Calculating Weighted Similarity Or Difference (e.g., Dont-care Areas) Patents (Class 382/220)
  • Patent number: 7746507
    Abstract: Even if a margin area, which did not exist in an original image, is present around a document area in a document acquired by printing the original image, an accurate layout comparison between the scanned image of the printed document and the original image can be performed as follows. An original image serving as a comparison target image is input, and block information about a block included in the original image is extracted. It is determined whether the size of the original image is a predetermined size. When the size is not a predetermined size, block information about the block included in the original image mapped to a predetermined size is created and registered. When a comparison source image is input, block information about a block included in the comparison source image is extracted. Subsequently, two pieces of the block information of the comparison source and target images are compared.
    Type: Grant
    Filed: July 27, 2006
    Date of Patent: June 29, 2010
    Assignee: Canon Kabushiki Kaisha
    Inventors: Masahiro Matsushita, Hiroshi Tojo
  • Patent number: 7734102
    Abstract: A system for screening cargo containers is provided including an image generation device, an apparatus for screening cargo containers and an output module. The image generation device generates an image signal conveying information related to the contents of the cargo container. The apparatus receives the image signal and a list of objects conveying objects expected to be present in the cargo container. A processing unit processes the image signal in combination with the list of objects and a group of target images associated with objects to derive mismatch information data. The mismatch information data conveys at least one distinction between the list of objects and the information related to the contents of the cargo container conveyed by the image signal. Information conveying the mismatch information data is released and conveyed to a user of the system by an output module.
    Type: Grant
    Filed: November 8, 2005
    Date of Patent: June 8, 2010
    Assignee: Optosecurity Inc.
    Inventors: Eric Bergeron, Luc Perron, Alain Bergeron
  • Publication number: 20100119162
    Abstract: An image processing apparatus includes: an image pyramid forming section configured to form an image pyramid by hierarchically creating layered image data including differently scaled images from inputted image data; a position calculating section configured to determine an in-image-pyramid position as a height position in the image pyramid to which template image data having an image portion of a target object at a fixed scale corresponds; an upper-layer-side likelihood calculating section configured to determine a likelihood for a target object by matching between upper-side layer image data directly above the in-image-pyramid position, and a state prediction; a lower-layer-side likelihood calculating section configured to determine a likelihood for a target object by matching between lower-side layer image data directly below the in-image-pyramid position, and a state prediction; and a true likelihood calculating section configured to determine a true likelihood from the likelihoods determined by the upper
    Type: Application
    Filed: November 6, 2009
    Publication date: May 13, 2010
    Inventors: Yuyu Liu, Keisuke Yamaoka, Takayuki Yoshigahara, Xi Chen
  • Publication number: 20100098342
    Abstract: A method, system, and medium are provided for detecting change in a geographic area. One embodiment includes receiving a set of remotely sensed imagery that depicts the geographic area, automatically identifying changes in physical features of the geographic area by comparing, without user intervention, the set of remotely sensed imagery to a dataset of previously stored remotely sensed imagery that also depicts the geographic area, and deriving a change-quality measurement associated with the set of remotely sensed imagery, wherein the change-quality measurement quantifies a suitability of comparison of the set of remotely sensed imagery to the previously stored remotely sensed imagery.
    Type: Application
    Filed: October 20, 2008
    Publication date: April 22, 2010
    Applicant: CURATORS OF THE UNIVERSITY OF MISSOURI
    Inventors: Curtis Herbert Davis, Brian Christopher Claywell, James Michael Keller, Matthew Nicholas Klaric, Grant Jason Scott, Chi-Ren Shyu
  • Patent number: 7643966
    Abstract: A computer model of a physical structure (or object) can be generated using context-based hypothesis testing. For a set of point data, a user selects a context specifying a geometric category corresponding to the structure shape. The user specifies at least one seed point from the set that lies on a surface of the structure of interest. Using the context and point data, the system loads points in a region near the seed point(s), and determines the dimensions and orientation of an initial surface component in the context that corresponds to those points. If the selected component is supported by the points, that component can be added to a computer model of the surface. The system can repeatedly find points near a possible extension of the surface model, using the context and current surface component(s) to generate hypotheses for extending the surface model to these points.
    Type: Grant
    Filed: March 8, 2005
    Date of Patent: January 5, 2010
    Assignee: Leica Geosystems AG
    Inventors: Jeffrey Minoru Adachi, Mark Damon Wheeler, Jonathan Apollo Kung, Richard William Bukowski, Laura Michele Downs
  • Patent number: 7606424
    Abstract: Improved correlation techniques employ data from forward (template-to-reference) and reverse (reference-to-template) correlation to identify valid correlation peaks, enforce symmetry in correlation peaks, and/or combine forward and reverse correlation data. In embodiments, these techniques eliminate or reduce rms noise in a recovered signal peak location by enforcing correlation peak symmetry. The forward and reverse correlation methods described herein may be used for validation of correlation peaks, detection of outlier data points and improved interpolation, such as for higher accuracy localization of a peak center with sub-pixel resolution.
