Determining Both Similarities And Differences Patents (Class 382/219)
-
Publication number: 20100135568Abstract: A system receives a mask pattern and a first image of at least a portion of a photo-mask corresponding to the mask pattern. The system determines a second image of at least the portion of the photo-mask based on the first image and the mask pattern. This second image is characterized by additional spatial frequencies than the first image.Type: ApplicationFiled: September 19, 2007Publication date: June 3, 2010Inventors: Moshe E. Preil, Alex N. Hegyi, Daniel S. Abrams
-
Patent number: 7729545Abstract: A first image of two images to be compared for similarity is divided into small areas and one small area is selected for calculating the correlation with a second image using a correlative method. Then, the position difference, luminance ratio and similarity in an area where the similarity, which is the square of the correlation value, reaches its maximum, are found. Values based on the similarity are integrated at a position represented by the position difference and the luminance ratio. Similar processing is performed with respect to all the small areas, and at a peak where the maximum integral value of the similarity is obtained, its magnitude is compared with a threshold value to evaluate the similarity. By extracting the small area voted for that peak, it is possible to extract a similar area.Type: GrantFiled: October 16, 2002Date of Patent: June 1, 2010Assignee: Sony CorporationInventors: Mototsugu Abe, Masayuki Nishiguchi
-
Patent number: 7720309Abstract: A similar-image detecting part detects similar image regions similar to one another in a plurality of frame images captured by rolling shutter type exposure. A displacement-vector detecting part detects a displacement vector of each of the similar image regions with respect to a reference position in each of the plurality of frame images. An average calculating part calculates an average of displacement vectors in the plurality of frame images. A correcting part shifts a similar image region in one of the plurality of frame images such that the displacement vector of the similar image region becomes the average calculated by the average calculating part.Type: GrantFiled: December 20, 2006Date of Patent: May 18, 2010Assignee: MegaChips CorporationInventors: Gen Sasaki, Yusuke Nara
-
Patent number: 7711169Abstract: A method of automatically identifying a region of differing intensity in a functional image is described.Type: GrantFiled: June 9, 2008Date of Patent: May 4, 2010Assignee: Accuray IncorporatedInventors: Jay B. West, Michael J. Saracen, John R. Dooley
-
Publication number: 20100104197Abstract: An image processing apparatus reduces two input images to be compared by the predetermined number of times to generate two image groups, extracts a plurality of feature points and a local feature amount of each feature point from these image groups, and determines a combination of feature points in which local feature amounts are similar to each other, between the image groups. Then, the image processing apparatus determines a relation of a reasonable combination, assigns high weights to the reasonable combination, and calculates a similarity degree between the two input images.Type: ApplicationFiled: October 21, 2009Publication date: April 29, 2010Applicant: CANON KABUSHIKI KAISHAInventors: Hidetomo Sohma, Hirotaka Shiiyama, Masahiro Matsushita, Koichi Magai
-
Publication number: 20100100835Abstract: A method, system, and medium are provided for presenting aspects of change associated with a geographic area that has been captured by high-resolution, remotely sensed imagery.Type: ApplicationFiled: October 20, 2008Publication date: April 22, 2010Applicant: CURATORS OF THE UNIVERSITY OF MISSOURIInventors: Matthew Nicholas Klaric, Curtis Herbert Davis, Grant Jason Scott, Chi-Ren Shyu, Brian Christopher Claywell
-
Patent number: 7702183Abstract: Methods and systems for detecting the insertion, removal, and change of objects of interest through the use of imagery are disclosed. In one embodiment, a method includes performing a scene registration including aligning image patterns in the first image to those in the second image; performing a feature content analysis to determine a likelihood of change for each pixel in the first and second images; performing a region identification to group pixels within the first and second images into one or more image regions based upon their likelihood of change; and performing an image region partitioning to prioritize the one or more image regions according to an image region score for each of the one or more image regions, the image region score being indicative of at least one of insertion, removal, and change of an object of interest within the common area of interest.Type: GrantFiled: May 17, 2006Date of Patent: April 20, 2010Assignee: The Boeing CompanyInventors: Ted L. Johnson, Michael G. Neff
-
