Patents Examined by Amelia M. Au
-
Patent number: 6628820Abstract: Upon observation of multi-viewpoint images, even when the viewpoint moves continuously, the image cannot normally be displayed in correspondence with the continuous movement of the viewpoint, and an image from a viewpoint closest to the current viewpoint is displayed. To prevent this, each two adjacent images of the multi-viewpoint images are interpolated by detecting corresponding pixels and generating an interpolated image in accordance with the correspondences among pixels. The interpolated image is generated in such a manner that an epipolar plane image is generated by juxtaposing corresponding lines of the multi-viewpoint image, straight lines are detected from the epipolar plane image, and the intersecting points between interpolated lines and the detected straight lines are detected as interpolated pixels. In this case, as for a point for which a straight line cannot be detected, a straight line passing the point is estimated, thereby generating an interpolated pixel.Type: GrantFiled: May 30, 2001Date of Patent: September 30, 2003Assignee: Canon Kabushiki KaishaInventors: Takahiro Oshino, Hideyuki Tamura, Akihiro Katayama, Hiroyuki Yamamoto, Koichiro Tanaka
-
Patent number: 6625304Abstract: Displacement of a first block of pixels from a first to a second image of a scene is determined for applications of automated distance computation. The selection of corresponding blocks in the two images is performed and verified as follows. A first block is taken from the first image. A first region is selected from a set of first regions in the second image, so that a difference between an image content of the first region and of the first block is minimal among the set of first regions. A second block is taken from the second image, the second block containing at least part of the selected first region. A second region is selected from a set of second regions in the first image, so that a difference between an image content of the second region and of the second block is minimal among the set of second regions. A first displacement between the first block and the selected first region is compared with a second displacement between the second block and the selecting second region.Type: GrantFiled: March 24, 2000Date of Patent: September 23, 2003Assignee: Koninklijke Philips Electronics N.V.Inventor: Johannes Bruijns
-
Patent number: 6621926Abstract: An image retrieval system and method using an image histogram for determining central points and dispersion values as well as quantity information of color about respective histogram bins, thereby using these as mapping information for image retrieval. The image retrieval method using an image histogram includes the following steps. A first step of computing an image histogram bin when an image is inputted, and accumulating values of x, y, x2, y2 to compute central points and dispersion values. A second step of normalizing the respective central points and dispersion values through dividing these by size of whole image, and storing these. A third step of generating a value of model to be retrieved by drawing a feature vector when a query image is inputted, and computing the difference between the generated value of model and central points and dispersion values of an image histogram, count, and number of corresponding bins within the data stored in the second step.Type: GrantFiled: February 4, 2000Date of Patent: September 16, 2003Assignee: Electronics and Telecommunications Research InstituteInventors: Ho Sub Yoon, Jung Soh, Byung Woo Min, Young Kyu Yang
-
Patent number: 6621940Abstract: An image is rotated in opponent color space, such as L*a*b* or Y CB CR color space, by inputting the opponent color space image data, subsampling the opponent color space image data, and addressing the subsampled opponent color space image data into an output configuration corresponding to a specified rotation angle. For 90° and 270° rotation, the opponent color space image data is scaled before being addressed. This eliminates distortion of the rotated image, while allowing real-time rotation of the image in hardware.Type: GrantFiled: June 10, 1999Date of Patent: September 16, 2003Assignee: Xerox CorporationInventors: Robert M. Chapin, Anthony M. Frumusa
-
Patent number: 6618502Abstract: In a first signal suppressing process, in cases where a signal level of a certain color signal among color signals obtained from an image sensing operation is higher than a predetermined signal level, the certain color signal is suppressed. An image sensing operation with a comparatively large exposure quantity and an image sensing operation with a comparatively small exposure quantity are performed alternately. It is detected that suppression of a certain color signal is performed in the first signal suppressing process when the image sensing operation with a comparatively large exposure quantity is performed. A calculation is made to find composition ratios of the color signals, which are obtained from the image sensing operation with a comparatively small exposure quantity. A second signal suppressing process is performed for suppressing at least one color signal other than the certain color signal such that the composition ratios become identical with the calculated composition ratios.Type: GrantFiled: September 30, 1999Date of Patent: September 9, 2003Assignee: Fuji Photo Optical Co., Ltd.Inventors: Fujio Okada, Mitsuhisa Nakagawa, Keiichi Negishi
-
