Point Features (e.g., Spatial Coordinate Descriptors) Patents (Class 382/201)
-
Publication number: 20110242616Abstract: An image processing apparatus comprises an anchor point candidate information extraction unit configured to decide coordinates of anchor point candidates and attributes of the anchor point candidates based on a plurality of predetermined extraction rules and a sequence of coordinate points that expresses an outline of image data; an anchor point decision unit configured to decide an anchor point candidate to be reduced based on the attributes of the anchor point candidates and priority orders set in advance for the attributes, and configured to decide anchor points by reducing the decided anchor point candidates to be reduced; a control point coordinate decision unit configured to decide control point coordinates based on the anchor points decided by the anchor point decision unit and the sequence of coordinate points; and a data output unit configured to output information including the coordinates of the decided anchor points and the decided control point coordinates.Type: ApplicationFiled: March 15, 2011Publication date: October 6, 2011Applicant: CANON KABUSHIKI KAISHAInventor: Hiroshi Oto
-
Publication number: 20110235923Abstract: A method of implementing accurate digitization from a georeferenced image is described. In one embodiment, at least one set of coordinates which have been measured at a point of interest is received. A correction is then determined which describes a difference between the at least one set of coordinates and a set of georeferenced coordinates from a georeferenced image of the point of interest which describes the position of the point of interest.Type: ApplicationFiled: June 3, 2011Publication date: September 29, 2011Inventors: Shawn D. Weisenburger, Peter G. France, James M. Janky
-
Publication number: 20110200259Abstract: There is disclosed a method for seamlessly replacing areas in a digital image with corresponding data from temporally close digital images depicting substantially the same scene. The method uses localized image registration error minimization over a fixed preliminary boundary. A least cost closed path which constitutes a boundary for the area to be replaced is calculated using dynamic programming. The replacement area is blended such that image data information from one image is seamlessly replaced with image data information from another image.Type: ApplicationFiled: February 14, 2011Publication date: August 18, 2011Inventors: Alexander LINDSKOG, Gustaf PETTERSSON, Ulf HOLMSTEDT, Johan WINDMARK, Sami NIEMI
-
Publication number: 20110194151Abstract: An image processing apparatus includes a binarization section, a determination section and an area setting section. The binarization section binarizes a given image. The determination section determines whether or not a pixel to be determined is effective in accordance with the number of pixels of one value of a binary value in each of determination areas. Each of the determination areas are placed so as not to contain the pixel to be determined in the binarized image and so as not to overlap in a predetermined direction of the pixel to be determined. The area setting section sets an area including the pixel determined effective in the determination section.Type: ApplicationFiled: July 30, 2010Publication date: August 11, 2011Applicant: FUJI XEROX CO., LTD.Inventor: Kosuke Maruyama
-
Patent number: 7991233Abstract: A method (1100) of creating an editable document is disclosed. The method analyses a bitmap image to detect at least one bit map representation of a graphical object and a bitmap representation of a line object. The method matches the graphical object with one of a plurality of predetermined template shapes (e.g., 420), the template shape having one or more predetermined non-contiguous connection points. The method selects one of the predetermined connection points for the line object if at least one end of the line object is within a predetermined distance of the selected connection point and associates the line object with the selected connection point. The method creates an editable document comprising the template shape with the line object connected thereto, wherein the line object remains associated with the selected connection point upon the template shape being modified within the document such that the line object remains dynamically connected to the template shape.Type: GrantFiled: November 29, 2007Date of Patent: August 2, 2011Assignee: Canon Kabushiki KaishaInventors: James Austin Besley, Eric Wai-Shing Chong, Khanh Phi Van Doan, Steven Richard Irrgang
-
Publication number: 20110182476Abstract: An apparatus and method capable of calculating a coordinate transformation parameter without having to utilize a rig are provided. The apparatus and method extract a first feature point based on a plane of first data, project the first feature point onto second data and then extract a second feature point from a part of the second data onto which the first feature point is projected. Then, calibration is performed based on the extracted feature points. Therefore, it is possible to perform calibration immediately as necessary without having to utilize a separate device such as a rig.Type: ApplicationFiled: December 7, 2010Publication date: July 28, 2011Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Dong-Jo Kim, Dong-Ryeol Park
-