Patent number: 7689918Abstract: A method is disclosed for displaying a multiplexed property indicator on a network topology map. A coloration designation specification that specifies property-color designations is obtained. A network topology map that includes devices and links having properties that are specified in the coloration designation specification is displayed. A link or device in the map is wrapped with a multiplexed graphical sleeve that includes a color for each property in the coloration designation specification that the link or device has.Type: GrantFiled: July 19, 2005Date of Patent: March 30, 2010Assignee: Cisco Technology, Inc.Inventor: Yvon Sauvageau
-
Publication number: 20100067805Abstract: A device for identifying a traffic sign in an image includes a Hough transformer implemented to identify a plurality of line sections running in different directions through the image in the image or in an edge image derived from same. The device further includes a shape detector implemented to detect a predefined shape in the image or in the edge image derived from same based on the identified line sections. The device apart from that includes a pattern identifier implemented to select an image section corresponding to the detected predefined shape based on the detected predefined shape and to identify a traffic sign based on the selected image section.Type: ApplicationFiled: December 18, 2007Publication date: March 18, 2010Applicant: Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V.Inventor: Frank Klefenz
-
Publication number: 20100063419Abstract: A method of monitoring a patient includes obtaining a first image of an object, obtaining a second image of the object, determining a level of similarity between the first and second images, obtaining a third image of the object, determining a level of similarity between the first and third images, analyzing a time series of values that includes the determined level of similarity between the first and second images and the determined level of similarity between the first and third images, and determining a state of the patient based at least on a result of the act of analyzing.Type: ApplicationFiled: September 5, 2008Publication date: March 11, 2010Applicant: Varian Medical Systems Technologies, Inc.Inventors: Hassan Mostafavi, Sergey Povzner
-
Patent number: 7657119Abstract: Methods and apparatus implementing systems and techniques for adjusting images. In general, in one implementation, the technique includes: receiving input defining an adjustment to be applied to a differential representation of a source image, calculating the differential representation of the source image, producing a structural representation of the source image, the structural representation corresponding to multiple types of contrast in the source image, modifying the differential representation based on the structural representation and the input defining the adjustment, and generating a modified image from the modified differential representation by solving a Poisson differential equation.Type: GrantFiled: July 17, 2007Date of Patent: February 2, 2010Assignee: Adobe Systems IncorporatedInventors: Todor G. Georgiev, Jen-Chan Chien
-
Patent number: 7650014Abstract: An image analysis apparatus includes a unit that accepts plural dynamic image data obtained by imaging a subject to be recognized from positions different from each other, a unit that detects a part to be detected of the subject to be recognized from series of frame image data respectively included in the plural dynamic image data, and a correction unit that compares information of a detection position of the part to be detected from the respective dynamic image data and corrects at least a part of the information of the detection position of the part to be detected from the respective dynamic image data on a basis of a result of comparison.Type: GrantFiled: January 12, 2006Date of Patent: January 19, 2010Assignee: Fuji Xerox Co., Ltd.Inventors: Hitoshi Ikeda, Motofumi Fukui, Takahiko Kuwabara
-
Patent number: 7646934Abstract: A method of detecting an image of a reflective object includes the steps of capturing an exposure image by an image sensor while an LED is ON; down-sampling an exposure image signal from the image sensor to a first digital signal by comparing the level of the first image signal with a first reference level; capturing a dark image by the image sensor while the LED is OFF; down-sampling a second image signal from the image sensor to a second digital signal by comparing the level of the second image signal with a second reference level; computing an image of difference between the exposure image and the dark image by subtracting the second digital signal from the first digital signal; and specifying the image of the reflective object by locating a bright point remaining in the image of difference.Type: GrantFiled: May 27, 2005Date of Patent: January 12, 2010Assignee: SSD Company LimitedInventors: Cheung Chuen Hing, Hiromu Ueshima, Shuhei Kato
-
