Dilation Or Erosion (e.g., Opening Or Closing) Patents (Class 382/257)
-
Patent number: 6901168Abstract: The object of the invention is a method of processing information contained in an image, including: a first processing (1-4), for defining an area of interest of the image (8), effecting an adaptive thresholding (1-8) of this area of interest in order to obtain a threshold image (10) of this area of interest, referred to as the first thresholded image, the segmentation (1-12) of the thresholded image, in order to obtain a first set of morphological layers (14-1, 14-2, 14-3, . . . ) of the thresholded image.Type: GrantFiled: May 6, 1999Date of Patent: May 31, 2005Assignee: France TelecomInventors: Joël Gardes, Rémy Mullot, Yves Lecourtier, Jean-Marc Ogier, Alain Lassaulzais
-
Patent number: 6891961Abstract: The invention is an image analysis system and method for grading of meat, predicting quality of meat and/or predicting meat yield of an animal. One embodiment of the invention is particularly designed to capture an image of the 12th rib cross section of the ribeye and perform an image analysis of the ribeye for grading purposes. The image capturing camera portion of the system has a wedged shaped camera housing for ease of insertion into the ribbed incision. The image capturing portion of the system further comprises a camera with a flash for consistent lighting. The camera is positioned such that it views the ribeye cross section at an angle to accommodate the wedge shape of the camera housing for ease of insertion in the incision. The camera housing also has various alignment means to facilitate the user's ability to capture images in a consistent manner.Type: GrantFiled: January 28, 2004Date of Patent: May 10, 2005Assignee: Tyson Fresh Meats, Inc.Inventors: Horst Eger, Annett Haagensen, Mohammed Koohmaraie, Steven D. Shackelford, Tommy L. Wheeler, Peter Haagensen
-
Patent number: 6882740Abstract: A system and method for automatically determining a seed vigor index for a lot of seeds by analysis of a scanned image of a plurality of seedlings grown from lot of seeds, including automatically separating and analyzing overlapped seedlings. According to one aspect of the current invention, seedling analysis software is used to analyze an image of seedlings. The seedling analysis software preferably analyzes both hypocotyl and radicle lengths and thus determines the separation point between the two for each seedling. The seedling analysis software also preferably separates overlapped seedlings, preferably using a simulated annealing technique. According to another aspect of the present invention, a low-cost scanner placed in an inverted configuration in a scanner enclosure is used to generate high-quality, reproducible images of seedlings. According to yet another aspect of the present invention, a method of using ordinary germination boxes, i.e.Type: GrantFiled: June 9, 2000Date of Patent: April 19, 2005Assignee: The Ohio State University Research FoundationInventors: Miller Baird McDonald, Jr., Kikuo Fujimura, Mark Alan Bennett, Yusaku Sako, Andrew Frederick Evans
-
Publication number: 20040263909Abstract: A method of improving edge rendering of objects includes dilation (or contraction) of an object's tag plane by one or more pixels into the surrounding region, with the adjacent tag region having a corresponding contraction (or dilation). The objects of interest (e.g., white text) are first identified; the corresponding object tag plane is then spread or choked, in a fashion analogous to trapping. In the case of negative text on a tint background, by expanding the tag plane for the negative text object, the text hint would be forced one pixel into the tint object plane everywhere along the perimeter of the negative text. This could then enable greatly improved negative text rendering.Type: ApplicationFiled: June 27, 2003Publication date: December 30, 2004Applicant: Xerox CorporationInventor: Jon S. McElvain
-
Patent number: 6832007Abstract: An image processing method and system compensates for artifacts in scaling operations of mixed raster content data representations. In such data representations, a document is segmented into data portions generally segregated by data types. At least one of the segments is dilated so that upon scaling reconstruction, there are additional pixels available for interpolation operations, thereby avoiding artifacts caused by discontinuity.Type: GrantFiled: November 21, 2000Date of Patent: December 14, 2004Assignee: Xerox CorporationInventors: Yeqing Zhang, Martin E. Banton, James R. Low, Steven J. Harrington, William A. Fuss
-
Patent number: 6816627Abstract: A system capable of efficiently fusing image information from multiple sensors operating in different formats into a single composite image and simultaneously display all of the pertinent information of the original images as a single image.Type: GrantFiled: April 12, 2001Date of Patent: November 9, 2004Assignee: Lockheed Martin CorporationInventor: Norman Ockman
-