    Type: Grant
    Filed: June 1, 2006
    Date of Patent: October 20, 2009
    Assignee: 3M Innovative Properties Company
    Inventor: Janos Rohaly
  • Patent number: 7596283
    Abstract: A method and system for non-rigidly registering a fixed to a moving image utilizing a B-Spline based free form deformation (FFD) model is disclosed. The methodology utilizes sparse feature correspondences to estimate an elastic deformation field in a closed form. In a multi-resolution manner, the method is able to recover small to large non-rigid deformations. The resulting deformation field is globally smooth and guarantees one-to-one mapping between the images being registered.
    Type: Grant
    Filed: April 5, 2005
    Date of Patent: September 29, 2009
    Assignee: Siemens Medical Solutions USA, Inc.
    Inventors: Chenyang Xu, Xiaolei Sharon Huang, Yiyong Sun
  • Publication number: 20090185747
    Abstract: A method for texture synthesis for video coding with side information may be implemented by a decoder device. The method may include receiving seed texture at high fidelity. The method may also include receiving remaining portions of synthesized regions at low fidelity. The method may also include receiving marking of regions to synthesize. The method may further include synthesizing the marked regions based on the high-fidelity seed texture and the low-fidelity portions of the synthesized regions.
    Type: Application
    Filed: September 3, 2008
    Publication date: July 23, 2009
    Applicant: Sharp Laboratories of America, Inc.
    Inventors: Christopher A. Segall, Yeping Su, Byung Tae Oh
  • Patent number: 7545984
    Abstract: Methods, apparatuses, and systems are presented for measuring difference between graphics images relating to performing an arithmetic operation involving a first graphics image comprising a plurality of first pixels and a second graphics image comprising a plurality of second pixels to produce a difference image comprising a plurality of difference pixels, generating measures of proximity from a plurality of ranges of observation within the difference image, wherein the measures of proximity represent spatial proximity of difference pixels to other difference pixels within the difference image, and applying non-uniform weighting to the difference pixels to produce a weighted difference image, wherein the non-uniform weighting depends on the measures of proximity generated from the plurality of ranges of observation.
    Type: Grant
    Filed: December 16, 2004
    Date of Patent: June 9, 2009
    Assignee: Nvidia Corporation
    Inventors: Jeffrey T. Kiel, Eldon S. Larsen
  • Patent number: 7529411
    Abstract: A method of identifying an object captured in a video image in a multi-camera video surveillance system is disclosed. Sets of identifying information are stored in profiles, each profile being associated with one object. The disclosed method of identifying an object includes comparing identifying information extracted from images captured by the video surveillance system to one or more stored profiles. A confidence score is calculated for each comparison and used to determine a best match between the extracted set of identifying information and an object. In one embodiment, the method is used as part of a facial recognition system incorporated into a video surveillance system.
    Type: Grant
    Filed: March 15, 2005
    Date of Patent: May 5, 2009
    Assignee: 3VR Security, Inc.
    Inventors: Gordon T. Haupt, J. Andrew Freeman, Stephen D. Fleischer, Robert P. Vallone, Stephen G. Russell, Timothy B. Frederick
  • Patent number: 7492947
    Abstract: This invention consists in an image processing method in which the similarity between a first pixel and a second pixel constituting an image is numerically given by statistical testing, and the values of the first and second pixels are averaged when the similarity numerically given is high, whereas the first and second pixel values are not averaged when the determined similarity is low, whereby an image with noises suppressed is obtained without spoiling a spatial resolution as well as a temporal resolution.
    Type: Grant
    Filed: October 8, 2003
    Date of Patent: February 17, 2009
    Assignee: Kabushiki Kaisha Toshiba
    Inventor: Kyojiro Nanbu
  • Patent number: 7450262
    Abstract: A form recognizing apparatus, a form recognizing method and a form recognizing program for easily and precisely recognizing whether or not a form including multiple pages corresponds to any of multiple registered forms are disclosed. A form is registered. The registered form includes a feature amount and weight information of each page of the registered form. A page similarity value of each page of each of the registered forms is calculated by comparing a feature amount of each page of an input form image to be recognized and a feature amount of the corresponding page of the registered form. A form similarity value between the input form image to be recognized and each of the registered forms is calculated by weighting the page similarity values of the calculated pages by using weight information of the registered pages. A registered form corresponding to the form image to be recognized is determined.