Patent number: 7647331Abstract: A duplicate image detection system generates an image table that maps hash codes of images to their corresponding images. The image table may group images according to their group identifiers generated from the most significant elements of the hash codes based on significance of the elements in representing an image. The image table thus segregates images by their group identifiers. To detect a duplicate image of a target image, the detection system generates a target hash code for the target image. The detection system then identifies the group of the target image based on the group identifier of the target hash code. After identifying the group identifier, the detection system searches the corresponding group table to identify hash codes that have values that are similar to the target hash code. The detection system then selects the images associated with those similar hash codes as being duplicates of the target image.Type: GrantFiled: March 28, 2006Date of Patent: January 12, 2010Assignee: Microsoft CorporationInventors: Mingjing Li, Bin Wang, Wei-Ying Ma, Zhiwei Li
-
Patent number: 7643966Abstract: 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: GrantFiled: March 8, 2005Date of Patent: January 5, 2010Assignee: Leica Geosystems AGInventors: Jeffrey Minoru Adachi, Mark Damon Wheeler, Jonathan Apollo Kung, Richard William Bukowski, Laura Michele Downs
-
Patent number: 7639890Abstract: The present invention provides for the automatic generation of a series of significant images. One or more representative significant images are used to generate a pattern description. The pattern description can include any information useful to identify an object of interest, or pattern. The pattern description can include a mathematical shape definition of one or more patterns, a search boundary defining an image area to search for matching patterns, and one or more pattern characteristics. The pattern description is compared to one or more images and one or more amounts of match between the pattern description and each image is obtained. The amount(s) of match are then compared to one or more thresholds. If one or more of the amounts of match exceed one or more thresholds or are within an upper and lower threshold window, then the image is automatically selected for inclusion in a series of significant images.Type: GrantFiled: October 25, 2005Date of Patent: December 29, 2009Assignee: General Electric CompanyInventors: Murali Kumaran Kuriathungal, Ashish Dolatrai Vassa
-
Patent number: 7636453Abstract: A video data processing apparatus, that processes video data including a sequence of images, the apparatus including: an object tracker unit configured to detect a presence of one or more objects within an image and to track a detected object across successive images; an identity association unit configured to associate an identity with an object tracked by the object tracker unit; a counter unit configured to, for a first and second identity, count a number of images within which a tracked object associated with the first identity and a tracked object associated with the second identity have both been detected; and a similarity detector unit configured to determine whether two tracked objects are similar in appearance.Type: GrantFiled: May 26, 2005Date of Patent: December 22, 2009Assignee: Sony United Kingdom LimitedInventors: Robert Mark Stefan Porter, Ratna Rambaruth, Simon Dominic Haynes, Jonathan Living, Clive Henry Gillard
-
Patent number: 7636478Abstract: A method is provided that increases throughput and decreases the memory requirements for matching multiple templates in image. The method includes determining a set of inter-template early elimination values that characterize the degree of matching between various templates and the image, at various locations in the image. A later-analyzed template may be rejected as a potential match at a location in the image based on comparing a value characterizing its degree of match at that location to an inter-template early elimination value corresponding to the degree of match of an earlier-analyzed template at that location. The compared values may be determined by different sets of operations, and may be normalized such that they are properly comparable. The inter-template early elimination conditions may be stored in a shared correlation map. The shared correlation map may be analyzed to determine the matching locations for multiple templates in the image.Type: GrantFiled: July 31, 2006Date of Patent: December 22, 2009Assignee: Mitutoyo CorporationInventor: Robert Kamil Bryll
-
Publication number: 20090304288Abstract: 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: ApplicationFiled: August 19, 2009Publication date: December 10, 2009Inventor: Janos Rohaly
-
Patent number: 7630562Abstract: In a technique for video segmentation, classification and summarization based on the singular value decomposition, frames of the input video sequence are represented by vectors composed of concatenated histograms descriptive of the spatial distributions of colors within the video frames. The singular value decomposition maps these vectors into a refined feature space. In the refined feature space produced by the singular value decomposition, the invention uses a metric to measure the amount of information contained in each video shot of the input video sequence. The most static video shot is defined as an information unit, and the content value computed from this shot is used as a threshold to cluster the remaining frames. The clustered frames are displayed using a set of static keyframes or a summary video sequence. The video segmentation technique relies on the distance between the frames in the refined feature space to calculate the similarity between frames in the input video sequence.Type: GrantFiled: August 18, 2006Date of Patent: December 8, 2009Assignee: NEC CorporationInventors: Yihong Gong, Xin Liu