Patent number: 6816614Abstract: The invention concerns a method for comparing two recorded pixelated source images (2a, 2b) of the same rectangular format representing in contrasted form the equipotential lines on an integrated circuit chip. The method consists in subjecting each source image (2a, 2b) to an adaptive thresholding processing with three contrast levels, then forming a result image (14) from the processed source images (3a, 3b) by assigning to each pixel a contrast level defined according to a logical rule of comparison.Type: GrantFiled: May 10, 2001Date of Patent: November 9, 2004Assignee: Centre National D'Etudes SpatialesInventors: Romain Desplats, Philippe Perdu
-
Publication number: 20040161161Abstract: A method for segmenting an image is disclosed wherein a fractal map of the image is generated by estimating the fractal dimension of each pixel in the image. The image is segmented by thresholding the fractal map of the image.Type: ApplicationFiled: February 14, 2003Publication date: August 19, 2004Inventor: Joel M. Recht
-
Patent number: 6771834Abstract: Briefly, in accordance with one embodiment of the invention, a method of segmenting an initial digital image includes the following. The initial digital image is processed to produce a first digital image with defined edges corresponding to the initial digital image and to produce a second digital image with at least two dominant contiguous regions corresponding to the initial digital image. Distinct non-overlapping regions of the first digital image formed by the defined edges are identified. The distinct non-overlapping regions of the first digital are combined based, at least in part, on a correspondence with the at least two dominant contiguous regions in the second digital image. Based, at least in part, on the remaining regions after combining the distinct non-overlapping regions of the first digital image, the initial digital image is segmented.Type: GrantFiled: July 2, 1999Date of Patent: August 3, 2004Assignee: Intel CorporationInventors: Fernando C. M. Martins, Rajeeb Hazra
-
Patent number: 6766043Abstract: An algorithm is disclosed that recovers regions of possible pleural nodules left out of an organ field or otherwise undetected due to the nature of low level image processing in the organ field. A morphological closing with an elliptical structuring element is performed on a region to detect nodules within the size of the ellipsoid. A deformable surface-based analysis is performed in distinctive regions for the identification of larger nodules. The integrated use of a deformable surface model and chamfer distance potential enables explicit representation of regularized, or smoothed, surfaces within which nodule candidates may be detected.Type: GrantFiled: November 23, 2001Date of Patent: July 20, 2004Assignee: R2 Technology, Inc.Inventors: Xiaolan Zeng, Wei Zhang
-
Patent number: 6763127Abstract: A fingerprint recognition method includes iterative gamma correction that compensates moisture effect, feature extraction operations, directional morphological filtering that effectively links broken ridges and breaks smeared ridges, adaptive image alignment by local minutia matching, global matching by relaxed rigid transform, and statistical matching with Gaussian weighting functions.Type: GrantFiled: October 6, 2000Date of Patent: July 13, 2004Assignee: IC Media CorporationInventors: Shang-Hung Lin, Hung-Min Jen
-
Patent number: 6756992Abstract: In a display device, three light-emitting elements, which respectively emit light of the three primary colors of R, G, and B, are aligned in a fixed order in a first direction to form one pixel. A plurality of such pixels are aligned in a the direction to form one line. A plurality of such lines are aligned in a second direction, which is orthogonal to the first direction, to form a display screen. With this display device, a three-times magnified pattern, with which a target pixel in a raster image to be displayed currently is magnified by three in the first direction, is determined dynamically in accordance with a rectangular reference pattern of 3×3 pixels consisting of the target pixel and pixels surrounding the target pixel. Display is performed upon allocating this three-times magnified pattern to the three light-emitting elements that comprise one pixel. Character interval adjustment and color display of sub-pixel precision precision are enabled.Type: GrantFiled: July 17, 2001Date of Patent: June 29, 2004Assignee: Matsushita Electric Industrial Co., Ltd.Inventors: Bunpei Toji, Tadanori Tezuka, Hiroyuki Yoshida
-
Patent number: 6754374Abstract: An apparatus and method for processing images with regions representing target objects involves registering a first and a second image, where the second image contains a target object. The method comprises the steps of identifying a region in the second image containing one or more image data elements representing the target object, transforming the second image to reduce the size of the region containing the target object, and registering the first image and the second image. Another embodiment comprises the steps of identifying a region in the second image containing one or more image data elements representing a target object. After identifying this region, the first and second images are registered using a first transform component that filters one or more data elements in the second image that are contained in the identified region, and a second transform component that includes one or more data elements in the second image that are contained in the identified region.Type: GrantFiled: December 16, 1999Date of Patent: June 22, 2004Assignee: Surgical Navigation Technologies, Inc.Inventors: Michael I. Miller, Ulf Grenander, Sarang C. Joshi
