Counting Individual Pixels Or Pixel Patterns Patents (Class 382/194)
-
Patent number: 6782124Abstract: An apparatus and method of analysis for three-dimensional (3D) physical phenomena. The physical phenomena may include any varying 3D phenomena such as time varying polar ice flows. A repesentation of the 3D phenomena is passed through a Hilbert transform to convert the data into complex form. A spatial variable is separated from the complex representation by producing a time based covariance matrix. The temporal parts of the principal components are produced by applying Singular Value Decomposition (SVD). Based on the rapidity with which the eigenvalues decay, the first 3-10 complex principal components (CPC) are selected for Empirical Mode Decomposition into intrinsic modes. The intrinsic modes produced are filtered in order to reconstruct the spatial part of the CPC. Finally, a filtered time series may be reconstructed from the first 3-10 filtered complex principal components.Type: GrantFiled: November 29, 2000Date of Patent: August 24, 2004Assignee: The United States of America as represented by the Administrator of the National Aeronautics and Space AdministrationInventor: Per Gloersen
-
Patent number: 6771813Abstract: A control unit selects a first labeling for a color image in a small number of colors so that the labeling is performed by clustering a color palette, and selects a second labeling for a color image in a large number of colors so that the labeling is performed by an adjacency expanding method.Type: GrantFiled: July 21, 1999Date of Patent: August 3, 2004Assignee: Fujitsu LimitedInventor: Yutaka Katsuyama
-
Patent number: 6771842Abstract: A method for detecting a skew of a document image corrects the skew of a document image input from an image scanner, and achieves increased accuracy compared with prior art document image skew detection methods. After segmenting the input document image into regions each having a predetermined width, lines containing black pixels are detected from each of these regions. Then, from a region where the detected lines containing black pixels follow one another in a consecutive manner, a partial image is extracted, the skew angle of the partial image is detected, and the skew angle of the document image is determined based on the thus detected skew angle of the partial image.Type: GrantFiled: September 19, 2000Date of Patent: August 3, 2004Assignee: Fujitsu LimitedInventors: Kenichiro Sakai, Hirotaka Chiba, Tsugio Noda
-
Publication number: 20040141208Abstract: A method and an apparatus to correct the length of an image in a flatten scanner. The method includes moving an image sensor by driving a motor; calculating a first number of pixels; calculating a difference between the first number of pixels and a second number of pixels; and correcting the length of the image scanned in the flatten scanner by using the calculated difference. Therefore, the method makes it possible that a scanned image can have the same length as that of an original image by using the difference between the first and second numbers of pixels. In addition, when a flatten scanner is developed, necessity for fine adjustment to correct the length of a scanned image is eliminated, and, therefore, time required to develop a scanner is shortened.Type: ApplicationFiled: December 29, 2003Publication date: July 22, 2004Inventor: Seong-Kyoo Park
-
Publication number: 20040125409Abstract: In the image processing apparatus, image data is divided into large blocks of a prescribed size and the large blocks are subdivided into small blocks by the dividing unit. The number of isolated points in each large block is then calculated by the large block isolated point calculation unit, and the number of isolated points in each small block is then calculated by the small block isolated point calculation units. It is then determined by the halftone-dot region determination unit whether or not the large block is a halftone-dot region. This determination considers both the number of isolated points in the large block and the number of isolated points in each small block.Type: ApplicationFiled: September 16, 2003Publication date: July 1, 2004Applicant: MINOLTA CO., LTD.Inventors: Tomohiro Yamaguchi, Yoshihiko Hirota
-
Patent number: 6748102Abstract: A system and method for detecting alteration of a document. The invention evaluates markings in half-tone fields by ascertaining a first dot count of dots isolated from the marking in the half-tone field of the document; forming an image of the marking; superimposing the image on a blank half-tone field having the same predetermined pattern as the half-tone field of the document; ascertaining a second dot count of dots isolated from the image superimposed on the blank half-tone field; and determining whether the marking has been altered by comparing the first dot count to the second dot count. An alteration is indicated where the first dot count and second clot count are different.Type: GrantFiled: January 24, 2001Date of Patent: June 8, 2004Assignee: International Business Machines CorporationInventor: Ravi Prakash
-
Patent number: 6744919Abstract: An image of a compound document is processed by accessing a plurality of blocks of the image; and classifying the blocks for compression. At least some of the blocks are classified according to their numbers of distinct colors.Type: GrantFiled: July 24, 2001Date of Patent: June 1, 2004Assignee: Hewlett Packard Development Company, L.P.Inventor: Amir Said
-