Publication number: 20110176734Abstract: An apparatus and method for recognizing a specific area of an image in a portable terminal. More particularly, an apparatus and method are for determining feature points with very high similarities as one group when the portable terminal recognizes a building included in an image or a picture, and for estimating a matching relation of the group to improve building recognition performance. The apparatus includes an image analyzer configured to, upon extracting feature points used for building recognition, classify feature points with similarities among the extracted feature points into a group, and recognize a building after estimating a matching relation by regarding the classified group as a feature point.Type: ApplicationFiled: January 21, 2011Publication date: July 21, 2011Applicants: SAMSUNG ELECTRONICS CO., LTD., SNU R&DB FOUNDATIONInventors: Sang-Hwa Lee, Seong-Jong Ha, Hyun-Su Hong, Nam-Ik Cho, Gye-Joong Shin, Sang-Uk Lee
-
Patent number: 7983489Abstract: A system, method, and computer-readable media are presented for presenting similar images of a selected image in a user interface. One embodiment of the method can include identifying a selected first image and identifying a selected direction from the first image. Additionally, the method can include calculating a best neighbor metric for each of one or more other images to determine a best neighbor image in the selected direction. Furthermore, the method can include presenting the best neighbor image to a user in a user interface.Type: GrantFiled: July 9, 2010Date of Patent: July 19, 2011Assignee: Microsoft CorporationInventors: Blaise H. Aguera y Arcas, Jonathan R. Dughi, Bryan Ressler, Ian A. Gilman, Alfred Astort, David M. Gedye
-
Publication number: 20110161999Abstract: A widget running on user equipment selectively obscures portions of media content according to user and/or service provider defined criteria. Information regarding potentially objectionable content in media content may be stored in databases. Based on the information regarding potentially objectionable content and the defined criteria, the database may provide censor instructions. The instructions may be executed by the widget to obscure the potentially objectionable content in media content that is accessed by the user equipment.Type: ApplicationFiled: December 30, 2009Publication date: June 30, 2011Applicant: ROVI TECHNOLOGIES CORPORATIONInventors: Walter R. Klappert, David D. Chung, Samson Bekele
-
Publication number: 20110156887Abstract: A method and system for forming a surrounding seamless bird-view image by processing a plurality of surrounding images associated with a carrier captured by different imaging devices is provided in the present invention. During the process, the surrounding images are converted into corresponding bird-images respectively and then an overlapping area corresponding to each two adjacent bird-view images is determined. After that, distances between the pixel in the overlapping area and the boundary of the overlapping area in each adjacent bird-view image is calculated so as to determine a weighting value for each corresponding pixel in each adjacent bird-view image thereby forming an overlapping image, wherein each pixel in the overlapping image is determined according to the weighting value and information of the corresponding pixel in each adjacent image. After determining the overlapping image for each two adjacent bird-view image, it is capable of forming the surrounding seamless bird-view image.Type: ApplicationFiled: February 8, 2010Publication date: June 30, 2011Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTEInventors: Hsin-Liang SHEN, Kuo-Hsiang Cheng, Tung-Chuan Wu, Din-Chang Tseng
-
Publication number: 20110158544Abstract: An information processing apparatus includes an information input section that reads input image information, a cumulative image information generator that generates cumulative image information for pixels corresponding to positions of pixels of a prescribed pixel pattern in the read input image information, and a memory controller that stores in the cumulative image information holding memory the cumulative image information generated in the cumulative image information generator. This configuration allows memory resources necessary for holding the cumulative image information to be reduced.Type: ApplicationFiled: December 16, 2010Publication date: June 30, 2011Applicant: CANON KABUSHIKI KAISHAInventor: Noriyasu Hashiguchi
-
Publication number: 20110158533Abstract: Apparatus for matching a query image against a catalog of images, comprises: a feature extraction unit operative for extracting principle features from said query image; a relationship unit operative for establishing relationships between a given principle feature and other features in the image, and adding said relationships as relationship information alongside said principle features; and a first comparison unit operative for comparing principle features and associated relationship information of said query image with principle features and associated relationship information of images of said catalog to find candidate matches.Type: ApplicationFiled: December 27, 2010Publication date: June 30, 2011Applicant: PicScout (Israel) Ltd.Inventors: Offir GUTELZON, Uri Lavi, Ido Omer, Yael Shor, Simon Bar, Golan Pundak
-