-
Publication number: 20040114787Abstract: An image processing system is described in which sets of image elements having display values outside of a target range B of display values are each respectively morphologically dilated. The intersection between the morphologically dilated sets of image elements is then identified and those image elements within the intersecting region are removed from the set of image elements having the target range B of display values. This removes image elements incorrectly appearing to have display values corresponding to the target range B of display values due to aliasing effect between regions of image elements having display values either side of the target range B of imaging may be two-dimensional or three-dimensional imaging. The morphologically dilatation is preferably performed with a quasi-circular or a quasi-spherical structuring element having a radius of between two and three voxels.Type: ApplicationFiled: October 13, 2003Publication date: June 17, 2004Inventors: Pavlos Papgeorgiou, Ian Poole
-
Patent number: 6741755Abstract: A system is provided for selecting a foreground region of an image, given a set of pixels defining the boundary of the foreground region of the image. The system includes a component to dilate the pixel set and a component to determine a foreground value (F) and to determine an opacity value (a) based on estimated foreground and background values for each pixel of the dilated set to facilitate a separation of the region from background portions of the image.Type: GrantFiled: December 22, 2000Date of Patent: May 25, 2004Assignee: Microsoft CorporationInventors: Andrew Blake, Kentaro Toyama
-
Patent number: 6731824Abstract: A spatial filtering method providing quick detection and visualization of irregularities of SEM images of components such as integrated circuits includes the steps of: (a) acquiring a digital image as a two-dimensional array of pixel data from an original image; (b) calculating a first Fourier transform to generate a two-dimensional array of complex data; (c) calculating a power spectrum to provide a real function representing a weighting of each spatial frequency in the original image; (d) generating a mask for suppressing regular structures of the original image and undesirable artifacts introduced by the acquiring of the digital image in step (a); (e) dilating the mask generated in step (d) by extending masking spots generated therein to increase the suppression of regular structures of the original image; (f) applying the mask dilated in step (e) to the data from the first Fourier transform for removing periodic data to result in a second Fourier transform; (g) calculating an inverse Fourier transform ofType: GrantFiled: February 21, 2001Date of Patent: May 4, 2004Assignee: PROMos Technologies, Inc.Inventor: Jeremy D. Russell
-
Patent number: 6728004Abstract: A method for processing digital images to be displayed, stored, or printed, to eliminate blooming and other artifacts. The system utilizes morphological processes to isolate and modify image structures susceptible to marking process artifacts and then combines the modified image structures with the input image to produce a printable image that may be rendered on a given printer.Type: GrantFiled: May 30, 2001Date of Patent: April 27, 2004Assignee: Xerox CorporationInventors: Robert P. Loce, Michael Branciforte, Ying-wei Lin
-
Publication number: 20040076335Abstract: A method for extracting an object of interest from an image is provided. The method initiates with defining an image feature space based upon frequency information. Then, the image feature space is filtered to smooth both focused regions and defocused regions while maintaining respective boundaries associated with the focused regions and the defocused regions. The filtered image feature space is manipulated by region merging and adaptive thresholding to extract an object-of-interest. A computer readable media, an image capture device and an image searching system are also provided.Type: ApplicationFiled: April 11, 2003Publication date: April 22, 2004Inventor: Changick Kim
-
Patent number: 6697168Abstract: A method for calibrating image recording equipment is described. According to the method, raster areas such as images or color prints are recorded pixel by pixel, line by line in the form of screen dots on an image support by use of at least one exposure beam generated in an exposure unit. An image stored as a bit-map image and containing line data (binary image) is divided into fields. A raster percentage is determined for every field by calculating an average. A variation in the raster percentage is determined from a density-exposure curve. The parameters required for the variation are calculated by an algorithm and memorized in a variation table. The most suitable algorithm is read from the variation table and executed and the data determined thereby are memorized.Type: GrantFiled: December 18, 2000Date of Patent: February 24, 2004Assignee: Heidelberger Druckmaschinen AGInventor: Jörg Olaf Von Wechgeln
-