Patent number: 6738519Abstract: There are provided: an n-fold-character recognizing part for collectively recognizing an unmatched portion without segmenting character candidate patterns character by character for an image of a read-wise skipped portion, i.e., the unmatched portion upon word verification; and an n-fold-character recognizing dictionary referred to by the n-fold-character recognizing part upon recognition; to thereby conduct re-recognition independent of instability of character segmentation even when the portion read-wise skipped by the word verification includes two or more characters.Type: GrantFiled: June 9, 2000Date of Patent: May 18, 2004Assignee: NEC CorporationInventor: Daisuke Nishiwaki
-
Patent number: 6738518Abstract: In a text recognition system that uses a stochastic finite state network to model a document image layout, the computational efficiency of text line decoding is improved. In a typical implementation, the dynamic programming operation that accomplishes decoding uses actual scores computed between two-dimensional (2D) bitmapped character template images and the (2D) bitmapped observed image. Scoring measures the degree of a match between a character template and the observed image. Computation of these actual scores is replaced with the simpler computation of column-based (i.e., one-dimensional) heuristic scores. Because the column-based heuristic scores can be shown to be a true upper bound on actual template-image scores, the heuristic scores are accurate enough to use in place of actual scoring during text line decoding.Type: GrantFiled: May 12, 2000Date of Patent: May 18, 2004Assignee: Xerox CorporationInventors: Thomas P. Minka, Dan S. Bloomberg, Ashok C. Popat
-
Publication number: 20040086183Abstract: A method is provided of processing data representing pixel colour having a luminance component and colour difference components. The data is divided into first and second data portions, the first data portion comprising the luminance components and the second data portion comprising the colour difference components. First and second instructions from a combined instruction word, and the first and second date portions are processed in parallel using first and second parallel processors within a processor architecture, the first and second parallel processors operating according to the first and second instructions, respectively. The processed first and second data portions are combined to provide processed pixel colour data. This method uses parallel processor sections to process the luminance and colour difference components. The parallel processor sections can then use instructions suited to the type of data being processed, providing an efficient method of processing the graphics data.Type: ApplicationFiled: October 4, 2002Publication date: May 6, 2004Applicant: Broadcom CorporationInventor: Sophie Wilson
-
Patent number: 6721070Abstract: An independent hardware pixel counter counts bits of print data in regions of interest. The independent pixel counter can be an application specific integrated circuit (ASIC), and is separate from a control processor. The independent hardware pixel counter selectively monitors a data bus carrying image data to or from a memory. Once the pixels of the image data have been counted, the count data can be sent to the control processor in order to implement a print strategy. The pixel counter counts the print data at a point when image data is being sent to the memory, since at that point the image data is both uncompressed and in a raster format, and thus can be easily analyzed. Additionally, because the image data is stored in the memory until enough print data has accumulated for printing, the processor is provided with sufficient time to gather and use print information before the counted image data is printed.Type: GrantFiled: November 4, 1999Date of Patent: April 13, 2004Assignees: Xerox Corporation, In-System Design, Inc.Inventors: R. Samuel Lee, Roger G. Markham
-
Patent number: 6717695Abstract: A method for producing compressed or expanded images is provided. For compression or expansion in a direction of the lines of the image, a line factor is determined as a starting value for a line variable. After this, the following steps are carried out cyclically: if a momentary value of the line variable is greater than zero, the source image data being processed is copied and used as a target image data Next, the momentary value of the line variable is reduced by a numerical value. If the momentary value of the line variable is not greater than zero, the next source image data is used in the place of the source image data being treated. Then the value of the line factor is added to the momentary value of the line variable. A column based expansion or compression is also provided for expanding or compressing an image in the direction of the columns. A circuit is provided for performing the expansion or compression, and a printer having the circuit is also provided.Type: GrantFiled: January 19, 2000Date of Patent: April 6, 2004Assignee: Océ Printing Systems GmbHInventor: Alexander Murmurachi
-
Patent number: 6711284Abstract: An image processor for a digital image of an object having a crack is disclosed, the digital image being made of a plurality of pixels. The image processor comprises a counter for counting a number of the pixels relating to the crack within a selected portion of the image, the selected portion being of a known area, an investigator for investigating the relationship among the pixels relating to the crack within the selected portion of the image, and a width evaluator for evaluating the width of the crack corresponding to the selected portion of the image on the basis of the number of the pixels and the relationship among the pixels.Type: GrantFiled: August 4, 2000Date of Patent: March 23, 2004Assignees: Nikon Corporation, Nikon Technologies, Inc.Inventor: Hiroshi Koide