Publication number: 20110135158Abstract: Provided is an image processing device which includes an optical flow computation unit computing optical flow within an image with reference to a past image, an optical flow detection unit setting multiple reference points in a partial region of the image and detecting whether or not optical flow is generated at the reference points, a feature point data storage unit storing, when optical flow is generated at the reference points, as a feature point a set of peaces of pixel data that generated the optical flow, a feature point tracking unit tracking a motion position of the feature point, a feature point deletion unit deleting the tracked feature point in accordance with a variation in motion position of the feature point, and a passage determination unit determining whether or not passage of an object is detected within the image based on multiple remaining undeleted feature points.Type: ApplicationFiled: December 2, 2010Publication date: June 9, 2011Inventors: Katsuaki Nishino, Nobuhiro Tsunashima
-
Publication number: 20110135206Abstract: An image correction device is provided with a CPU (22). The CPU (22) calculates the square values of the differences between pixel values of a transformed frame image In+1 and pixel values of a frame image In at the identical coordinates thereof each time predetermined values are set in the amount of translation and the amount of rotation, respectively, and a first transform frame image is generated; integrates the square values corresponding to all identical coordinates, where at least the transformed frame image In+1 and the frame image In overlap, so as to derive the error function; searches for the minimum value of the derived error function by using the Broyden-Fletcher-Goldfarb-Shanno (BFGS) method; and extracts the affine transform parameters, which are obtained at the minimum value of the error function, as the amount of change of the frame image In+1 relative to the frame image In.Type: ApplicationFiled: June 22, 2009Publication date: June 9, 2011Inventors: Kenjiro Miura, Kenji Takahashi
-
Patent number: 7953280Abstract: A distribution-based anomaly detection platform is described that identifies a non-flat background that is specified in terms of the distribution of the data. A resampling approach is also disclosed employing scrambled resampling of the original data with one class specified by the data and the other by the explicit distribution, and solving using binary classification.Type: GrantFiled: October 12, 2007Date of Patent: May 31, 2011Assignee: Los Alamos National Security LLCInventors: James P. Theiler, Simon J. Perkins
-
Publication number: 20110123068Abstract: A method of reducing the spatial resolution of images is disclosed. At least one embodiment of the method includes: —acquiring an input image including image parts having a spatial resolution larger than SR pixels/meter; —acquiring a depth map associated with the input image; —determining for each pixel p(x,y) a spatial resolution value by means of the depth map; —processing a region of pixels of the input image for which holds that the spatial resolution value is larger than a predefined threshold corresponding to SR pixels/meter to obtain a corresponding region of pixels having a spatial resolution smaller then or equal to SR pixels/meter in an output image. The method enables to removes privacy information from images by reducing the spatial resolution to a level that the privacy information cannot be recognized in the image anymore.Type: ApplicationFiled: September 25, 2008Publication date: May 26, 2011Inventors: Krzysztof Miksa, Marcin Michal Kmiecik
-
Publication number: 20110123090Abstract: A method for determining a contour of an object in a digital image includes determining a preliminary object center and determining contour candidate image points. The contour candidate image points are determined as image points on a plurality of paths leading away from a preliminary object center by detecting a change from a first section to a second section on a feature space based on the image point value range of the digital image or by detecting the exceeding of a predetermined strength of a feature change in the feature space, wherein the contour candidate image points have a distance to the preliminary or to an improved object center and are ordered according to a polar angle. Further, the method includes determining zones of neighboring contour candidate image points within which a change of the distance of the contour candidate image points lies above a threshold value and an elimination of contour candidate image points which lie between the zones of neighboring contour candidate image points.Type: ApplicationFiled: December 29, 2010Publication date: May 26, 2011Applicant: Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V.Inventors: Thorsten ZERFASS, Tobias BERGEN, Dirk STECKHAN
-
Publication number: 20110103698Abstract: In verification of image data of a captured image as to whether it is original one, the verification is possible even for image data subjected to a peripheral illumination correction or an exposure correction. An order information calculation unit selects a pixel set including two or more pixels based on pixel values and information on an image space of image data of a captured image, and calculates an order of magnitude between pixels in the selected pixel set. A verification data producing unit generates verification data used in verification of whether the image data has not been tampered with, based on the calculated order of magnitude. An image output unit outputs the image data and the verification data.Type: ApplicationFiled: October 28, 2010Publication date: May 5, 2011Applicant: CANON KABUSHIKI KAISHAInventors: Junichi Hayashi, Nobuhiro Tagashira, Kazuya Kishi, Yasuhiro Nakamoto, Yoshiharu Imamoto, Jun Tamaru