-
Publication number: 20090297044Abstract: There is provided an image processing apparatus including a weight generating section that generates weight data in which a weight of a first region is larger than a weight of a second region, where the first region has a larger difference between a target image and at least one of a plurality of to-be-selected images than the second region, a calculating section that calculates a degree of similarity between the target image and each of two or more of the plurality of to-be-selected images with a difference between the target image and the to-be-selected image being weighted in each region in accordance with the weight data, and an image selecting section that selects, from the two or more to-be-selected images, one or more to-be-selected images that are more similar to the target image by referring to the degrees of similarity of the two or more to-be-selected images.Type: ApplicationFiled: May 14, 2009Publication date: December 3, 2009Applicant: NIKON CORPORATIONInventors: Yuji Kokumai, Hideki Sasaki
-
Publication number: 20090297043Abstract: A pattern scanner is provided for identifying which portions of a security log entry is unrecognizable by currently defined data patterns. Furthermore, an editor is provided for identifying portions of the security log entry that are recognizable by sub-patterns of the currently defined data patterns and portions of the security log entry that are not recognizable. The editor further provides a user interface through which a user may associated sub-patterns with portions of the security log entry that are not recognized. Moreover, a user interface may be provided for defining new sub-patterns that may be applied to recognizing portions of security log entries. A data pattern based on a combination of sub-patterns for the recognized and unrecognized portions of the security log entry may then be automatically generated.Type: ApplicationFiled: May 28, 2008Publication date: December 3, 2009Applicant: International Business Machines CorporationInventors: Heather M. Hinton, Ping Wang, Hang Xiao, Jean X. Yu
-
Patent number: 7627179Abstract: An apparatus includes (a) an image processor which (i) calculates a similarity between first image data of a first partial region in object image data and reference image data, with respect to each pair of a second partial region of the first image data and a third partial region of the reference image data that correspond to each other, (ii) calculates a statistic of a plurality of the calculated similarities, with respect to a plurality of the image pairs, and (iii) recognizes, as a position of an object region in the object image data, a position of the first partial region in the object image data, which has the highest statistic of a plurality of the calculated statistics, and (b) an exposure unit which exposes a substrate to a pattern based on the position of the object region recognized by the image processor.Type: GrantFiled: June 16, 2005Date of Patent: December 1, 2009Assignee: Canon Kabushiki KaishaInventor: Tomoyuki Miyashita
-
Patent number: 7620250Abstract: The invention relates to a method for indexing and retrieving multimedia data. In particular the invention provides a method of comparing at least two sets of multimedia data using shape information in order to provides a dissimilarity measure between the sets. The invention finds use in retrieving images or parts of sequences based on their content in image and video sequence databases.Type: GrantFiled: March 25, 2004Date of Patent: November 17, 2009Assignee: Dublin City UniversityInventors: Thomas Adamek, Noel O'Connor, Sean Marlow, Noel Murphy, Alan Smeaton
-
Patent number: 7606424Abstract: 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: GrantFiled: June 1, 2006Date of Patent: October 20, 2009Assignee: 3M Innovative Properties CompanyInventor: Janos Rohaly
-
Patent number: 7596240Abstract: An object tracking apparatus consisting of an imaging device, a signal processor for processing a video signal generated by the imaging device, and a display for displaying the result of processing performed by the signal processor. An intruding object is detected within a field under monitoring based on a video signal captured by the imaging device, and the imaging device is controlled in response to motions of the intruding object to track the object. The position of a visual field range of the imaging device is calculated, and panning and tilting of the imaging device and an imaging lens are controlled such that the calculated position of the visual field range of the imaging device does not include an imaging prohibited region positioned within the field under monitoring.Type: GrantFiled: July 22, 2004Date of Patent: September 29, 2009Assignee: Hitachi Kokusai Electric, Inc.Inventors: Wataru Ito, Miyuki Fujii