-
Patent number: 6711280Abstract: A method and system for ranging an object are disclosed. The method includes illuminating a field of view potentially including the object, synchronously receiving reflected signals from the field of view with and without illumination, capturing first and second images within an array, and generating a subtraction image using the images. One image is captured in the array while the other image is in the array. The first and second images include reflected signals from the field of view with and without illumination, respectively. The array includes first and second groups of lines that are unmasked and masked, respectively. In one exposure, the first group of lines is loaded with the first or second image. The image in the first group of lines is shifted into the second group. In another exposure, the first group of lines is loaded with the other image, which is shifted into the second group.Type: GrantFiled: May 25, 2001Date of Patent: March 23, 2004Inventors: Oscar M. Stafsudd, Ioannis Kanellakopoulos, Phyllis R. Nelson, Nicholas Bambos
-
Patent number: 6704439Abstract: A method of identifying an alveolar nerve region in a mandible image for dental implantation. The method includes: (a) slicing the 3-dimensional mandible image into a number of 2-dimensional slice images; (b) detecting a binary image object corresponding to a mandible region from one of the slice images; (c) grouping pixels of the binary image object of the mandible region into clusters each containing pixels having a similar intensity; (d) determining clusters that have pixels more than a predetermined minimum number of pixels, and determining the minimum labeled cluster having the lowest pixel intensity distribution among the clusters; (e) composing a new binary image containing pixels which belong to both the mandible region and the clusters having intensity distribution lower than that of the minimum labeled cluster, to extract a candidate nerve object; and (f) determining whether the candidate nerve object corresponds to the real alveolar nerve region.Type: GrantFiled: September 14, 2000Date of Patent: March 9, 2004Assignee: 10DR Co. Ltd.Inventors: Heu-yeon Lee, Chan-kyung Lee, Chang-hwan Kong
-
Publication number: 20040042662Abstract: A digital image that includes first and second regions is processed. An intrinsic color of a given pixel located in an area of interest that is adjacent to at least one of the first and second regions is estimated by extrapolating from colors of multiple pixels in one of the first and second regions and multiple pixels in the other of the two regions.Type: ApplicationFiled: September 5, 2003Publication date: March 4, 2004Inventors: Gregg D. Wilensky, Martin E. Newell
-
Patent number: 6701025Abstract: A digital image processor for a medical imaging system enhances acquired images and corrects the images for non-uniformities in the data acquisition process. The non-uniformity correction includes calculating a non-uniformity correction function h in an iterative process in which two input parameters V and S are adjusted until an optimal correction function h is produced. The acquired image is corrected using the optimal correction function h.Type: GrantFiled: November 22, 1999Date of Patent: March 2, 2004Assignee: GE Medical Systems Global Technology Company LLCInventor: Gopal B. Avinash
-
Patent number: 6688449Abstract: A pattern identification apparatus is used to speedily identify tokens at a game arcade. The apparatus is inexpensive and has an image pickup device (15). The image pickup device has an area sensor (17) consisting of a two-dimensional matrix of photoelectric pixels. Each of the photoelectric pixels has a photodiode (19), a signal comparator (21), and a signal holder (23). The photoelectric pixels are connected to address lines (5), respectively. Required ones of the address lines are specified. Signals are read, to a data line, out of the signal holders of the photoelectric pixels that are connected to the specified address lines in response to addressing signals passed through the specified address lines. The specified address lines correspond to concentric circles (45, 47, 49) defined on a target (39) of disk shape. The target is identified according to the read signals that represent the concentric circles defined on the target.Type: GrantFiled: August 31, 2000Date of Patent: February 10, 2004Assignee: Unirec Co., Ltd.Inventor: Junichi Yamagishi
-
Patent number: 6650776Abstract: A two-dimensional code recognition processing method for recognizing a two-dimensional code made of a plurality of square cells arranged in accordance with predetermined layout rules. The method comprises the steps of: generating binary data from image information acquired externally in accordance with a predetermined threshold value; detecting a reference cell serving as a reference in recognizing the two-dimensional code based on the binary data generated in the binary data generating step; detecting corner cells each located in a predetermined search range with respect to the reference cell detected in the reference cell detecting step, on the basis of the binary data generated in the binary data generating step; and detecting code data assigned to the two-dimensional code existing inside an area of a code part enclosed by the reference cell and by the corner cells on the basis of the binary data generated in the binary data generating step.Type: GrantFiled: June 28, 1999Date of Patent: November 18, 2003Assignee: Sony CorporationInventors: Keigo Ihara, Junichi Rekimoto, Shinji Nakajima, Takahiko Sueyoshi
-