    Type: Grant
    Filed: September 23, 2004
    Date of Patent: November 11, 2008
    Assignee: Canon Kabushiki Kaisha
    Inventor: Hiroaki Ikeda
  • Patent number: 7444033
    Abstract: The luminance and chrominance values of pixels encoded according to MPEG or JPEG encoding are extracted using a forward discrete cosine transform (DCT). The forward DCT used in MPEG encoding is analyzed to derive a set of equations which directly relate a pixel value in an encoded image to one or more of the DCT coefficients obtained via the forward DCT transform in the usual image encoding process. These predetermined equations are used to allow for extremely fast and computationally efficient extraction of pixel values directly from the DCT coefficients of an encoded pixel block, without having to undergo an inverse DCT transform. Original images from MPEG and JPEG encoded versions may be extracted in a fast and efficient manner.
    Type: Grant
    Filed: December 24, 2002
    Date of Patent: October 28, 2008
    Assignee: British Telecommunications PLC
    Inventors: Jianmin Jiang, Li-Qun Xu
  • Patent number: 7440602
    Abstract: A method for improving images of an imaging system including a plurality of detector cells includes assigning a quality factor for each detector cell.
    Type: Grant
    Filed: November 17, 2004
    Date of Patent: October 21, 2008
    Assignees: General Electric Company, Purdue Research Foundation, The University of Notre Dame du 1ac
    Inventors: Jiang Hsieh, Charles Addison Bouman, Ken David Sauer, Jean-Baptiste Thibault
  • Patent number: 7409108
    Abstract: A method of aligning a pair of images with a first image and a second image, wherein said images comprise a plurality of intensities corresponding to a domain of points in a D-dimensional space includes identifying feature points on both images using the same criteria, computing a feature vector for each feature point, measuring a feature dissimilarity for each pair of feature vectors, wherein a first feature vector of each pair is associated with a first feature point on the first image, and a second feature vector of each pair is associated with a second feature point on the second image. A correspondence mapping for each pair of feature points is determined using the feature dissimilarity associated with each feature point pair, and an image transformation is defined to align the second image with the first image using one or more pairs of feature points that are least dissimilar.
    Type: Grant
    Filed: September 21, 2004
    Date of Patent: August 5, 2008
    Assignee: Siemens Medical Solutions USA, Inc.
    Inventors: Chenyang Xu, Xiaolei Huang, Frank Sauer, Christophe Chefd'hotel, Jens Gühring, Sebastian Vogt, Yiyong Sun
  • Patent number: 7406187
    Abstract: In computer aided diagnosis, a high-accuracy image indicating a temporal difference of a diseased part of a patient is produced from a current image and a past image as follows. First, a plurality of matching ROIs (Regions of Interest) are defined on the current image and the past image. A matching processing is performed on corresponding ROIs of the two images to determine points on the past image corresponding to the respective points on the current image. Obtained shift vectors are fitted to a two-dimensional polynomial. In the fitting, when a matching ROI of the current image is included in or overlapped with a previously-defined region of interest, shift vectors are weighted by a small factor. The current image is then modified according to obtained fitting coefficients. Finally, an image indicating the difference between the modified current image and the past image is produced.
    Type: Grant
    Filed: January 27, 2005
    Date of Patent: July 29, 2008
    Assignee: Canon Kabushiki Kaisha
    Inventors: Makoto Sato, Muling Guo
  • Publication number: 20080050023
    Abstract: A method and apparatus for data filling is disclosed herein. In one embodiment, the method comprises receiving an image and a mask associated with the image and performing a block-based, iterative multi-pass data filling process to fill a layer as part of compound document compression.
    Type: Application
    Filed: August 25, 2006
    Publication date: February 28, 2008
    Inventors: Guotong Feng, Michael J. Gormish
  • Patent number: 7319791
    Abstract: A method for recognizing an object in a target image using model primitives comprising an additive primitive and a subtractive primitive; weights are assigned to the additive and subtractive primitives; a target primitive is derived for the object; associations are determined between the target primitive and the model primitives; a similarity score is computed for the target primitive with respect to the model primitives; the similarity score is increased for each association between the target primitive and the additive primitive and decreased for each association between the target primitive and the subtractive primitive; the weights determine an amount by which the similarity score is increased or decreased for each of the associations.
    Type: Grant
    Filed: February 25, 2005
    Date of Patent: January 15, 2008
    Assignee: Matrox Electronic Systems, Ltd.