Patent number: 6614929Abstract: An apparatus for detecting a character writing area inputs a plurality of images of written documents respectively having different characters recorded thereon to an existing document. The apparatus produces a common image and a differential image, based on the input images. By using of the common image and the differential image, a character-writing-areas are detected and an attribute is set for each of the areas. A format used for the written document is produced by using of the character-writing-areas and set attributes.Type: GrantFiled: March 23, 2000Date of Patent: September 2, 2003Assignee: Kabushiki Kaisha ToshibaInventor: Kazuaki Yokota
-
Patent number: 6614917Abstract: A method for identifying a detected object in multi-dimensional imagery data is disclosed. The method includes, (a) providing (1) a set of comparative feature values associated with one or more known objects in one or -more specified observation conditions and (2) a set of observation-related values including (i) a set of feature values for one or more features of an object as observed in an environment, (ii) a set of condition values for one or more conditions of the observation, including one or more of an orientation value, a depression value, a resolution value, and an obscuration value; and (b) generating one or more identification values for the object by comparing the set of feature values to the set of comparative feature values, including compensating for the set of condition values.Type: GrantFiled: October 22, 1999Date of Patent: September 2, 2003Assignee: Lockheed Martin CorporationInventor: Ronald William Phillips
-
Patent number: 6608928Abstract: A mixed raster content system and method improves the performance of the compression process by reducing the amount of data. The system and method uses a selector plane as a reference to aid in reducing the amount of data necessary to encode each of associated planes. A smoothing technique is used to pre-process the associated planes using the information contained in the selector plane, thereby reducing the amount of data that will be subjected to further processing. The system and method determines the useless data, smooths the boundary of the useless data, and replaces the useless data by values that improve compression.Type: GrantFiled: November 3, 1999Date of Patent: August 19, 2003Assignee: Xerox CorporationInventor: Ricardo de Queiroz
-
Patent number: 6603877Abstract: A novel method all of and apparatus for categorizing different material regions of an object-to-be inspected, by optical scanning of the object to produce a pixel image thereof, discriminating different pixel regions of the image corresponding to possibly different materials on the basis of color, and texture brightness measurements of the pixel regions and assigning preliminary likelihoods to such discrimination through with ambiguities; and comparing the measurements of the pixel regions with their local neighborhood surroundings in the image to assist in resolving said ambiguities and determining the material categorizations of the pixel regions with a high likelihood.Type: GrantFiled: June 1, 1999Date of Patent: August 5, 2003Assignee: Beltronics, Inc.Inventor: Robert Bishop
-
Patent number: 6600833Abstract: A method comprising determining an optimal color correction matrix accounting for both total noise variance and color reproduction error for a captured image; and correcting the colors of said captured image using said optimal color correction matrix.Type: GrantFiled: July 23, 1999Date of Patent: July 29, 2003Assignee: Intel CorporationInventors: Yap-Peng Tan, Tinku Acharya
-
Patent number: 6600828Abstract: When additional information is embedded into image data, both image quality and tolerance are improved. The image processing method includes the steps of: providing a plurality of pixels or a plurality of spatial-frequency components into which additional information is to be embedded; and changing the data value of the plurality of embedding pixels or spatial-frequency components in accordance with a value corresponding to the data value of the spatial-frequency components in order to embed the additional information.Type: GrantFiled: May 26, 1999Date of Patent: July 29, 2003Assignee: Canon Kabushiki KaishaInventor: Naoto Kawamura
-
Patent number: 6597806Abstract: A method of processing an image of an object to obtain a dimension-difference relating amount which relates to a difference of an actual dimension of the object from a reference dimension thereof, the method including the steps of producing a plurality of search lines each of which perpendicularly intersects a corresponding one of a plurality of substantially straight portions of an edge of the image of the object, and obtaining the dimension-difference relating amount based on a sum of a plurality of products each of which is obtained by multiplying a corresponding one of respective edge-point deviations of respective actual edge points where the search lines intersect the straight portions of the edge, respectively, from respective reference edge points on the search lines, in respective directions parallel to the search lines, by a corresponding one of respective parallel-direction distances of the reference edge points from a dimension center of the image of the object in the respective directions paralleType: GrantFiled: December 3, 1999Date of Patent: July 22, 2003Assignee: Fuji Machine Mfg. Co., Ltd.Inventor: Tousuke Kawada
-