Publication number: 20030206651Abstract: Provided herein are a method and an apparatus for examining foreign matters in through holes, which can quickly conduct an examination of foreign matter in through holes with low costs and high accuracy. Light passing through a plurality of through holes having a uniform size is simultaneously taken as image data, the number of areas of the imaged masses corresponding to the plurality of the respective through holes is initially counted, and a process to determine presence or absence of foreign matters is conducted by mutually comparing areas of adjacent masses for only a work piece with a counted value of the masses being concurred with a specified value.Type: ApplicationFiled: March 29, 2001Publication date: November 6, 2003Inventors: Noboru Goto, Mikio Saito
-
Patent number: 6643410Abstract: A digital image processing method determines the extent of blocking artifacts in a digital image by first forming a column difference image and averaging the values in the columns in the column difference image to produce a column difference array. The average of the values in the column difference array that are separated by one block width are computed to produce a block averaged column difference array. Then, the peak value in the block averaged column difference array is located, and the mean value of the block averaged column difference array (excluding the peak value) is calculated to produce a column base value, and the ratio between the peak value and the base value are computed to produce a column ratio. The foregoing steps are repeated in the row direction to produce a row ratio. Finally, the column and row ratios are employed as a measure of the extent of blocking artifacts in the digital image.Type: GrantFiled: June 29, 2000Date of Patent: November 4, 2003Assignee: Eastman Kodak CompanyInventors: Qing Yu, Jiebo Luo, Rajan L. Joshi
-
Patent number: 6640001Abstract: A method and apparatus for the fast detection of spiculated lesions in a digital mammogram, the method for use in a computer aided diagnosis system for assisting a radiologist in identifying and recognizing the spiculations among a multiplicity of lines corresponding to standard fibrous breast tissue. A line and direction image is created from a digital mammogram, and a region of potential intersection for substantially every pixel in the digital mammogram image is determined. The region of potential intersection for each pixel is a predetermined pattern, such as a high aspect ratio rectangle or trapezoid, positioned around the pixel and rotated in a direction corresponding to direction information for that pixel. The regions of potential intersection are accumulated among the pixels to produce a cumulative array, and information in the cumulative array is processed for identifying spiculations in the digital mammogram.Type: GrantFiled: July 17, 2001Date of Patent: October 28, 2003Assignee: R2 Technology, Inc.Inventors: Jimmy R. Roehrig, Harlan M. Romsdahl, Wei Zhang
-
Patent number: 6636631Abstract: A method of recognizing characters of a document including ruled lines. After separating the characters from the ruled lines, a bounding box and a corresponding character pattern are extracted for each character (hereinafter, “the character”). Contour information and ground (white pel area) information are extracted as fundamental features from the character pattern. Various statistical features are extracted based on the fundamental features. Various structural features are extracted based on the fundamental features and the character pattern. On the basis of the extracted statistical features, some candidates for the character and corresponding degrees of similarity are found to provide at least such one of the candidates as has largest degree(s) of similarity and degree(s) of similarity associated with the provided candidate(s).Type: GrantFiled: June 4, 1999Date of Patent: October 21, 2003Assignee: Matsushita Electric Industrial Co., Ltd.Inventors: Keiichi Miyazaki, Masato Minami, Toshiyuki Kouda
-
Patent number: 6636632Abstract: An image processor wherein, with respect to pixels included in a pattern image and in a plural directions from a selected pixel among pixels, a number of same kind of pixels which consecutively continues from the selected pixel is counted. A processing recognition area effective signal that shows a range in which an area to be processed exists is produced. Whether the selected pixel is a processing candidate pixel is determined based on a determination whether the number is larger, in the plural directions, than a reference value. A processing image is made by comparing the processing candidate pixel and the processing recognition area effective signal.Type: GrantFiled: January 31, 2001Date of Patent: October 21, 2003Assignee: Ibiden Co., Ltd.Inventor: Masahiro Okada
-
Patent number: 6636630Abstract: An area-separation processing section, installed in an image-processing apparatus of the present invention, is provided with a block memory A for storing image signals, a maximum/minimum pixel detection section, a maximum/minimum pixel feature-amount calculation section and a maximum/minimum pixel classifying section that make a judgment as to what kind of maximum pixel or minimum pixel a target pixel A within the block memory A forms, a block memory B for storing classifying signals outputted from the maximum/minimum pixel classifying section, and a mesh feature-amount calculation section and a mesh judgment section that make a judgment as to whether or not a target pixel B within the block memory B belongs to a mesh areaType: GrantFiled: May 26, 2000Date of Patent: October 21, 2003Assignee: Sharp Kabushiki KaishaInventors: Yasushi Adachi, Toshihiro Kanata