-
Publication number: 20110091115Abstract: A feature point positioning apparatus positions a plurality of feature points for a predetermined pattern in image data. The apparatus selectively executes first candidate decision processing which decides position candidates of the feature points and second candidate decision processing which decides position candidates of the feature points at a higher processing speed than the first candidate decision processing in accordance with an operation mode, and executes, when the operation mode is a high-speed mode in which an operation is executed at a higher speed than a normal mode, the second candidate decision processing for more feature points than in the normal mode; and corrects the position candidates of the plurality of feature points obtained by the first candidate decision processing and the second candidate decision processing based on a layout relationship among the plurality of feature points.Type: ApplicationFiled: October 6, 2010Publication date: April 21, 2011Applicant: CANON KABUSHIKI KAISHAInventors: Masami Kato, Katsuhiko Mori
-
Patent number: 7929767Abstract: A mechanism for recognizing and inputting handwritten mathematical expressions into a computer by providing part of a multi-path framework is described. The part of the multi-path framework includes a subordinate sub-expression analysis component. A method for analyzing a handwritten mathematical expression for a subordinate sub-expression includes identifying sub-expressions based on dominant symbols and determining a character for potential dominant symbols based upon sub-expression information. A determination may be made whether an expression structure candidate is valid and valid expression structure candidates may be stored in a parse tree.Type: GrantFiled: June 20, 2005Date of Patent: April 19, 2011Assignee: Microsoft CorporationInventors: Mingqing Xu, Yu Zou, Lei Huang, Jian-Lai Zhou, Xiaohui Hou, Zhouchen Lin, Dongmei Zhang, Jian Wang
-
Patent number: 7929772Abstract: A method for generating typographical line is provided. In the present method, an asymptote of an upper or a lower edge of a line of printing words is obtained first. Then, two typographical lines of the other edge of the line of printing words are obtained according to the asymptote. Two typographical lines of the present edge of the line of printing words are obtained based on the previously obtained typographical lines. Finally, the relations of these typographical lines and edge reference points of the line of printing words are used for removing useless typographical lines. Therefore, the typographical lines obtained by the present invention can provide the means of recognizing word direction, large or small character writing, and punctuation marks, so as to increase the efficiency and accuracy of character recognition.Type: GrantFiled: June 27, 2007Date of Patent: April 19, 2011Assignee: Compal Electronics Inc.Inventors: Wen-Hann Tsai, Hsin-Te Lue
-
Publication number: 20110064288Abstract: Described herein is a computer-aided technology for facilitating detection of folds of an object surface. In one implementation, image data is processed to determine curvature characteristics at one or more points of the surface of a region of interest. If the curvature characteristics of one of the one or more points correspond to a hyperbolic curvature, the point is identified as a seed point. A region of a predetermined thickness is grown around the seed point so as to detect the presence of any fold feature within the grown region.Type: ApplicationFiled: September 10, 2010Publication date: March 17, 2011Applicant: SIEMENS MEDICAL SOLUTIONS USA, INC.Inventor: Yoshihisa Shinagawa
-
Publication number: 20110058029Abstract: Multiple template images to be evaluated are used to carry out pattern matching with multiple images, correlation coefficients among the multiple template images are computed based on the results of the pattern matchings, and the template images are evaluated based on the computation result. As a result, the template images can be evaluated in the selection of template images used for pattern matching.Type: ApplicationFiled: September 2, 2010Publication date: March 10, 2011Applicant: CANON KABUSHIKI KAISHAInventors: Junko Nakajima, Norihiko Utsunomiya
-
Publication number: 20110052080Abstract: In right and left white road line detection regions on a image, a stereo image recognition device of a white road line recognition device for a vehicle detects a pair of a white road line starting point and a white road line ending point for each of retrieval lines set in the horizontal direction based on the change in the luminance on the retrieval lines, calculates a midpoint Pm between each pair of the white road line starting point and white road line ending point, selects a point group with a smaller dispersion between the point group consisting of the white road line starting points and the point group consisting of midpoints based on a predetermined condition, and calculates a white road line based on the selected point group.Type: ApplicationFiled: August 17, 2010Publication date: March 3, 2011Applicant: Fuji Jukogyo Kabushiki KaishaInventors: Yuichiro Tamura, Toru Saito