-
Publication number: 20090185717Abstract: In a system for detecting a target object, a similarity determining unit sets a block in a picked-up image, and compares a part of the picked-up image contained in the block with a pattern image data while changes a location of the block in the picked-up image to determine a similarity of each part of the picked-up image contained in a corresponding one of the different-located blocks with respect to the pattern image data. A specifying unit extracts some different-located blocks from all of the different-located blocks. The determined similarity of the part of the picked-up image contained in each of some different-located blocks is equal to or greater than a predetermined threshold similarity. The specifying unit specifies, in the picked-up image, a target area based on a frequency distribution of some different-located blocks therein.Type: ApplicationFiled: January 21, 2009Publication date: July 23, 2009Applicant: DENSO CORPORATIONInventors: Akihiro Watanabe, Noriaki Shirai, Satoshi Osanai
-
Publication number: 20090180698Abstract: A method of and system for verifying a document, the method comprising generating verification information for the document, comparing the verification information with authentic verification information, and identifying differences between the document and an authentic document.Type: ApplicationFiled: January 6, 2009Publication date: July 16, 2009Inventors: Srinivasan RAMANI, Badri Narayanan Ranganathan, Srinivasu Godavari, Anjaneyulu Seetha Rama Kuchibhotla, Nagabhushana Ayyanahalli Matad
-
Patent number: 7561722Abstract: A document layout is adjusted to alter the quality of the document by generating an initial document with a plurality of blocks. A user can manually adjust the parameters of the document. Thereafter, a base quantized quality score is generated for the document based upon the manually changed parameters of the document. The parameters of the document are changed and a first quantized quality score for the document is generated. The first quantized quality score is compared with the base quantized quality score. If the first quantized quality score is closer to a preferred quantized quality score than the bench quantized quality score, the base quantized quality score is changed to equal the first quantized quality score and the parameters of the document to equal the changes. The changed document may be displayed after each comparison so that the user can accept the changed document.Type: GrantFiled: December 14, 2005Date of Patent: July 14, 2009Assignee: Xerox CorporationInventor: Steven J. Harrington
-
Patent number: 7551782Abstract: A system and method for imaging an object, and using reference templates to recognize and enhance object image, including the identification of a template for a specific area of a target object to which images of the object may be compared, the use of the camera on a wireless device to image the target object, comparison of the images of the object within the specific area of the object to the template for that area of the object, identification of the image of the object from the comparison of the image to the template for the specific area of the object, and the storage of the template and the identified image on a data server.Type: GrantFiled: February 14, 2006Date of Patent: June 23, 2009Assignee: DSPV, Ltd.Inventor: Zvi Haim Lev
-
Publication number: 20090148050Abstract: Methods, apparatuses/systems, and software for comparing two drawings to create a compare drawing that includes options for highlighting added and deleted graphic objects, as well as unchanged graphic objects, and comparing one drawing to many or many drawings to many drawings, whether or not the drawings are similar. The invention includes a filtered zoom feature that enables the user to zoom in on a filtered set of graphic objects and to continue to zoom in until a single graphic object is depicted. Detailed information from selected graphic objects can be captured and placed in a list for generating schedule changes, bill of materials, and for other purposes. The invention further includes the ability to detect and report any variances between the drawings, including area differences between drawings depicting physical objects.Type: ApplicationFiled: May 1, 2008Publication date: June 11, 2009Applicant: M.E.P. CAD, Inc.Inventors: Joseph P. Reghetti, Phillip M. Schaeffer
-
Publication number: 20090148051Abstract: Disclosed herein is a method of estimating a geometrical relationship between a first image (101) and a second image (102), wherein the second image (102) includes a noise component. The method determines a location and size of each one of a plurality of image patches (201), based on the noise component included in the second image (102) and correlation information derived from the first image (101). The method then identifies a plurality of first image areas in the first image and a corresponding plurality of second image areas in the second image, based on the location and size of each one of the plurality of image patches. Each first image area of the first image (101) corresponds to a related second image area of the second image (102).Type: ApplicationFiled: December 10, 2008Publication date: June 11, 2009Applicant: CANON KABUSHIKI KAISHAInventors: Tuan Quang Pham, Stephen James Hardy