-
Publication number: 20030179911Abstract: The present invention discloses the detection of faces in digital images. Rather than subjecting the entire image (1) to computationally intensive face detection analysis, the image is instead segmented into regions (2) each of which has a substantially homogeneous colour. Only those regions (2) having a predominantly skin colour are then subjected to the face detection analysis. Preferably the face detection analysis is independent of facial colour.Type: ApplicationFiled: June 7, 1999Publication date: September 25, 2003Inventors: EDWIN HO, ALISON JOAN LENNON
-
Patent number: 6591011Abstract: A method and apparatus for processing plural pictures to generate a synthesized picture, in which plural images are synthesized by application of a geometrical model. An image processing apparatus 10 extracts feature points from each of two or more images. Feature points of one of the images and those of the other image or images are compared to each other to effect matching. Based on the results of this matching, computations are conducted to change the relative position of the one and the other images to synthesize the two or more images.Type: GrantFiled: November 15, 1999Date of Patent: July 8, 2003Assignee: Sony CorporationInventor: Frank Nielsen
-
Patent number: 6583897Abstract: A method of smoothing edges of an input image is provided for use in connection with an image rendering engine that supports two opposing intensity levels and a range of intermediate intensity levels there between. The method includes sampling scan lines from the input image. Each scan line includes an array of pixels, and each pixel possesses one of the two opposing intensity levels. Simultaneously a plurality of the scan lines are buffered. Thereafter, the method includes detecting defined patterns in an unbounded region within the buffered scan lines. Finally, intensity levels of selected pixels are adjusted to intermediate intensity levels in response to the defined patterns detected.Type: GrantFiled: November 24, 1999Date of Patent: June 24, 2003Assignee: Xerox CorporationInventor: Steven J. Harrington
-
Patent number: 6580818Abstract: A method and apparatus for the automated detection of masses in a digital mammogram, the method for use in a computer aided diagnosis system for assisting a radiologist in identifying and recognizing suspicious portions of the digital mammogram. A gradient image is created from the digital mammogram, and information in the gradient image is processed for identifying masses. In a preferred embodiment, a portion of a spiculation detection algorithm is applied to the gradient image for identifying masses. The spiculation detection algorithm comprises a line detection portion and a post-line detection portion, and it is the post-line detection portion which is applied to the gradient image for identifying masses. Advantageously, computer programs which have already been written for spiculation detection may, with minor modifications, be ported into mass detection programs.Type: GrantFiled: October 9, 2001Date of Patent: June 17, 2003Assignee: Altera CorporationInventors: Nico Karssemeijer, Guido M. te Brake
-
Patent number: 6574349Abstract: Supplemental data is embedded in an information signal such as a sigma-delta modulated audio signal. The encoded signal includes two or more channels, e.g. a left channel bit stream and a right channel bit stream. The same supplemental data is accommodated at corresponding predetermined bit positions, e.g. every Mth bit position, of the bit streams. This allows detection and extraction of the supplemental data without the need for accommodating a sync pattern in the signal. At the receiving end, a sequence of Mth bits from the first channel is compared with a corresponding sequence of Mth bits from the second channel. If they are identical, the sequence is a candidate supplemental data sequence. This is done for different sequence positions until the supplemental data has been found.Type: GrantFiled: November 17, 1999Date of Patent: June 3, 2003Assignee: Koninklijke Philips Electronics N.V.Inventors: Johan P. M. G. Linnartz, Franciscus L. A. J. Kamperman, Erwin Kragt
-
Publication number: 20030031365Abstract: A multi-exposure drawing apparatus for drawing a given pattern on a workpiece is provided. The apparatus uses an exposure unit with optical modulation elements arranged in a matrix. The apparatus comprises a first, second, and third memory, a coordinate transformation processor, a calculation processor, and an exposure-data generating processor. The first, second, and third memory respectively stores raster-data of the given pattern, first-coordinate data representing a position of each optical modulation element, and second-coordinate data representing a position of the exposure unit. The coordinate transformation is performed for the first-coordinate data. Address-data is calculated in accordance with a pixel size of the raster-data, and is based on the sum of the first and second coordinate data. Exposure-data generated by outputting the raster-data of the address-data is given to each of the optical modulation elements. The given pattern is drawn on the drawing surface as to the exposure-data.Type: ApplicationFiled: August 7, 2002Publication date: February 13, 2003Applicant: ASAHI KOGAKU KOGYO KABUSHIKI KAISHAInventor: Takashi Okuyama
-