-
Patent number: 7894640Abstract: It is an object of an identification apparatus of the present invention to realize a face identification in such a way that a system user does not worry that other people take a glance at a user's own face image when the user gets the face image for use in face identification. An identification apparatus of the present invention includes a capturing device 22 for capturing an image, a face template database 254 for storing various images, an alternative image generation controlling portion 251 for specifying a first area, which contains at least a part of a face, out of the image captured by the capturing portion and then replacing the first area of the image captured by the capturing portion with an image stored in the face template database 254, and a displaying device 23 for displaying an image generated by the alternative image generation controlling portion 251.Type: GrantFiled: July 27, 2006Date of Patent: February 22, 2011Assignee: Panasonic CorporationInventor: Katsuyuki Itou
-
Publication number: 20110037563Abstract: A biometric register includes: a feature extraction unit for performing preprocessing for a fingerprint to extract a feature point m for the fingerprint; a transformation function generation unit for generating a transformation function which is composed of an arbitrary rotation matrix and an arbitrary vector; and a template generation unit for transforming a coordinate of the feature point m using the generated transformation function, and organizing a fuzzy vault using a randomly generated fake feature point and a feature point m1 applied by the transformed coordinate, thereby generating a one-time template.Type: ApplicationFiled: November 9, 2009Publication date: February 17, 2011Applicant: Electronics and Telecommunictions Research InstituteInventors: Woo Yong Choi, Dae Sung Moon, Yongjin Lee, Ki Young Moon, Jang-Hee Yoo, Yun Su Chung, So-Hee Park, Byung Jun Kang
-
Publication number: 20110026833Abstract: A system capable of recognizing position, a shape, a posture and the like of an object present in a marginal environment of a device such as a robot in order to make the device perform operations on the object as a subject. In an environment recognition system, 3D information and physical information (color information and the like) of a subject are associated by using camera parameters of each of a 3D image senor a 2D image sensor. Thereby, the position, the posture and the shape related to the subject and the physical information of the subject present in the environment of a robot are obtained.Type: ApplicationFiled: August 3, 2010Publication date: February 3, 2011Applicant: HONDA MOTOR CO., LTD.Inventors: Tsukasa SUGINO, Ryujin WATANABE
-
Patent number: 7873220Abstract: A method and algorithm for measuring the symmetry (SYM=total symmetry) of N points based on counting the number of “elementary symmetric recognition acts”, or having two distances d(A,B) and d(C,D) be equal within a given tolerance t. The same algorithm can be adapted to measure un-normalized positional entropy deficit (UPED) and positional entropy of N points. These parameters (SYM and UPED) come out almost the same for small occupation numbers (1<=k<=4). Here the occupation number k is the number of equal distances in the figure for a given value d. The algorithm can be incorporated into an imaging device, such as computer graphic programs or cameras, to solve problems of defect detection, say in gems, or object detection.Type: GrantFiled: March 9, 2007Date of Patent: January 18, 2011Inventor: Dennis G. Collins
-
Publication number: 20110007974Abstract: The present invention discloses an object detection apparatus and method. A feature extracting section of the present invention comprises: a feature point extracting section, for extracting a combination of predetermined feature point pairs from an image; a pixel value obtaining section, for obtaining a pixel value of each feature point in the combination of feature point pairs; a feature point comparing section, for comparing, in accordance with the pixel values obtained by the pixel value obtaining section, two feature points in each feature point pair to obtain a logical value; and an feature obtaining section, for determining the feature of the image in accordance with the logical value.Type: ApplicationFiled: December 24, 2008Publication date: January 13, 2011Inventors: Haizhou Ai, Chang Huang, Shihong Lao, Takayoshi Yamashita
-
Publication number: 20100331041Abstract: Method, device, system and framework for enabling token and point level operations on language independent paper documents through camera phone interface. Image descriptors from snapshots of document captured by the phone can be extracted by phone itself and transmitted to server. In another implementation, the descriptors are extracted by receiving server. The server is connected to database of high-quality images of the same document and matched high-quality patch is sent back to phone for user's viewing and manipulation. Modifications and annotations of high-quality patch are transmitted to database and stored. Motion detection is combined with image recognition to provide high quality images of regions of document being viewed by sweeping the phone.Type: ApplicationFiled: June 26, 2009Publication date: December 30, 2010Applicant: FUJI XEROX CO., LTD.Inventors: Chunyuan Liao, Qiong Liu