Publication number: 20040032600Abstract: A method for converting an original halftone bitmap image to a color converted halftone bitmap image by morphological filtering of the original image to compensate for tone and color reproduction characteristics comprising: providing an original halftone bitmap image. The method includes providing a set of asymmetrical morphological filters that have the property that when they are applied recursively in order, the features in the halftone bitmap image are dilated or eroded by varying amounts by extending or reducing the edges first in one direction, then in two directions, etc.Type: ApplicationFiled: August 19, 2002Publication date: February 19, 2004Applicant: Eastman Kodak CompanyInventors: Peter D. Burns, Gustav J. Braun, Kurt M. Sanger
-
Publication number: 20040027618Abstract: The image defect detecting method detects, from image data obtained by reading photoelectrically an original, image defect candidates of an image to be reproduced by the image data which are due to damage of the original and foreign matter sticking to the original, or further foreign matter sticking to a reading system for reading the original, or foreign matter sticking to an image pick-up system for shooting a subject, and removes the image defect candidates in accordance with a density at which the image defect candidates are present, such that the image defect candidates present in a place where the density exceeds a predetermined state are removed and the image defect candidates which are not removed are regarded as image defects of the image to be reproduced by the image data.Type: ApplicationFiled: June 3, 2003Publication date: February 12, 2004Applicant: FUJI PHOTO FILM CO., LTD.Inventors: Hiroaki Nakamura, Kui Fu, Yoshifumi Donomae
-
Patent number: 6681032Abstract: A system and method for acquiring, processing, and comparing an image with a stored image to determine if a match exists. In particular, the system refines the image data associated with an object based on pre-stored color values, such as flesh tone color. The system includes a storage element for storing flesh tone colors of a plurality of people, and a defining stage for localizing a region of interest in the image. A combination stage combines the unrefined region of interest with one or more pre-stored flesh tone colors to refine the region of interest based on color. This flesh tone color matching ensures that at least a portion of the image corresponding to the unrefined region of interest having flesh tone color is incorporated into the refined region of interest. Hence, the system can localize the head, based on the flesh tone color of the skin of the face in a rapid manner. According to one practice, the refined region of interest is smaller than or about equal to the unrefined region of interest.Type: GrantFiled: August 16, 2001Date of Patent: January 20, 2004Assignee: Viisage Technology, Inc.Inventors: Jay F. Bortolussi, Francis J. Cusack, Jr., Dennis C. Ehn, Thomas M. Kuzeja, Michael S. Saulnier
-
Subtraction technique for computerized detection of small lung nodules in computer tomography images
Patent number: 6678399Abstract: A method, system, computer readable medium and apparatus for computerized detection of lung nodules in computer tomography images, by which mask images are created such that subtractions of the mask image from a targeted CT section image reveal or highlight small lung nodules in the target CT section. The mask image is created utilizing the targeted CT section image along with other CT section images generated from the same CT scan. Based on these other section CT images and the targeted CT section image, a mask image can be created that is very similar to the target CT section image, but without the presence of small lung nodules. When the mask image is subtracted from the targeted CT section image, the differences between the mask images and the CT section images reveal small lung nodules. The mask image may be created by linear interpolation or a morphological filtered image.Type: GrantFiled: November 23, 2001Date of Patent: January 13, 2004Assignee: University of ChicagoInventors: Kunio Doi, Takayuki Ishida, Shigehiko Katsuragawa -
Patent number: 6674914Abstract: A grayscale morphological erosion operator image processor which operates on images of any size and dimension with a structuring element of any dimension and shape. The present invention performs all 1D erosion operations in the domain by first decomposing an image and structuring element into a series of 1D slices, and then further segmenting the structuring element into a plurality of shorter 1D segments. These segments are processed in parallel using an array of parallel processors. Once the erosion operations are complete, the resulting one dimensional slices are composed into a final eroded image.Type: GrantFiled: September 21, 1999Date of Patent: January 6, 2004Assignee: Lucent Technologies Inc.Inventor: Reitseng Lin
-
Publication number: 20040001624Abstract: A method and a system for separating an image signal into a set of image planes in accordance with a control signal. The system comprises a selector module, an edge processing module and a foreground/background separation module. The selector module receives the control signal and produces a selector signal. The edge processing module receives the selector signal and produces a decision signal. The foreground/background separation module receives the image signal and the decision signal, and outputs a foreground signal and a background signal, a representation of the current pixel of the image signal being included in at least one of the foreground signal and the background signal in accordance with the decision signal.Type: ApplicationFiled: July 1, 2002Publication date: January 1, 2004Applicant: Xerox CorporationInventors: Donald J. Curry, Doron Kletter, Asghar Nafarieh