    Inventors: Stephane Baldo, Djamel Yahia Meddah
  • Patent number: 7308443
    Abstract: A query is received. The query may be an object containing temporal information. A query model including static and temporal components is then determined for the object. A weighting for static and temporal components is also determined. The query model is then compared with one or more search models. The search models also include static and temporal components. Search results are then determined based on the comparison. In one embodiment, the comparison may compare the static and temporal components of the query model and the search model. A weighting of the differences between the static and temporal components may be used to determine the ranking for the search results.
    Type: Grant
    Filed: December 23, 2004
    Date of Patent: December 11, 2007
    Assignee: Ricoh Company, Ltd.
    Inventors: Dar-Shyang Lee, Jonathan J. Hull, Gregory J. Wolff
  • Patent number: 7308140
    Abstract: A method of measuring a similarity between images is provided. The method includes the steps of (a) computing a statistical dissimilarity between the images; (b) computing a perceptual dissimilarity between the images; and (c) computing a dissimilarity between the texture features of the images based on the statistical dissimilarity and the perceptual dissimilarity. When images perceptually similar to a query image are searched and retrieved according to the above measuring method, the possibility that the retrieved images are not perceptually similar to the query image is small. Accordingly, the image searching performance can be improved when searching images having texture features similar to that of a query image.
    Type: Grant
    Filed: April 2, 2001
    Date of Patent: December 11, 2007
    Assignees: Samsung Electronics Co., Ltd., The Regents of the University of California, Applera Corporation
    Inventors: Hyun-doo Shin, Yang-Iim Choi, Bangalore S. Manjunath, Peng Wu
  • Patent number: 7298907
    Abstract: A target recognizing device that creates a template concerning a target by itself is provided. The device comprises a robot camera for creating continuous images showing a target and an arithmetic operation unit for controlling the robot camera. A robot camera acquires continuous image information by means of a camera rotatable by a motor. The arithmetic operation unit comprises a template management section for allowing an update part to update a template stored in a template storage part and a target recognition section having an image storage part where the acquired image information is stored, a recognizing part for recognizing a target by using the template, and a motion command part for rotating a camera according to the result of recognition.
    Type: Grant
    Filed: February 13, 2002
    Date of Patent: November 20, 2007
    Assignee: Honda Giken Kogyo Kabushiki Kaisha
    Inventor: Yuji Hasegawa
  • Patent number: 7221805
    Abstract: A method is provided for computing a composite image representing a focused image of an object in an application of machine vision in an optical inspection system. An image tessellated into focus regions is evaluated by region for fine feature sharpness. A sharpness image is computed for each focused region using a fine feature sharpness measurement. A focused composite image is computed by combining as a weighted average, the images at several focus settings, using the sharpness image at each focus setting as the weight. The focused composite image can be further analyzed, inspected, or otherwise processed.
    Type: Grant
    Filed: December 21, 2001
    Date of Patent: May 22, 2007
    Assignee: Cognex Technology and Investment Corporation
    Inventor: Ivan Bachelder
  • Patent number: 7136508
    Abstract: A moving image Vd consists of a plurality of frames F1–F12. A scene change SC of the moving image Vd is detected according to change in each frame regarding to brightness information of image, and the plurality of frames are divided into frame groups FG1 (F1–F8) and FG2 (F9–F12) each having substantially the same scene at the scene change as a boundary. Then, with respect to the frame group FG1, every three frames, F1, F4, F7 are sampled to execute scene determination, and a most frequent scene is determined as a common scene of the frame group. Consequently, scene determination results for sufficiently scene-changed frames F4, F7 interposed between frames F1, F12 of both ends of the frame group FG1 can be utilized, so that it is possible to determine the common scene with high accuracy.
    Type: Grant
    Filed: November 1, 2001
    Date of Patent: November 14, 2006
    Assignee: Minolta Co., Ltd.
    Inventors: Motohiro Asano, Yumiko Tozuka
  • Patent number: 7103227
    Abstract: A method enhances images of a naturally illuminated scene. First, a set of images Ii(x, y) is acquired of a scene. Each image is acquired under a different uncontrolled illumination. For each image Ii(x, y), intensity gradients ?Ii(x, y) are determined, and each image is weighted with weights according to the intensity gradients. The weighted images are then combined to construct an enhanced image I?.
    Type: Grant
    Filed: March 19, 2003
    Date of Patent: September 5, 2006
    Assignee: Mitsubishi Electric Research Laboratories, Inc.