-
Publication number: 20100310177Abstract: A computer implemented method for point matching comprising providing a pair of images captured, selecting first and second sets of interest points from the images; constructing a control network of super points for each set of interest points; assigning a position, with respect to the closest network control point of each control network, to other interest points on the images; locating conjugate points for each other interest point of each set based on its assigned position; and adding the conjugate points to the control network.Type: ApplicationFiled: May 6, 2010Publication date: December 9, 2010Applicant: UNIVERSITY OF NEW BRUNSWICKInventors: Zhen Xiong, Yun Zhang
-
Publication number: 20100309226Abstract: For retrieving information based on images, a first image is taken (S1) using a digital camera associated with a communication terminal (1). Query data related to the first image is transmitted (S3) via a communication network (2) to a remote recognition server (3). In the remote recognition server (3) a reference image is identified (S4) based on the query data. Subsequently, in the remote recognition server (3), a Homography is computed (S5) based on the reference image and the query data, the Homography mapping the reference image to the first image. Moreover, in the remote recognition server (3), a second image is selected (S6) and a projection image is computed (S7) of the second image using the Homography. By replacing a part of the first image with at least a part of the projection image, an augmented image is generated (S8, S10) and displayed (S11) at the communication terminal (1).Type: ApplicationFiled: May 8, 2007Publication date: December 9, 2010Applicants: EIDGENOSSISCHE TECHNISCHE HOCHSCHULE ZURICH, KOOABA AGInventors: Till Quack, Herbert Bay
-
Publication number: 20100309289Abstract: A 3D positioning apparatus is used for an object that includes feature points and a reference point. The object undergoes movement from a first to a second position. The 3D positioning apparatus includes: an image sensor for capturing images of the object; and a processor for calculating, based on the captured images, initial coordinates of each feature point when the object is in the first position, initial coordinates of the reference point, final coordinates of the reference point when the object is in the second position, and final coordinates of each feature point. The processor calculates 3D translational information of the feature points using the initial and final coordinates of the reference point, and 3D rotational information of the feature points using the initial and final coordinates of each feature point. A 3D positioning method is also disclosed.Type: ApplicationFiled: December 29, 2009Publication date: December 9, 2010Applicant: National Taiwan UniversityInventors: Homer H. Chen, Ping-Cheng Chi
-
Patent number: 7848547Abstract: An apparatus for detecting a feature point includes an image input unit that inputs an image of the target object; a three-dimensional shape information holding unit that stores three-dimensional shape information including reference feature points of a model relating to the target object; a correspondence relation acquiring unit that acquires a correspondence relation between the input image and the three-dimensional shape; a seek area acquiring unit that acquires image information of a seek area on the input image corresponding to an area including a point corresponding to the specific feature point in the model on the basis of the correspondence relation; and a feature point detecting unit that detects the position of the specific feature point in the input image from the image information.Type: GrantFiled: March 1, 2007Date of Patent: December 7, 2010Assignee: Kabushiki Kaisha ToshibaInventors: Tomoyuki Takeguchi, Tatsuo Kozakaya, Masahide Nishiura, Osamu Yamaguchi, Mayumi Yuasa
-
Publication number: 20100303364Abstract: Provided is an image quality evaluation method for evaluating image qualities of a second image by using a difference from a first image. In the image quality evaluation method, a representative pixel component value indicating a pixel component value that represents pixels in the image frame of one of the images, and pixel position information indicating a pixel position where the representative pixel component value appears are extracted as a feature quantity. By using the representative pixel component value and the pixel position information, which are the image feature quantity, and based on a difference between a pixel component value at the pixel position indicated by the pixel position information in the image frame of the other image and the representative pixel component value, a difference of the entire second image from the first image is estimated.Type: ApplicationFiled: October 18, 2007Publication date: December 2, 2010Applicant: NEC CORPORATIONInventor: Toru Yamada
-
Publication number: 20100290669Abstract: The present invention provides an image judgment device that can prevent increase in a storage capacity to store element characteristic information.Type: ApplicationFiled: December 12, 2008Publication date: November 18, 2010Inventors: Hiroto Tomita, Akihiko Inoue
-