-
Publication number: 20030218780Abstract: A method for color correcting an original halftone bitmap image by a predefined color correction function to produce a color corrected halftone bitmap image comprising: providing an original halftone bitmap image; estimating the dot area percentage of the original halftone bitmap image in a set of sub-image blocks; calculating an aim dot area percentage, based on a predefined color correction function, for each sub-image block in the original halftone bitmap image, calculating the number of halftone bitmap image pixels to convert to on or off states to produce a modified original halftone bitmap image that has the aim dot area percentage where said value is designated by N, for each sub-image block in the original halftone bitmap image, and converting N pixels in the original halftone bitmap image to either on or off states depending on whether the aim dot area percentage is greater or less than the dot area percentage of the original halftone bitmap image respectively, for each sub-image block in the originaType: ApplicationFiled: May 24, 2002Publication date: November 27, 2003Applicant: Eastman Kodak CompanyInventors: Gustav J. Braun, Peter D. Burns, Kevin E. Spaulding
-
Patent number: 6654495Abstract: Methods and apparatus are provided for removing ruled lines from a binary image containing character portions and ruled line portions, comprising the following steps. First, horizontal black runs in the bit-map image are detected and the detected black runs portions are stored as a run-length table comprising values of the horizontal start point and the length from the starting point of each black run for each vertical position. Then, based on the run-length table, black runs exceeding a predetermined threshold value are removed from the image to remove the ruled line comprising those black runs. Then, residual noise is eliminated from the image after the removal of the ruled lines. Then, in the image after the elimination of the residual noise, vertically disconnected components of a character are connected. Then, a portion of the character which is deleted by ruled line removal process is extracted from the image after the connection of vertically disconnected components of the character.Type: GrantFiled: April 25, 2000Date of Patent: November 25, 2003Assignee: International Business Machines CorporationInventors: Shin Katoh, Hiroyasu Takahashi
-
Patent number: 6650788Abstract: A binary morphological erosion operator image processor which operates on images of any size and dimension with a structuring element of any dimension and shape. The erosion operations are all processed in the 1D domain by first decomposing the image and structuring element into a series of 1D slices, and then further segmenting the structuring element into a plurality of shorter 1D segments. These segments are processed in parallel using an array of parallel processors. Once the erosion operations are completed, the resulting 1D slices are composed into a final eroded image.Type: GrantFiled: September 28, 1999Date of Patent: November 18, 2003Assignee: Lucent Technologies Inc.Inventor: Reitseng Lin
-
Patent number: 6631212Abstract: A method and system for segmenting textures in an image includes computing multiresolution simultaneous autoregressive (MSAR) features in the image, preparing an uncertainty map of the MSAR features (the uncertainty map including high confidence pixels and low confidence pixels), computing wavelet features in the image, preparing a classifier based on the high confidence pixels and the wavelet features, and reclassifying the low confidence pixels based on the classifier to obtain the final segmentation.Type: GrantFiled: September 13, 1999Date of Patent: October 7, 2003Assignee: Eastman Kodak CompanyInventors: Jiebo Luo, Andreas E. Savakis
-
Publication number: 20030174892Abstract: The present invention provides a technique for automated selection of a parameterized operator sequence to achieve a pattern classification task. A collection of labeled data patterns is input and statistical descriptions of the inputted labeled data patterns are then derived. Classifier performance for each of a plurality of candidate operator/parameter sequences is determined. The optimal classifier performance among the candidate classifier performances is then identified. Performance metric information, including, for example, the selected operator sequence/parameter combination, will be outputted. The operator sequences selected can be chosen from a default set of operators, or may be a user-defined set. The operator sequences may include any morphological operators, such as, erosion, dilation, closing, opening, close-open, and open-close.Type: ApplicationFiled: January 9, 2003Publication date: September 18, 2003Inventors: Xiang Gao, Visvanathan Ramesh, Terrance E. Boult
-