    Inventors: Ramesh Raskar, Adrian Ilie, Jingi Yu
  • Patent number: 7062083
    Abstract: An image retrieval method with improved performance in which a data image similar to a query image is retrieved by appropriately combining color and texture features. The method for retrieving a data image similar to a query image in an image database containing a plurality of data images involves: calculating color and texture distances between a query image and each data image in the image database; weighting the calculated color and texture distances with predetermined weighting factors; calculating a feature distance between the query image and each data image by combining the weighted color and texture distances by considering human visual perception attributes; and determining the data image similar to the query image using the feature distance. According to the image retrieval method, data images similar to a query image can be retrieved based on the human visual perception mechanism by combining both color and texture features extracted from image regions.
    Type: Grant
    Filed: January 9, 2002
    Date of Patent: June 13, 2006
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Choi Yang Lim, Cho Nam Ik, Kwak Jung Won
  • Patent number: 7047238
    Abstract: Disclosed are a document retrieval method and system for separately performing a process for correcting erroneously recognized characters existing in characteristic character strings within a seed document or the documents to be registered and a process for tolerating erroneously recognized characters existing in the documents targeted for retrieval. The process for correcting erroneously recognized characters existing in characteristic character strings extracts characteristic character strings from a read document, replaces the extracted characteristic character strings containing erroneously recognized characters with character strings appropriate for document retrieval, and selects characteristic character strings for use in actual document retrieval.
    Type: Grant
    Filed: February 21, 2003
    Date of Patent: May 16, 2006
    Assignees: Hitachi, Ltd., Hitachi Systems & Services, Ltd.
    Inventors: Katsumi Tada, Hisashi Takatori
  • Patent number: 7046850
    Abstract: A method for matching digital images, including regularization of image features of a first digital image, composed of pixels, defining a finite set of candidate values, wherein a candidate value represents a candidate for a possible match between image features of the first image and a second image, establishing a matching penalty function for evaluation of the candidate values, evaluating the matching penalty function for every candidate value, selection of a candidate value based on the result of the evaluation of the matching penalty function, regularization of the first image by segmentation of the first image, comprising assigning at least part of the pixels of the first image to respective segments, determining a certainty parameter for at least part of the pixels of a segment, and establishing the matching penalty function to be at least partially based on the certainty parameter.
    Type: Grant
    Filed: September 4, 2001
    Date of Patent: May 16, 2006
    Assignee: Koninklijke Philips Electronics N.V.
    Inventors: Ralph Antonius Cornelius Braspenning, Fabian Edgar Ernst, Cornelius Wilhelmus Antonius Marie Van Overveld, Piotr Wilinski
  • Patent number: 7030885
    Abstract: A method and apparatus for measuring a color-texture distance and a method and apparatus for sectioning an image into a plurality of regions using the measured color-texture distance are provided.
    Type: Grant
    Filed: October 22, 2001
    Date of Patent: April 18, 2006
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Sang-kyun Kim, Seong-deok Lee, Chang-yeong Kim, Pavel A. Chochia, Dmitry V. Sushko, Boris M. Miller
  • Patent number: 7027045
    Abstract: A method models a graphics object by providing a model of the graphics object and generating a first adaptively sampled distance field for the model. Next, a topological hint is constructed. A second adaptively sampled distance field is generated from the topological hint. First locations of the second adaptively sampled distance field are sampled to determine a corresponding topological feature for each location. Second locations in the first adaptively sampled distance are determined from the corresponding topological features. The first adaptively sampled distance field is then sampled at the second locations to determine a distance value for each of the second locations to model the graphics object according to the topological hint.
    Type: Grant
    Filed: March 16, 2001
    Date of Patent: April 11, 2006
    Assignee: Mitsubishi Electric Research Labs Inc.
    Inventors: Ronald N. Perry, Sarah F. Frisken, Jackson W. J. Pope
  • Patent number: 7010163
    Abstract: The invention is a method and apparatus for improving image-processing applications. Embodiments of the invention provide methods for preserving computation results and offer intermediary computation steps to allow the processing of images at any location to take advantage of previously processed image areas. The preferred embodiment offers a method for building a median filter that significantly improves the processing speed over basic techniques. By building a histogram hierarchy, image data statistics are added and subtracted using a multiplicity of histograms from the histogram hierarchy, where each histogram describes an image area. Furthermore, a histogram hierarchy is built using multiple layers, each layer defining a level of statistical resolution.
    Type: Grant
    Filed: April 22, 2002
    Date of Patent: March 7, 2006
    Assignee: Shell & Slate Software
    Inventor: Ben Weiss
  • Patent number: 6993182
    Abstract: The present invention is directed to method of detecting a scene change in video. The method includes a difference being calculated between consecutive frames of the video producing a plurality of difference values. A histogram is taken of the difference values. A scene change is detected if a majority of the difference values in the histogram exceed a predetermined value.
