candidate anomalies being identified in subsequent images produced with an imaging device. A constellation match (14), (16), (18), (19) is carried out between the first and second pluralities of candidate anomalies to identify a correlation therebetween, represented by a constellation match value. A plurality of constellation match values is determined with a different relative x-y shift between the first and second pluralities of candidate images. If a good correlation is found at a particular x-y shift then the candidate anomalies are common between the first and second images, which is indicative of the first and second images including anomalies.Type: GrantFiled: October 24, 2011Date of Patent: September 22, 2015Assignee: Optos PLCInventors: David Clifton, Craig Robertson
-
Patent number: 9137438Abstract: A biometric image sensor system and method is disclosed which may comprise a first light source having a first wavelength ?1, a second light source having a second wavelength ?2, a photodetector configured and positioned to receive light of the first wavelength ?1 and light of the second wavelength ?2 reflecting from a biometric object being imaged and to produce a first output indicative of the amount of reflectance of the light of the first wavelength ?1 and a second output indicative of the amount of reflectance of the light of the second wavelength ?2, and a computing device configured to compare the difference between the first output and the second output with an authenticity threshold.Type: GrantFiled: February 8, 2013Date of Patent: September 15, 2015Assignee: Synaptics IncorporatedInventors: Richard Alexander Erhart, Erik Jonathon Thompson, Jaswinder Jandu, Pamela Percy