Publication number: 20030161547Abstract: The present invention is related to a method for processing a digital image, wherein the digital image comprises at least a gray-scale component. The method may comprise: morphologically filtering the grayscale component to produce a segmentation result; low-pass filtering the gray-scale component under control of at least the segmentation result to produce an image mask; and enhancing tone reproduction of the digital image utilizing at least the image mask.Type: ApplicationFiled: February 22, 2002Publication date: August 28, 2003Inventor: Huitao Luo
-
Publication number: 20030133621Abstract: A parallel processing logic circuit for sensor signal processing includes sensors and processing units. The sensor and the processing unit are integrated in the same pixel and arranged in a matrix. The processing unit contains a logic structure that consists of a register and a combinational logic function to execute pixel-parallel processing, based on binary data for a sensor, other processing units, and itself. The combinational logic function performs only a predetermined logic function and its dual one exclusively, thereby sharing the circuit resource and reducing the size of the processing unit. The register focusing on compactness also contributes to the small unit.Type: ApplicationFiled: July 29, 2002Publication date: July 17, 2003Inventors: Koji Fujii, Satoshi Shigematsu, Hiroki Morimura, Mamoru Nakanishi
-
Publication number: 20030123749Abstract: An annular window-shaped structuring element is provided for image processing to remove speckles from a scanned image. The window-shaped structuring element is composed of two differently sized squares sharing the same geometric center-point. The pixel to be analyzed with the structuring element is at the center-point. The structuring element is used in a method to remove speckles from binary, grayscale, and/or color images by first eroding the image, detecting speckles relative to other pixels in the image, and removing declared speckles. The method may additionally include a halftoning module to protect halftone images.Type: ApplicationFiled: January 2, 2002Publication date: July 3, 2003Applicant: XEROX CORPORATIONInventors: Hui Cheng, Ying-wei Lin, Stuart A. Schweid
-
Patent number: 6574374Abstract: A method including defining a morphological filtering operator designed to remove ringing artifacts in a decompressed image, and then applying that operator upon pixels of the decompressed image that belong to non-texture image regions.Type: GrantFiled: April 14, 1999Date of Patent: June 3, 2003Assignee: Intel CorporationInventor: Tinku Acharya
-
Patent number: 6571014Abstract: A method of encoding images such as fingerprint type images (FIG. 2) is disclosed. A phase map structure for the image is formed (FIG. 3) and any singularities (+1, 2, 0.5) in the phase map structure are removed to create a continuous phase map structure (FIG. 5). The structure of the singularities and the continuous phase map structure are then separately encoded to form an encoded representation (88) of the image (50). Preferably, the singularity encoding includes encoding a position of each singularity in addition to its order and orientation. The phase map structure can be of the form: ƒ(x,y)=a(x,y)+b(x,y)cos(&phgr;(x,y))+c(x,y)+n(x,y) The significance map can further include a separate encoding of phase map magnitude components.Type: GrantFiled: April 21, 1999Date of Patent: May 27, 2003Assignee: Canon Kabushiki KaishaInventor: Kieran Gerard Larkin
-
Patent number: 6563964Abstract: A method and apparatus for digital image downsampling are disclosed with particular application to computer-graphics imagery. The digital image is downsampled non-uniformly in a manner that attempts to minimize aliasing of high-spatial-frequency image information by concentrating deletion paths in lower-spatial-frequency image regions. A spatial frequency estimator compares groups of pixels in order to produce a classification of the image. A path generator and path scorer trace and score potential deletion paths through the image, and the path with the greatest score (i.e., one that provides minimal distortion and aliasing) is selected for pixel removal. A recursor repeats this process until a desired number of image rows and/or columns have been removed.Type: GrantFiled: February 8, 1999Date of Patent: May 13, 2003Assignee: Sharp Laboratories of America, Inc.Inventor: Bryan Severt Hallberg
-
Publication number: 20030072489Abstract: The invention relates to a method of recognizing a code which is encoded inside an image data set which contains a piece of respective information on a gray scale value for each of a plurality of picture elements. At least one dilation operation and/or erosion operation is carried out on the image data set.Type: ApplicationFiled: August 28, 2002Publication date: April 17, 2003Applicant: Sick AGInventors: Juergen Reichenbach, Christiane Stortz, Carl Joseph Hafner, Peter Hauser
-