    Type: Grant
    Filed: March 29, 2002
    Date of Patent: January 31, 2006
    Assignee: Koninklijke Philips Electronics N.V.
    Inventors: Yibin Yang, Lilla Boroczky
  • Patent number: 6993189
    Abstract: A system and method to facilitate pattern recognition or matching between patterns are disclosed that is substantially invariant to small transformations. A substantially smooth deformation field is applied to a derivative of a first pattern and a resulting deformation component is added to the first pattern to derive a first deformed pattern. An indication of similarity between the first pattern and a second pattern may be determined by minimizing the distance between the first deformed pattern and the second pattern with respect to deformation coefficients associated with each deformed pattern. The foregoing minimization provides a system (e.g., linear) that may be solved with standard methods.
    Type: Grant
    Filed: June 14, 2004
    Date of Patent: January 31, 2006
    Assignee: Microsoft Corporation
    Inventors: Nebojsa Jojic, Patrice Simard
  • Patent number: 6957387
    Abstract: An apparatus for reproducing an information signal stored on a first storage medium (4). The apparatus comprises a reading unit (2) for reading the information signal from the first storage medium, an output unit (6) for supplying the information signal to a display unit, an user controllable input unit (8) for receiving commands to enable an user to access the information signal. The user controllable input unit is adapted to receive a first command at an instant. The apparatus further comprises a unit (10) for controlling the reading unit to start reading the information signal from said storage medium at a second position in the information signal in response to said first command, the information signal at said second position having features showing a similarity with features of the information signal at a first position read at said instant of receiving said first command, or a features of an information signal read prior to said instant.
    Type: Grant
    Filed: September 5, 2001
    Date of Patent: October 18, 2005
    Assignee: Koninklijke Philips Electronics N.V.
    Inventor: Mauro Barbieri
  • Patent number: 6895073
    Abstract: An apparatus and method for inspecting parts. The apparatus includes an x-ray source for illuminating a part from a plurality of locations with respect to the part and an imaging detector for forming a plurality of measured x-ray images of the part, one such measured x-ray image corresponding to each of the illumination locations. A controller compares each of the measured x-ray images with a corresponding calibration image. The controller provides a defective part indication if one of the measured x-ray images differs from the corresponding calibration image by more than a threshold value in part of the measured x-ray image. The controller localizes defects on the part by comparing two or more of the measured x-ray images with two or more corresponding calibration images. The calibration images can be constructed from measured images of defect free parts.
    Type: Grant
    Filed: November 22, 2002
    Date of Patent: May 17, 2005
    Assignee: Agilent Technologies, Inc.
    Inventors: Ang Shih, S. Jeffrey Rosner
  • Patent number: 6856697
    Abstract: A character reading technique recognizes character strings in grayscale images where characters within such strings have poor contrast, are variable in position or rotation with respect to other characters in the string, or where portions of characters in the string are partially obscured. The method improves classification accuracy by improving the robustness of the underlying correlation operation or the character design. Characters are divided into regions before performing correlations. Based upon the relative individual region results, region results are combined into a whole character result. Using the characters that are read, a running checksum is computed and, based upon the checksum result, characters are replaced to produce a valid result.
    Type: Grant
    Filed: December 29, 2003
    Date of Patent: February 15, 2005
    Inventors: Shih-Jong J. Lee, Piloco Louis
  • Patent number: 6801661
    Abstract: A method for representing an image in terms of the shape properties of its identified segments of interest involves analyzing each segment of interest to automatically identify one or more of its perceptually significant components and then representing each perceptually significant component in terms of its shape properties, e.g., by means of Fourier descriptors. The image segment is then characterized as a composition of the shape properties of its perceptually significant components. By repeating the foregoing steps, the image is represented as a composition of its characterized segments. This technique can then be used to archive and retrieve images based on the shape properties of identified segments.
    Type: Grant
    Filed: February 15, 2001
    Date of Patent: October 5, 2004
    Assignee: Eastman Kodak Company
    Inventors: George E. Sotak, Rajiv Mehrotra
  • Patent number: 6785419
    Abstract: A system and method to facilitate pattern recognition or matching between patterns are disclosed that is substantially invariant to small transformations. A substantially smooth deformation field is applied to a derivative of a first pattern and a resulting deformation component is added to the first pattern to derive a first deformed pattern. An indication of similarity between the first pattern and a second pattern may be determined by minimizing the distance between the first deformed pattern and the second pattern with respect to deformation coefficients associated with each deformed pattern. The foregoing minimization provides a system (e.g., linear) that may be solved with standard methods.