Patent number: 6519350Abstract: A method and arrangement for embedding a watermark in an image are disclosed. The watermark consists of a pseudo-random, dense subset of image pixels, e.g. a pattern of lines (20). A number of salient image pixels (21-26), for example, local extremes, corners or edges, is identified and it is determined whether they lie on (i.e. within a vicinity &dgr; of) the line pattern (21-23) or not (24-26). In an unwatermarked image (FIG. 2A), the number of most salient pixels (21) lying on the watermark is substantially the same as the number of most salient pixels (25,26) not lying on the watermark. The image is watermarked (FIG. 2B) by modifying the saliency of the salient pixels in such a way that a significant majority (21,23) of the most salient pixels (21,23,25) is eventually located within the vicinity of the line pattern.Type: GrantFiled: January 4, 2000Date of Patent: February 11, 2003Assignee: Koninklijke Philips Electronics N.V.Inventors: Cornelis W. A. M. Van Overveld, Peter M. J. Rongen, Maurice J. J. J.-B. Maes
-
Patent number: 6507417Abstract: An image pickup device for sensing a two-dimensional (2D) image while causing a projected image of an object to be sensed being projected onto a linear image sensor to relatively move with respect to the linear image sensor in a direction (V scanning) perpendicular to the internal scan (H scan) direction of the linear image sensor. This device includes a position detector circuit that detects the position of the object to be sensed, and a pixel size modifier circuit for changing or modifying the setup configuration of a pixel size in the V scan direction of the linear image sensor on the basis of a position detection signal indicative of the position of the to-be-sensed object as detected by the position detector circuit. The pixel size modifier circuit is operable based on the object position detection signal to periodically change the interval of H-scanning start pulses of the linear image sensor.Type: GrantFiled: June 26, 1998Date of Patent: January 14, 2003Assignee: Hitachi, Ltd.Inventors: Hiroshi Makihira, Shunji Maeda, Kenji Oka, Minoru Yoshida, Yasuhiko Nakayama
-
Patent number: 6501856Abstract: A scheme for detecting telop character displaying frames in video image which is capable of suppressing erroneous detection of frames without telop characters due to instability of image features is disclosed. In this scheme, each input frame constituting the video data is entered, and whether each input frame is a telop character displaying frame in which telop characters are displayed or not is judged, according to edge pairs detected from each input frame by detecting each two adjacent edge pixels for which intensity gradient directions are opposite on some scanning line used in judging an intensity gradient direction at each edge pixel and for which an intensity difference between said two adjacent edge pixels is within a prescribed range as one edge pair, edge pixels being pixels at which an intensity value locally changes by at least a prescribed amount with respect to a neighboring pixel among a plurality of pixels constituting each input frame.Type: GrantFiled: September 28, 2001Date of Patent: December 31, 2002Assignee: Nippon Telegraph and Telephone CorporationInventors: Hidetaka Kuwano, Hiroyuki Arai, Shoji Kurakake, Kenji Ogura, Toshiaki Sugimura, Minoru Mori, Minoru Takahata
-
Patent number: 6483942Abstract: A method of estimating the dot frequency of an area of a band of an image. The band is divided into small areas, and within each area, each column is processed, pixel by pixel. If a pixel is encountered that is not of the same type as a neighbor, it is assigned a new identification. If a current pixel is the same as the one above or to the left, it is given the same identification. If the pixel is the same as the one above and to the left, the two identifications are merged. At the end of each column two numbers are calculated, one is the number of separate identifications there are in the column, the other is the number of identifications that are in use since the beginning of the entire image. For each area, the dot frequency is the number of separate identifications in the first column plus the number of identifications used in the image up to the last column minus the number of identifications in use at the end of the first column of the band.Type: GrantFiled: September 27, 1999Date of Patent: November 19, 2002Assignee: Xerox CorporationInventor: Donald J. Curry
-
Patent number: 6483935Abstract: A system and method for counting objects or parts on a continuously moving conveyor, or other elongated surface, provides a camera and associated machine vision system that acquire/capture and analyze multiple, successive fields of view taken within an area of interest defined by the system. Each of the fields of view includes flanking right and left overlap zones with respect to adjacent fields of view. The overlap zones are defined to be at least as wide as the maximum width of a part being counted. The captured fields of view are stored within the system and analyzed in succession based upon a set of rules. These rules determine whether or not a particular part within the subject field of view is to be counted. More specifically, the rules are applied within the overlap zones for each field of view to determine whether or not to count the part.Type: GrantFiled: October 29, 1999Date of Patent: November 19, 2002Assignee: Cognex CorporationInventors: Fariborz Rostami, Todd O. Dampier, Edwin C. Mangalindan
-