Patent number: 6597807Abstract: Red-Green-Blue color-coding of overlaid registered stereo pair imagery from different spectral regions (for example, near-, mid-, and far-infrared) can be used to derive depth perception information. The human preattentive vision process uses coarse spatial structure in the scene to fuse the images for the detection of depth and motion cues. Optimization is accomplished by assigning green to the lowest spatial frequency content image, then red to the next lowest, and finally blue. If the fusion of one of the colored imagery layers produces depth perception information in one portion of the scene whereas the other two colored layers do not, the human mind can retain the information from this color and discard the inputs from the other two colors as noise. The same is true for the other two colors. Human color discrimination and depth perception are combined to greatly enhance preattentive object recognition in the fused stereo pair imagery.Type: GrantFiled: September 27, 1999Date of Patent: July 22, 2003Assignee: The United States of America as represented by the Secretary of the ArmyInventors: Wendell R. Watkins, Jay B. Jordan
-
Patent number: 6584221Abstract: A method for representing an image in an image retrieval database first separates and filters images to extract color and texture features. The color and texture features of each image are partitioned into a plurality of blocks. A joint distribution of the color features and a joint distribution of the texture features are estimated for each block. The estimated joint distributions are stored in the database with each image to enable retrieval of the images by comparing the estimated joint distributions.Type: GrantFiled: August 30, 1999Date of Patent: June 24, 2003Assignee: Mitsubishi Electric Research Laboratories, Inc.Inventors: Baback Moghaddam, Henning Biermann, Dimitris Margaritis
-
Patent number: 6580837Abstract: A method for determining a value for an unknown picture element (pixel) T based on neighboring pixel values of a checkerboard decimated color plane. Immediate and extended neighborhood pixel values are selected. In one configuration, immediate neighborhood pixel values are averaged. In another configuration, all neighborhood pixels are averaged. A binary pattern is determined by comparing the average with each immediate and extended neighborhood pixel values. The binary pattern is reduced to identify a set of coefficients for the binary pattern. A summed cross-product is computed for the set of coefficients and each pixel value of the immediate and extended neighborhoods. In one configuration, coefficients are stored in look up tables, where different tables correspond to different input image types. In another configuration, multiple lookup tables are stored within input images, allowing different image reconstruction options based on the embedded tables.Type: GrantFiled: December 7, 1999Date of Patent: June 17, 2003Assignee: Intel CorporationInventor: Louis Johnson
-
Patent number: 6580810Abstract: A method of image processing in three-dimensional (3-D) head motion tracking is disclosed.Type: GrantFiled: June 10, 1999Date of Patent: June 17, 2003Assignee: Cyberlink Corp.Inventors: Tzong-Jer Yang, Fu-Che Wu, Ming Ouhyoung
-
Patent number: 6580820Abstract: A method and apparatus for preventing or inhibiting effective reproduction of documents such as currency, checks, stock certificates, and any other printed document including a pre-defined security mark printed therein. The subject method and apparatus operate to effect a multi-step review of all digital image data acquired from a printed document to be reproduced for purposes of locating any potential security marks and further examining same for purposes of positively identifying a potential security mark as an actual security mark. If a mark is located and verified to be an authentic security mark, effective reproduction of the printed document will not be permitted and/or other security measures will be taken.Type: GrantFiled: June 9, 1999Date of Patent: June 17, 2003Assignee: Xerox CorporationInventor: Zhigang Fan
-
Patent number: 6577745Abstract: An input image is distorted so that it has less correlation to a watermark and the distorted image is subtracted from the input image to provide a preprocessed image. If the correlation between the preprocessed image and a watermark is sufficient then the watermark is detected in the input image. The distortion may be a spatially-variant distortion such as stretching, shrinking, shearing or rotation or the distortion may be a non-linear transforming or filtering such as median, local minimum or local maximum filtering.Type: GrantFiled: October 26, 1999Date of Patent: June 10, 2003Assignee: Koninklijke Philips Electronics N.V.Inventors: Marc J. R. Op De Beeck, Jaap A. Haitsma, Geert F. G. Depovere, Antonius A. C. M. Kalker
-
Patent number: 6577758Abstract: A position detection tool in a machine vision system finds the position of target objects in a digital image using the length and width of the target object as parameters. The input length and width dimensions are measured by the developer as the length and width of a simple hypothetical rectangle that surrounds the object. For most shapes, the developer can easily obtain these two measurements. The position detection tool can easily be adapted to discern particular image patterns from multiple component images.Type: GrantFiled: September 24, 1999Date of Patent: June 10, 2003Assignee: Cognex Technology and Investment CorporationInventors: Masayuki Kawata, Kenji Okuma, Hiroyuki Hasagawa
-
Patent number: 6574361Abstract: There is disclosed a technology of measuring three-dimensional geometric information on a plane and position information on a point from an image such as the optical flow pattern and a stereo image.Type: GrantFiled: April 4, 2000Date of Patent: June 3, 2003Assignee: Fujitsu LimitedInventors: Susumu Kawakami, Masahiro Matsuoka, Hiroaki Okamoto, Shinya Hosogi