    Type: Grant
    Filed: December 22, 2000
    Date of Patent: August 31, 2004
    Assignee: Microsoft Corporation
    Inventors: Nebojsa Jojic, Patrice Simard
  • Patent number: 6757431
    Abstract: A method for resolution conversion for re-sampling anti-aliased images is disclosed which decreases bandwidth costs associated with anti-aliased line art and other costs associated with interpolating these images to a desired resolution. The present method first involving the receipt of an image which is comprised of bitmap data including at least a plurality of gray-scale pixel tiles that define the image. Then receiving the image data at a first resolution and extracting pixel tile information of the received image at a second resolution. The method has the step of next using loose gray scale template matching on each of the pixel tile information with at least one of a plurality of templates so as to generate pixel-wise looseness interval values there between. Then, outputting a portion of the enhanced pixel tile information wherein the enhanced pixel tile information is formed by a matching of a template with pixel-wise looseness values.
    Type: Grant
    Filed: December 19, 2000
    Date of Patent: June 29, 2004
    Assignee: Xerox Corporation
    Inventors: Robert P. Loce, John C. Handley, Clara Cuciurean-Zapan
  • Patent number: 6751354
    Abstract: Techniques for classifying video frames using statistical models of transform coefficients are disclosed. After optionally being decimated in time and space, image frames are transformed using a discrete cosine transform or Hadamard transform. The methods disclosed model image composition and operate on grayscale images. The resulting transform matrices are reduced using truncation, principal component analysis, or linear discriminant analysis to produce feature vectors. Feature vectors of training images for image classes are used to compute image class statistical models. Once image class statistical models are derived, individual frames are classified by the maximum likelihood resulting from the image class statistical models. Thus, the probabilities that a feature vector derived from a frame would be produced from each of the image class statistical models are computed.
    Type: Grant
    Filed: March 11, 1999
    Date of Patent: June 15, 2004
    Assignees: Fuji Xerox Co., Ltd, Xerox Corporation
    Inventors: Jonathan T. Foote, Lynn Wilcox, Andreas Girgensohn
  • Patent number: 6735337
    Abstract: A character reading technique recognizes character strings in grayscale images where characters within such strings have poor contrast, are variable in position or rotation with respect to other characters in the string, or where portions of characters in the string are partially obscured. The method improves classification accuracy by improving the robustness of the underlying correlation operation. Characters are divided into regions before performing correlations. Based upon the relative individual region results, region results are combined into a whole character result. Using the characters that are read, a running checksum is computed and, based upon the checksum result, characters are replaced to produce a valid result.
    Type: Grant
    Filed: February 2, 2001
    Date of Patent: May 11, 2004
    Inventors: Shih-Jong J. Lee, Louis Piloco
  • Publication number: 20040088722
    Abstract: A method discovers patterns in unknown multi-dimensional data. A time-series of the multi-dimensional data is generated and a point cross-distance matrix is constructed by self-correlating the time-series. All minimum cost paths in the point cross-distance matrix are located at multiple time resolutions. The minimum cost paths are then related to temporal sub-sequences in the multi-dimensional data to discover high-level patterns in the unknown multi-dimensional data.
    Type: Application
    Filed: November 1, 2002
    Publication date: May 6, 2004
    Inventor: Kadir A. Peker
  • Patent number: 6711293
    Abstract: A method and apparatus for identifying scale invariant features in an image and a further method and apparatus for using such scale invariant features to locate an object in an image are disclosed. The method and apparatus for identifying scale invariant features may involve the use of a processor circuit for producing a plurality of component subregion descriptors for each subregion of a pixel region about pixel amplitude extrema in a plurality of difference images produced from the image. This may involve producing a plurality of difference images by blurring an initial image to produce a blurred image and by subtracting the blurred image from the initial image to produce the difference image. For each difference image, pixel amplitude extrema are located and a corresponding pixel region is defined about each pixel amplitude extremum. Each pixel region is divided into subregions and a plurality of component subregion descriptors are produced for each subregion.
    Type: Grant
    Filed: March 6, 2000
    Date of Patent: March 23, 2004
    Assignee: The University of British Columbia
    Inventor: David G. Lowe
  • Patent number: 6697505
    Abstract: Configuration is made by a feature pattern extracting section 12 for extracting a feature obtainable from a person, a subspace calculating section 14 for calculating a subspace from the feature pattern, a recognition section 16 for effecting recognition using the subspace, a registered information holding section 18 for holding a plurality of the subspaces, and a registered information updating section 20 for updating the registered information using the subspaces. When identifying a person, the effect of aging change is reduced by suppressing time and year changes and keeping the recognition rate high.