Patent number: 6477272Abstract: This invention is directed toward an object recognition system and process that identifies the location of a modeled object in a search image. This involves first capturing model images of the object whose location is to be identified in the search image. A co-occurrence histogram (CH) is then computed for each model images. A model image CH is computed by generating counts of every pair of pixels whose pixels exhibit colors that fall within the same combination of a series of pixel color ranges and which are separated by a distance falling within the same one of a series of distance ranges. Next, a series of search windows, of a prescribed size, are generated from overlapping portions of the search image. A CH is also computed for each of these search windows using the pixel color and distance ranges established for the model image CHs. A comparison between each model image CH and each search window CH is conducted to assess their similarity.Type: GrantFiled: June 18, 1999Date of Patent: November 5, 2002Assignee: Microsoft CorporationInventors: John Krumm, Peng Chang
-
Patent number: 6470095Abstract: The spatial separations between clusters of objects on the electronic work surface are analyzed to automatically generate borders, which may be used in at least two manners. The borders may become explicit editable borders within an output image. Alternatively, the borders created may be implicit ephemeral borders. According to an aspect, a method uses the sufficient stability grouping technique to determine grouping of elements in the input image array into the text lines in the output text lines array. According to another aspect, a method uses the sufficient stability grouping technique to determine the amount of vertical expansion to apply to each text line so as to create text regions in the output array which correspond to the text lines in the input text lines array. According to yet another aspect, a method takes the text regions array as input and extracts enclosure borders from the text regions.Type: GrantFiled: October 13, 1998Date of Patent: October 22, 2002Assignee: Xerox CorporationInventors: James V. Mahoney, Patrick Chiu, Thomas P. Moran, William J. van Melle
-
Patent number: 6466923Abstract: In an analysis of a set of discrete multidimensional data which can be represented in an array with a topology, where the array that can be mapped to an image space of discrete elements, such as digitized image data, seismic data and audio data, genotype/phenotype classifications are imposed on the topology, and then molecular biological-like processes (annealing, fragmentation, chromatographic separation, fingerprinting, footprinting and filtering) are imposed upon that topology to perceive classifiable regions such as edges. More specifically, an image feature probe constructed of strings of contiguous image fragments of the class of N-grams called linear N-grams, anneals genotypes of topological features by complementary biological-like techniques in the same manner that complex biological systems are analyzed by genetic mapping, sequencing and cloning techniques. For example, molecular biological probes anneal with molecular biological genotypes and then are used to classify those genotypes.Type: GrantFiled: April 29, 1998Date of Patent: October 15, 2002Assignee: Chroma Graphics, Inc.Inventor: Fredric S. Young
-
Patent number: 6466262Abstract: A digital wide camera is capable of forming, in real time, a wide view still image from a dynamic sequence of images generated during a recording operation by panning the camera to capture a scene. The camera shoots each frame of the sequence with a certain angular field of view at 30 frames per second, for example. The wide view still image has an apparent field of angular view that is greater than that of the image of each frame. The images of the sequence are connected together by determining a shift in position between adjacent images and then overwriting each image to a wide view image buffer after shifting the image by the shift amount. Determining the shift amounts and overwriting the image buffer is accomplished in less time than the interval between shooting consecutive images so that the display of the wide view image can be updated in real time for a user's observation.Type: GrantFiled: June 9, 1998Date of Patent: October 15, 2002Assignee: Hitachi, Ltd.Inventors: Takafumi Miyatake, Akio Nagasaka, Masakazu Ejiri
-
Patent number: 6463171Abstract: A method of analyzing and classifying defects on a semiconductor wafer during a semiconductor manufacturing process using an automatic defect resizing tool to accurately measure the sizes of defects.Type: GrantFiled: June 30, 1999Date of Patent: October 8, 2002Assignee: Advanced Micro Devices, Inc.Inventors: Paul J. Steffan, Allen S. Yu
-
Patent number: 6449391Abstract: Segmentation of a character-containing image, made by placing a dark mark against a light background, is accomplished by establishing a vertical pixel projection for each pixel column in the image. For more exact segmentation, the image is horizontally scanned in each row of the image after detecting edges of characters. The scanned results and thresholds are compared to verify whether edges and spaces of the scanned row are noise or discontinuous edges. The thresholds correlate with neighboring row data of the image. According to the results of the comparison, the discontinuous edges are connected and the noise is eliminated. Thereby, the character-containing image can be segmented into each character without segmentation errors.Type: GrantFiled: September 9, 1999Date of Patent: September 10, 2002Assignee: Samsung Electronics Co., Ltd.Inventor: Jeong-Hoe Ku
-