Patent number: 6549646Abstract: A divide-and-conquer (DAC) method and system improve the detection of abnormalities, like lung nodules, in radiological images via the use of zone-based digital image processing and artificial neural networks. The DAC method and system divide the lung zone into different zones in order to enhance the efficiency in detection. Different image enhancement techniques are used for each different zone to enhance nodule images, as are different zone-specific techniques for selecting suspected abnormalities, extracting image features corresponding to selected abnormalities, and classifying the abnormalities as either true or false abnormalities.Type: GrantFiled: February 15, 2000Date of Patent: April 15, 2003Assignee: Deus Technologies, LLCInventors: Hwa-Young Michael Yeh, Jyh-Shyan Lin, Yuan-Ming Fleming Lure, Xin-Wei Xu, Ruiping Li, Rong Feng Zhuang
-
Publication number: 20030039307Abstract: Video data is compressed with nonkey frames encoded with reference to segmentation of reference frames, where the encoded video data includes kinetic information relating segments of a reference frame to pixels of a nonkey frame and the kinetic information includes translations of segments and at least one of a z-order, a deformation and a lighting change. The segmentation performed during encoding can be included in whole or part in the compressed video data. If used, z-ordering could be relative or absolute, based on changes of occlusion of segments by other segments between the frames, based on content of other frames or based on z-order indications in the video data being compressed. Other kinetic information might include segment changes between frames such as rotation, dilation, affine transformations, nonlinear transformations defined by a set of deformation parameters, linear lighting offsets in one, two or three color planes, and/or residue information.Type: ApplicationFiled: March 20, 2002Publication date: February 27, 2003Applicant: Pulsent CorporationInventors: Adityo Prakash, Eniko Fodor
-
Publication number: 20030039402Abstract: To avoid generating visible artifacts in the image, such as those generated when mildly defective areas are not identified, a system and method for identifying and correcting defects in a digital image including adjusting the pixel values of pixels surrounding the defective pixels are disclosed. The method for correcting defects in a input digital image comprises the steps of identifying the defects to form at least one defect map, generating a region of interest for each defect map, correcting the values of the pixels in each defect map, and adjusting the values of the pixels in each region of interest.Type: ApplicationFiled: August 24, 2001Publication date: February 27, 2003Inventors: David R. Robins, Jong Chul Ye
-
Patent number: 6522786Abstract: A method and apparatus for reducing noise in a three dimensional rectilinear parallelepiped data point array includes both erosion and dilation processes for each array point value. The erosion process includes the steps of determining gradients along all three axis which pass through a data point and modifying the point value as a function of the gradients to generate an updated point value. The dilation process includes the steps of using point values from the updated array, determining gradients along all three axis which pass through the point, and modifying the updated point value as a function of the gradients to generate a final and revised point value.Type: GrantFiled: June 14, 1999Date of Patent: February 18, 2003Assignee: General Electric CompanyInventor: Harvey Ellis Cline
-
Patent number: 6516097Abstract: In a system for segmenting a pixel based image, pixels containing image boundaries are identified. The image boundaries are then fattened by repeatedly adding fattening rows of pixels to the pixels containing boundaries to separate the remaining pixels into separate segments. The separate segments are then grown back to their original size before the boundaries were fattened. This operation has the effect of linking the boundaries together to separate the image into segments and to extend incomplete boundaries into complete boundaries around segments in the image.Type: GrantFiled: July 16, 1999Date of Patent: February 4, 2003Assignee: Lockheed Martin CorporationInventor: Mark D. Pritt
-
Publication number: 20030021480Abstract: By a method of detecting a branch point, the branch point in a random line pattern of neovascularization or the like is detected accurately and efficiently. After a binary image is obtained from an original image, noise filling is performed for removing a noise in a line element to provide a filled image. The filled image is thinned to provide in a thinned image including the line element having its width change to one pixel. Plural previously-registered branch patterns are collated with the thinned image, and consequently, the branch point at which the line element of the random line pattern branches off is detected.Type: ApplicationFiled: July 22, 2002Publication date: January 30, 2003Inventor: Yuji Ishitsu
-
Patent number: 6512845Abstract: Selection of pixels from a scanned image of a target document. The target document includes a plurality of color patches. The image includes a rectangular grid of pixels at least some of which correspond to a color patch on the target document. All of the selected pixels correspond to the color patch. The pixels of the image have color values associated therewith. A position in the image is determined which is expected to correspond to the color patch on the target document. An approximation is selected of pixels which correspond to the color patch at the determined position in the image. Groups of all pixels for a border of the approximation are successively discarded, thereby reducing an area of the approximation. The groups of pixels are successively discarded until a variance of color values is stabilized for pixels in the approximation.Type: GrantFiled: July 20, 1999Date of Patent: January 28, 2003Assignee: Canon Kabushiki KaishaInventors: John S. Haikin, Timothy L. Kohler