Publication number: 20100278435Abstract: A system, method, and computer-readable media are presented for presenting similar images of a selected image in a user interface. One embodiment of the method can include identifying a selected first image and identifying a selected direction from the first image. Additionally, the method can include calculating a best neighbor metric for each of one or more other images to determine a best neighbor image in the selected direction. Furthermore, the method can include presenting the best neighbor image to a user in a user interface.Type: ApplicationFiled: July 9, 2010Publication date: November 4, 2010Applicant: Microsoft CorporationInventors: Blaise H. Aguera y Arcas, Jonathan R. Dughi, Bryan Ressler, Ian A. Gilman, Alfred Astort, David M. Gedye
-
Publication number: 20100272328Abstract: The present invention relates to a face authentication system and an authentication method thereof.Type: ApplicationFiled: June 23, 2009Publication date: October 28, 2010Applicant: Samsung Electro-Mechanics Co., Ltd.Inventor: Kyoung Tai LEE
-
Patent number: 7822245Abstract: A method for detecting a response of each probe zone on a test strip is provided. The present method includes providing a test strip having a color pattern displayed thereon. The color pattern occurs in response to a tested solution contacting with the test strip and including a plurality of color lines displayed in sequence from a bottom portion of the test strip to a top portion thereof. The site of each color line represents a probe zone of the test strip. Capturing a whole image of the test strip and selecting at least one scan line perpendicular to the image of the color lines therefrom. Setting a pixel position of the scan line having a minimum pixel value corresponding to a bottom edge of the test strip and using the pixel position as a reference to identify respective pixel positions of the color lines on the scan line so as to identify the image positions thereof on the whole image.Type: GrantFiled: February 13, 2007Date of Patent: October 26, 2010Inventor: Kuo-Jeng Wang
-
Publication number: 20100238034Abstract: The present invention discloses a system and a process for rapidly detecting drowsiness in a individual operating a machine. The system can capture a plurality of facial images of the individual and compare one or more facial parameters from the images to a plurality of stored high priority sleepiness facial actions that are in a prioritized action database. Based on the comparison, a current level of sleepiness can be determined for the individual and an actuator can be actuated in order to alert the individual and possibly any other individuals that may be in the vicinity.Type: ApplicationFiled: March 23, 2009Publication date: September 23, 2010Applicant: Toyota Motor Engineering & Manufacturing North America, Inc.Inventor: Pujitha Gunaratne
-
Publication number: 20100232709Abstract: The invention relates to a method for estimating an image relation model for two or more related images based on a plurality of point correspondences. The method includes using a weighted random sampling algorithm to repeatedly draw subsets of point correspondences for generating model estimates, evaluating said model estimates for the full plurality of the point correspondences, and updating weights associated with each of the point correspondences in the random sampling algorithm based on information obtained in said evaluating.Type: ApplicationFiled: December 8, 2009Publication date: September 16, 2010Inventors: Liang Zhang, Demin Wang, Houman Rastgar, André Vincent
-
Patent number: 7792622Abstract: The method and system for vehicular guidance comprises an imaging device for collecting color image data to facilitate distinguishing crop image data (e.g., crop rows) from background data. A definer defines a series of scan line segments generally perpendicular to a transverse axis of the vehicle or of the imaging device. An intensity evaluator determines scan line intensity data for each of the scan line segments. An alignment detector (e.g., search engine) identifies a preferential heading of the vehicle that is generally aligned with respect to a crop feature, associated with the crop image data, based on the determined scan line intensity meeting or exceeding a maximum value or minimum threshold value.Type: GrantFiled: December 15, 2005Date of Patent: September 7, 2010Assignees: Deere & Company, Kansas State University Research FoundationInventors: Jiantao Wei, Shufeng Han
-
Patent number: 7787651Abstract: Reducing the number of hypotheses for locations of an active object in a saved image generated by a graphical user interface (GUI) of an application program may be accomplished by determining possible triangles for the saved image, wherein vertices of the triangles are points where the active object and any two additional objects of the saved image are located, determining possible pairs of hypotheses corresponding to the two additional objects from a current playback image corresponding to the saved image, determining triangles corresponding to the possible pairs of hypotheses and filtering the detected triangles, determining vertices with weights for similar triangles of the current playback image, and calculating a weight for every hypothesis of the active object and filtering hypotheses of the active object on the current playback image based on a weight bound.Type: GrantFiled: November 11, 2005Date of Patent: August 31, 2010Assignee: Intel CorporationInventor: Denis Sergeevich Milov
-