-
Publication number: 20090116754Abstract: Disclosed are a system and a method for a computerized automatic placement of objects in media files in post-production. Embodiments of the present invention enable the automatic placement of objects which appear in a media file, such as a digital video file. According to one embodiment of the present invention, the disclosed system and method allow the replacement of a specific pattern which appears in a given video file with a new image, in a fully transparent manner. According to embodiments of the present invention the makers of the media file place a designated pattern in the media file, such as a sticker on an object. Embodiments of the present invention enable the replacing of a new image on the designated pattern on the sticker with a new image.Type: ApplicationFiled: November 6, 2007Publication date: May 7, 2009Inventors: Jacob SAMBOURSKY, Uri Rotshtein
-
Publication number: 20090116753Abstract: Apparatus, system, and method to authenticate and identify objects using nanoparticles are described herein. In one embodiment, a computer-readable storage medium includes executable code to: (1) derive an index based on an authentication image of a marking; (2) select a reference image of the marking based on the index; (3) compare the authentication image with the reference image to determine whether the authentication image matches the reference image; and (4) produce an indication of authenticity based on whether the authentication image matches the reference image.Type: ApplicationFiled: September 8, 2006Publication date: May 7, 2009Applicant: UltraDots, Inc.Inventors: John A. Midgley, William M. Pfenninger, John T. Kenney
-
Publication number: 20090110064Abstract: In one embodiment, the method includes determining reference picture index numbers in a reference picture list. The reference picture index numbers increase for reference pictures having a decreasing display order with respect to a picture including the macroblock. The reference picture index numbers increase for reference pictures having an increasing display order with respect to the picture including the macroblock, and the reference picture index numbers of the reference pictures having a decreasing display order are less than the reference picture index numbers of the reference pictures having an increasing display order.Type: ApplicationFiled: September 30, 2008Publication date: April 30, 2009Inventors: Yoon Seong Soh, Byeong Moon Jeon
-
Patent number: 7526143Abstract: A method which, while displacing the field-of-view, allows the image in a target area to be acquired without degradations such as out-of-focus of the image. Plural pieces of images are acquired before and after a target area while displacing the field-of-view. Next, these images are grouped into groups each of which includes several pieces of images, and integrated images on each group basis are created. Moreover, a relational expression is calculated which holds between image displacement quantity calculated by comparing the integrated images with each other and the number of the photographed pieces of images. Furthermore, image displacement quantities between the acquired plural pieces of images are calculated from this relational expression. Finally, these images are corrected by the amounts of these displacement quantities, then being integrated. This process allows reconfiguration of the image in the target area.Type: GrantFiled: April 26, 2006Date of Patent: April 28, 2009Assignee: Hitachi High-Technologies CorporationInventors: Kohei Yamaguchi, Kazuo Aoki, Kenji Obara
-
Patent number: 7508986Abstract: In document recognition processing for accurately recognition a document image at high speed, a shape feature is extracted from a component included in an input document image, and the degree of similarity of shape between the document image and the registered document is calculated based on the extracted shape feature. When it is determined that the component of the document image has color information, the color information is extracted from the document image, thus calculating the degree of similarity of color information from the document image. The degree of similarity of shape is corrected based on the degree of similarity of color information, thus determining that the registered document is similar to the document image.Type: GrantFiled: November 23, 2004Date of Patent: March 24, 2009Assignee: Canon Kabushiki KaishaInventors: Hiroaki Ikeda, Keiko Nakanishi, Taeko Gotoh
-