Patent number: 6445817Abstract: A color transition and area counting device for use in a machine vision system may include an input port for inputting a stream of pixels in a frame. The pixels in the frame with particular colors may be counted and stored by associated counters. The frame may be loaded simultaneously into four frame memories. Each frame memory may be read out in a different pattern, for example, horizontally, vertically, diagonally, and cross-diagonally. The number of valid color transitions detected in each of the four read out operations may be added to determine a transition count for the frame. The area count and transition count may be used to flag potentially defective objects examined by the system.Type: GrantFiled: July 13, 2000Date of Patent: September 3, 2002Assignee: ChromaVision Medical Systems, Inc.Inventor: Jose de la Torre-Bueno
-
Patent number: 6438265Abstract: A method of binarization used in an OCR system involves in determining text pixels by checking, for each pixel, that the difference between its value and the values of a plurality of pixels located at a predetermined distance therefrom is greater than a relative threshold corresponding to the difference in intensities between the text and the background of the image, subsampling the image at a rate corresponding to at least two pixels in order to detect kernels of text, and then binarizing the image pixels only in tiles of several stroke width sides containing text kernels by using in each tile, an absolute threshold estimated in that tile.Type: GrantFiled: May 12, 1999Date of Patent: August 20, 2002Assignee: International Business Machines Corp.Inventors: Andrei Heilper, Yaakov Navon, Eugene Walach
-
Patent number: 6434271Abstract: A technique for locating objects within an image is disclosed. In one embodiment, the technique is realized by obtaining an image and then identifying an object within the image based upon an orientation of the object within the image. The image can be a representation of a plurality of pixels, wherein the plurality of pixels are arranged in a plurality of columns and rows, and wherein at least some of the plurality of pixels are enabled to represent the object.Type: GrantFiled: February 6, 1998Date of Patent: August 13, 2002Assignee: Compaq Computer CorporationInventors: Andrew Dean Christian, Brian Lyndall Avery
-
Patent number: 6434270Abstract: A pattern extraction apparatus computes the convexity/concavity of an input pattern, regards a pattern having large convexity/concavity as a character, and regards a pattern having small convexity/concavity as a ruled line.Type: GrantFiled: February 10, 1998Date of Patent: August 13, 2002Assignee: Fujitsu LimitedInventors: Atsuko Ohara, Satoshi Naoi
-
Patent number: 6434701Abstract: A system enables encoding of a removable mark into digital data, and decoding of the mark from the digital data. The system comprises an encoder and a decoder. The encoder includes a target area locator for locating in the digital data a flat area having a flatness value n, and includes a marker for using the flatness value n to encode a mark into the flat area. The decoder attempts to extract a mark that includes a plateau and a core from digital data. The decoder includes a mark area locator for using a flatness value n to search digital data for a possible plateau, an unmarker coupled to the flat area locator for decoding a possible core upon locating a possible plateau and for using the flatness value n to replace the possible core with possible original data, and an authenticator coupled to the unmarker for examining the possible core for accuracy.Type: GrantFiled: April 6, 1999Date of Patent: August 13, 2002Assignee: Kwan Software Engineering, Inc.Inventor: John Man Kwong Kwan
-
Publication number: 20020106126Abstract: Embodiments of the invention provide methods, computer software products and systems for detecting pixel stutter of a scanner. In one embodiment, a numeric count of stuttered pixels in both the x (row) and y (column) directions and a graphic display of the stuttered pixels overlaid on the image data are provided by the invention. The y-direction stutter count provides the estimate of pixel stutter from pure statistical data variations.Type: ApplicationFiled: December 11, 2000Publication date: August 8, 2002Inventors: Daniel M. Bartell, Richard Watts
-
Publication number: 20020081031Abstract: An isolation point counting section, an internal edge counting section, and a continuity detecting section are provided at a halftone dot internal character region signal generating section. The halftone dot internal character region signal generating section discriminates a character region in a halftone dot image based on the detection results of the isolation point counting value caused by the isolation point counting section, the internal edge count value caused by the internal edge counting section, and the presence or absence of continuity of the internal edges caused by the continuity detecting section by making best use of the fact that the halftone dot region and character region in the halftone dot image are completely reversed in their characteristics.Type: ApplicationFiled: December 21, 2001Publication date: June 27, 2002Inventor: Hiroyuki Suzuki
-
Publication number: 20020076106Abstract: An image processing apparatus includes an object extracting unit, a selecting unit, and an object storing unit. The object extracting unit extracts an object from a target image through a plurality of processing, and outputs the result of extracting the object. The selecting unit selects at least a part of the result of extracting the object which is obtained through the plurality of processing, in accordance with a user's operation. The object storing means stores the result of extracting the object which is selected by the selecting unit.Type: ApplicationFiled: September 10, 2001Publication date: June 20, 2002Inventors: Tetsujiro Kondo, Hisakazu Shiraki, Hideo Nakaya, Yuji Okumura