Patent number: 7787677Abstract: A presentation method and a presentation device presents an image of an object, wherein a starting image and at least one target image of the object, a first location within the starting image, and a second location within the starting image and the at least one target image are provided. The second location is the location of a reference feature detectable in the starting image and the at least one target image. A corridor is determined in the at least one target image, wherein the corridor contains a circular line, wherein the circular line defines a circle, whose radius corresponds to a distance between the first location and the second location in the starting image and whose centre position corresponds to said second location. Finally, the corridor and the at least one target image are presented.Type: GrantFiled: August 16, 2006Date of Patent: August 31, 2010Assignee: MeVis BreastCare GmbH & Co. KGInventors: Carl J. G. Evertsz, Anke Bödicker
-
Publication number: 20100215249Abstract: A method of decomposing a set of scans of different views of overlapping objects into constituent objects is presented. The method involves an initialization process whereby keypoints in two views are determined and matched, disparity between keypoint pairs are computed, and the keypoints are grouped into clusters based on their disparities. Following the initialization process is an iterative optimization process whereby a cost function is calculated and minimized assuming a fixed composition matrix and re-solved assuming a fixed attenuation coefficient. Then, the composition matrix and the attenuation coefficient are updated simultaneously, and the solving, the re-solving, and the updating steps are repeated until there is no significant improvement in the result.Type: ApplicationFiled: February 20, 2009Publication date: August 26, 2010Inventors: Geremy Heitz, Gal Chechik
-
Publication number: 20100195914Abstract: Methods are disclosed for finding images from a large corpus of images that at least partially match a query image. The present method makes use of feature detectors to bundle features into local groups or bundles. These bundled features are repeatable and much more discriminative than an individual SIFT feature. Equally importantly, the bundled features provide a flexible representation that allows simple and robust geometric constraints to be efficiently enforced when querying the index.Type: ApplicationFiled: February 2, 2009Publication date: August 5, 2010Inventors: Michael Isard, Qifa Ke, Jian Sun, Zhong Wu
-
Patent number: 7769227Abstract: An object detector includes a brightness change calculating section (103) that calculates the change in brightness in an image, a three-dimensional object detecting section (105) that uses three-dimensional information measured from a plurality of images to detect a three-dimensional object, an object candidate extracting section (106) that refers to the three-dimensional object detection results and the brightness change calculation result to extract a moving object candidate area and a still object candidate area, and an object judging section (107) that judges whether or not the candidate area is an object. In this way, the object detector refers to the change in brightness in the area detected as a three-dimensional object to judge whether the detected three-dimensional object is a moving object or a still object. Therefore, a still object in the image can be accurately detected without using background difference processing.Type: GrantFiled: August 30, 2005Date of Patent: August 3, 2010Assignee: Panasonic CorporationInventor: Seiji Kigasawa
-
Publication number: 20100189361Abstract: Image processing apparatus and methods are provided for detecting coordinate positions of characteristic portions of a face image in a target image. A method includes identifying a face area of the target image, determining initial coordinate positions for the characteristic portions, determining corrected coordinate positions for the characteristic portions by modifying the initial coordinate positions or previously generated corrected coordinate positions, and identifying the corrected coordinate positions as the coordinate positions of the characteristic portions of the face image.Type: ApplicationFiled: January 27, 2010Publication date: July 29, 2010Applicant: SEIKO EPSON CORPORATIONInventors: Masaya Usui, Kenji Matsuzaka
-
Publication number: 20100188519Abstract: An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points; an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation.Type: ApplicationFiled: January 15, 2010Publication date: July 29, 2010Inventors: Keisuke YAMAOKA, Jun Yokono
-
Patent number: RE42256Abstract: A background subtraction apparatus of the present invention includes a key point locator for locating key points on a known object type, a boundary point locator for locating boundary points of the known object that make up the edges of the known object, and an edge processor for processing the edges to provide a clean-edged extraction of the known object from a background image. Preferably, the key point locator includes an alignment detector for detecting alignment of an image of the known object type with a skeleton image. Still more preferably, the skeleton image is an exoskeleton image and the known object type is a human being.Type: GrantFiled: January 9, 2009Date of Patent: March 29, 2011Assignee: Elet Systems L.L.C.Inventor: Jeffrey L. Edwards