Patent number: 7502528Abstract: An image matching apparatus includes a numerical analyzing unit that solves an equation of motion numerically. The equation of motion is formulated as an image matching state transition model representing a mapping relation between a source image and a destination image. The equation of motion represents a force applied on each lattice point of the destination image including potential energy force. The numerical analyzing unit calculates the potential energy force, and sets a convergence value of a solution of the equation of motion as a mapping relation between the lattice point of the source image and the lattice point of the destination image based on the numerical analysis.Type: GrantFiled: September 12, 2005Date of Patent: March 10, 2009Assignee: Kabushiki Kaisha ToshibaInventors: Nao Mishima, Go Ito, Masahiro Baba
-
Patent number: 7492947Abstract: 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: GrantFiled: October 8, 2003Date of Patent: February 17, 2009Assignee: Kabushiki Kaisha ToshibaInventor: Kyojiro Nanbu
-
Patent number: 7474768Abstract: An image processing apparatus for processing image data including: appending information generating unit for receiving image data and generating an appending information based on contents of the image data; correlativity judgment unit for judging correlativity between the received image data and another image data, including the appending information based on the appending information; and correlativity information assignment unit for assigning correlativity information indicating the correlativity to both the received image data and the other image data.Type: GrantFiled: June 24, 2003Date of Patent: January 6, 2009Assignee: Fujifilm CorporationInventor: Shuichi Ohtsuka
-
Patent number: 7463773Abstract: An initial search method uses the input image and the template to create an initial search result output. A high precision match uses the initial search result, the input image, and the template to create a high precision match result output. The high precision match method estimates high precision parameters by image interpolation and interpolation parameter optimization. The method also performs robust matching by limiting pixel contribution or pixel weighting. An invariant high precision match method estimates subpixel position and subsampling scale and rotation parameters by image interpolation and interpolation parameter optimization on the log-converted radial-angular transformation domain.Type: GrantFiled: November 26, 2003Date of Patent: December 9, 2008Assignee: DRVision Technologies LLCInventors: Shih-Jong J. Lee, Seho Oh
-
Patent number: 7460737Abstract: Digital image data including discrete photographic images of a variety of different subjects, times, and so forth, are collected and analyzed to identify specific features in the photographs. In an embodiment of the invention, distinctive markers are distributed to aid in the identification of particular subject matter. Facial recognition may also be employed. The digital image data is maintained in a database and quarried in response to search requests. The search requests include criteria specifying any feature category or other identifying information, such as date, time, and location that each photograph was taken, associated with each photograph. Candidate images are provided for review by requesters, who may select desired images for purchase or downloading.Type: GrantFiled: February 10, 2005Date of Patent: December 2, 2008Assignee: Hoshiko LLCInventor: Gary Stephen Shuster
-
Patent number: 7450262Abstract: 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: GrantFiled: September 23, 2004Date of Patent: November 11, 2008Assignee: Canon Kabushiki KaishaInventor: Hiroaki Ikeda
-
Patent number: 7450759Abstract: A digital pictorial book system for searching for and providing to a user with an explanation of an object captured by an image capturing module includes an image capturing module for taking an image; a main object selecting module for selecting a main object out of the image; a feature extracting module for extracting a feature of the main object; an image database selecting module for selecting an image database which stores a feature of a kind extracted by the feature extracting module out of a plurality of image databases which store explanations of objects corresponded to a plurality kinds of different features of the objects; and an explanation searching module for searching for the explanation of the main object in the selected image database.Type: GrantFiled: February 9, 2005Date of Patent: November 11, 2008Assignee: FUJIFILM CorporationInventor: Yoshimitsu Kudoh
-
Patent number: 7450785Abstract: A method of comparing images is disclosed herein. The images may be represented by image data comprising a plurality of image data values. An embodiment of the method may comprise determining at least one image data value representative of at least one first portion of a first image. The method may further comprise determining at least one second image data value representative of at least one first portion of a second image. The at least one first portion of the first image and the at least one first portion of the second image are located in substantially similar regions of the first image and the second image. The at least one first image data value is compared to the at least one second image data value. The first image is similar to the second image if the at least one first image data value is within a preselected amount of the at least one second image data value.Type: GrantFiled: January 22, 2003Date of Patent: November 11, 2008Assignee: Hewlett-Packard Development Company, L.P.Inventors: William R. Haas, Kirk S. Tecu, David W. Boll