-
Patent number: 6504953Abstract: In a method for automatic removal of image errors in digital image data, for example which have arisen due to scratches, hairs, etc., a contour mask is generated with a contour filter and a color mask is additionally generated that covers the image areas having the typical color of an image error. By operating the contour mask and the color mask, an error mask arises that is also automatically corrected and is manually edited as warranted. The remaining contours of the error mask are vectorized. An automatic bleeding retouch is then implemented along the vectorized contours.Type: GrantFiled: August 18, 1999Date of Patent: January 7, 2003Assignee: Heidelberger Druckmaschinen AktiengesellschaftInventor: Rolf Behrends
-
Publication number: 20020191831Abstract: Three-dimensional analysis of surface defects and microdefects of an object is performed by correlating two images of the surface of the object based upon a stereoscopic view thereof. Analyzing surface defects may be implemented by integrating, in a single monolithic component made using VLSI CMOS technology, an optical sensor with a cellular neural network. The optical sensor includes a matrix of cells configured as analog processors.Type: ApplicationFiled: April 25, 2002Publication date: December 19, 2002Applicant: STMicroelectronics S.r.l.Inventors: Giuseppe Spoto, Marco Branciforte, Francesco Doddo, Luigi Occhipinti
-
Publication number: 20020154831Abstract: Binary screen image data redigitized in pixels are retouched, specifically to eliminate local screen defects such as dust artifacts and scratch artifacts. Defective screen dots are selected and recorded for the purpose of detecting screen defects. Then, dust artifacts and scratch artifacts or the like are removed from contaminated image data. Furthermore, missing points in the screen are also filled up, and inhomogeneous image regions are corrected in part. The production of visible moire effects in the retouched image data is avoided by the replacement of only small areas.Type: ApplicationFiled: March 21, 2002Publication date: October 24, 2002Inventors: Michael Hansen, Erich Selder, Jorg Olaf Von Wechgeln
-
Publication number: 20020150303Abstract: A spatial filtering method providing quick detection and visualization of irregularities of SEM images of components such as integrated circuits includes the steps of: (a) acquiring a digital image as a two-dimensional array of pixel data from an original image; (b) calculating a first Fourier transform to generate a two-dimensional array of complex data; (c) calculating a power spectrum to provide a real function representing a weighting of each spatial frequency in the original image; (d) generating a mask for suppressing regular structures of the original image and undesirable artifacts introduced by the acquiring of the digital image in step (a); (e) dilating the mask generated in step (d) by extending masking spots generated therein to increase the suppression of regular structures of the original image; (f) applying the mask dilated in step (e) to the data from the first Fourier transform for removing periodic data to result in a second Fourier transform; (g) calculating an inverse Fourier transform ofType: ApplicationFiled: February 21, 2001Publication date: October 17, 2002Inventor: Jeremy D. Russell
-
Publication number: 20020141631Abstract: Methods, code and apparatus analyze cell images to automatically identify and characterize the Golgi complex in individual cells. This is accomplished by first locating the cells in the image and defining boundaries of those cells that subsume some or all of the Golgi complex of those cells. The Golgi complex in the images typically have intensity values corresponding to the concentration of a Golgi component in the cell (e.g. a polysaccharide associated with the Golgi complex). The method/system then analyzes the Golgi components of the image (typically on a pixel-by-pixel basis) to mathematically characterize the Golgi complex of individual cells. This mathematical characterization represents phenotypic information about the cells' Golgi complex and can be used to classify cells. From this information, mechanism of action and other important biological information can be deduced.Type: ApplicationFiled: February 20, 2001Publication date: October 3, 2002Applicant: Cytokinetics, Inc.Inventors: Eugeni A. Vaisberg, Ge Cong, Hsien-Hsun Wu
-
Patent number: 6411733Abstract: A method and apparatus is provided for segmenting a binary document image so as to assign image objects to one of three types: CHARACTER-type objects, STROKE-type objects, and LARGE-BITMAP-type objects. The method makes use of a contour tracing technique, statistical analysis of contour features, a thinning technique, and image morphology.Type: GrantFiled: November 25, 1998Date of Patent: June 25, 2002Assignee: Xerox CorporationInventor: Eric Saund