    Type: Grant
    Filed: June 5, 2003
    Date of Patent: February 24, 2004
    Assignee: Kabushiki Kaisha Toshiba
    Inventors: Osamu Yamaguchi, Kazuhiro Fukui
  • Patent number: 6687398
    Abstract: A method and a device for the identification of incorrectly orientated parts and/or parts departing from a predetermined master, the parts being moved by means of a conveyor means (13) past at least one camera (18) for registering the shapes of the parts. When there is a preset departure from stored masters values the respective part is identified as being faulty and/or removed. On the basis of image signals of the camera (18) corresponding to the shape of the respective part a plurality of criteria are derived such as overall length, overall height, area, axial position, surface waviness, position of center of gravity. Such individual compared with the corresponding individual criteria derived from at least one master part. This means that with a relatively small memory requirement the parts may be reliably identified and more particularly significant fine structures may be distinguished.
    Type: Grant
    Filed: September 30, 1999
    Date of Patent: February 3, 2004
    Assignee: Festo AG & Co.
    Inventors: Ansgar Kriwet, Herbert Hufnagel
  • Patent number: 6678414
    Abstract: An apparatus and method of template fitting for fitting a plurality of templates in correspondence with a gray-scale image, including receiving gray-scale image information of an observed image; defining a window of the gray-scale image information so as to enable a loose-gray-scale fit between the defined window and the plurality of templates; extracting a plurality of pixels of the image information and using the window to which to fit at least one of the plurality of templates. Further, fitting one of the plurality of templates to the defined window within a threshold looseness interval associated with the template wherein a looseness interval between the window of image data and the template is less than the threshold looseness interval.
    Type: Grant
    Filed: February 17, 2000
    Date of Patent: January 13, 2004
    Assignee: Xerox Corporation
    Inventors: Robert P. Loce, Clara Cuciurean-Zapan, Leon C. Williams
  • Patent number: 6665441
    Abstract: A pattern recognition matching processing method and apparatus uses expansion processing with dictionary data as a matching candidate (pattern image). Contraction processing may be performed for the pattern image, and a differential image between the expanded and contracted images can be found. A mask image is prepared based on the differential image, and matching processing of the image containing a character to be recognized with the pattern image is performed with respect to pixels in an area other than the prepared mask image.
    Type: Grant
    Filed: June 29, 2000
    Date of Patent: December 16, 2003
    Assignee: Keyence Corporation
    Inventor: Yoshiaki Nishio
  • Patent number: 6643410
    Abstract: 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: Grant
    Filed: June 29, 2000
    Date of Patent: November 4, 2003
    Assignee: Eastman Kodak Company
    Inventors: Qing Yu, Jiebo Luo, Rajan L. Joshi
  • Patent number: 6621929
    Abstract: A method for matching images is provided that includes the step of providing a template image and an input image. The images include pixels, each pixel having an intensity associated therewith. An energy function formed by weighting a sum of squared differences of data constraints corresponding to locations of both the template image and the input image is minimized to determine estimated geometric and spatially-varying illumination-parameters for the input image with respect to the template image. The estimated geometric and spatially-varying illumination parameters are outputted for further processing.
    Type: Grant
    Filed: June 22, 1999
    Date of Patent: September 16, 2003
    Assignee: Siemens Corporate Research, Inc.
    Inventors: Shang-Hong Lai, Ming Fang
  • Patent number: 6608914
    Abstract: Configuration is made by a feature pattern extracting section 12 for extracting a feature obtainable from a person, a subspace calculating section 14 for calculating a subspace from the feature pattern, a recognition section 16 for effecting recognition using the subspace, a registered information holding section 18 for holding a plurality of the subspaces, and a registered information updating section 20 for updating the registered information using the subspaces. When identifying a person, the effect of aging change is reduced by suppressing time and year changes and keeping the recognition rate high.
    Type: Grant
    Filed: December 11, 1998
    Date of Patent: August 19, 2003
    Assignee: Kabushiki Kaisha Toshiba
    Inventors: Osamu Yamaguchi, Kazuhiro Fukui
  • Patent number: 6606402
    Abstract: A system and method for ascertaining blockage of one or more stencil apertures is provided. An analysis of pixels in an image of the stencil region that includes the aperture is made that includes determining the relative grayscale intensity of pixels acquired from the clean stencil and also the variance among nearby pixels. The grayscale and variance values for each pixel are combined to form a series of histogram groupings or bins, based upon levels. These values are used to compute parameters that represent how the apertures appear under the lighting conditions used to acquire the image, thereby allowing the informing of a decision function that estimates the probability that a given pixel represents unblocked aperture rather than solder paste.
    Type: Grant
    Filed: August 24, 2001
    Date of Patent: August 12, 2003
    Assignee: Cognex Corporation
    Inventor: Adam H. Wagman