-
Publication number: 20080267512Abstract: A VI production system and method for automatic review of variable imaging job output includes a VI interpreter includes raster image processing for producing electronic output document images based on a variable imaging job included in a VI job stream. A proofing process includes obtaining sample document images from the output document images, and for each obtained sample document image, performing a review procedure. The review procedure includes comparing the obtained sample document image to a corresponding expected document image selected from the expected database to determine differences between the obtained sample document image and the corresponding expected document image. Based on at least one difference being determined, the differences are resolved by displaying the obtained sample document image on the user interface, indicating in the displayed sample document image each of the differences, and performing a difference procedure based on an operator input.Type: ApplicationFiled: April 26, 2007Publication date: October 30, 2008Inventors: Paul R. Austin, Philip C. Rose
-
Patent number: 7440619Abstract: An image matching method includes setting first and second lattices to first and second images respectively, computing potential force to each second lattice point of the second lattice by a gradient of an image correlation potential energy based on a position of each first lattice point and pixel thereof and a position of the second lattice point and pixel thereof, computing elasticity force to the second lattice point from elasticity energy between the second and adjacent lattice points, computing frictional force occurring at the second lattice point, performing a numerical analysis of an equation of motion regarding the second lattice point and based on the potential force, elasticity force and frictional force to obtain a convergence state of the second lattice points, and adding a new lattice point between an adjacent lattice point pair of second lattice points according to a distance between the adjacent lattice point pair.Type: GrantFiled: February 16, 2006Date of Patent: October 21, 2008Assignee: Kabushiki Kaisha ToshibaInventors: Nao Mishima, Goh Itoh, Masahiro Baba
-
Patent number: 7440617Abstract: A mobile terminal reads a read manuscript as image data. A character recognition block performs character recognition from the image data, which is read, on the basis of a threshold for judgement of unrecognizableness. A character recognition result is transmitted to a central control unit, or the threshold for judgement of unrecognizableness is received from the central control unit in a threshold receiver. On the other hand, the central control unit receives the result of character recognition from the mobile terminal, or transmits the threshold for judgement of unrecognizableness from a threshold transmitter to the mobile terminal. Furthermore, the central control unit controls the threshold for judgement of unrecognizableness with a threshold controller.Type: GrantFiled: March 17, 2005Date of Patent: October 21, 2008Assignee: Canon Kabushiki KaishaInventor: Kitahiro Kaneda
-
Patent number: 7436989Abstract: A digitized writing is recorded in a digitized writing record including at least the position of each point of a writing in coordinates relative to a coordinate of a previous point thereof and time. The digitized writing record may be converted to image format.Type: GrantFiled: February 2, 2004Date of Patent: October 14, 2008Assignee: Avante International Technology, Inc.Inventors: Kevin Kwong-Tai Chung, Xiaoming Shi
-
Publication number: 20080247651Abstract: An object recognition apparatus sets each of keypoints extracted from a typical image and one of keypoints extracted from an input image, having scale invariant features similar to each other, as a typical corresponding point and an object corresponding point matching with each other, and produces a position vector directed from a typical reference point of the typical image to each typical keypoint. The apparatus determines a position of an object reference point in the input image from a position of each object corresponding point and the vector of the typical corresponding point matching with the object corresponding point. When the positions of the object reference point are concentrated, the apparatus judges that an object picture having the object corresponding points in the input image matches with the typical image, and the apparatus recognizes the picture as an object indicated by the typical image.Type: ApplicationFiled: April 7, 2008Publication date: October 9, 2008Applicants: DENSO CORPORATION, Hironobu FujiyoshiInventors: Masanari Takaki, Hironobu Fujiyoshi