Where The Object Is A Character, Word, Or Text Patents (Class 382/292)
  • Patent number: 9298997
    Abstract: Where the recognition of small characters (e.g., text, numbers or symbols) expressed in substantially large images is desired, the recognition process may be facilitated by identifying a signature or a pattern of marked identifiers (e.g., bar codes) within the image, and determining where such characters are typically located in relation to the signature or pattern of identifiers. Because the recognition of characters within images typically occupies a substantial amount of a computer's processing capacity, focusing a recognition technique on portions where such characters are frequently located within an image that includes the signature or pattern, and not on the entire image, the time required in order to process an image in order to recognize such characters may be markedly reduced.
    Type: Grant
    Filed: March 19, 2014
    Date of Patent: March 29, 2016
    Assignee: Amazon Technologies, Inc.
    Inventor: Ned Lecky
  • Patent number: 8995780
    Abstract: A method for creating a binary mask image from an inputted digital image of a scanned document, including the steps of creating a binarized image by binarizing the inputted digital image, detecting first text regions representing light text on a dark background, and inverting the first text regions, such that the inverted first text regions are interpretable in the same way as dark text on a light background. A method for comparing in a binary image a first pixel blob with a second pixel blob to determine whether they represent matching symbols, including the steps of detecting a line in one blob not present in the other and/or determining if one of the blobs represents an italicized symbol where the other does not.
    Type: Grant
    Filed: December 23, 2013
    Date of Patent: March 31, 2015
    Assignee: I.R.I.S.
    Inventors: Michel Dauw, Pierre De Muelenaere
  • Patent number: 8929656
    Abstract: Provided is a method of detecting important information from a moving picture. The method includes: detecting first candidate areas that are presumed to include important information in a plurality of moving picture frames by using stop edge information, which is edge information overlapped at a same position throughout the plurality of moving picture frames, from among edge information in at least two received moving picture frames; determining second candidate areas by performing grouping on the stop edge information according to a position of the stop edge information in the first candidate areas; analyzing the second candidate areas determined in the at least two moving picture frames; and detecting important information areas from each of the at least two moving picture frames based on the analysis.
    Type: Grant
    Filed: March 24, 2010
    Date of Patent: January 6, 2015
    Assignees: Samsung Electronics Co., Ltd., Soongsil University Research Consortium techno-PARK
    Inventors: Jin-guk Jeong, Kee-chul Jung, Dong-keun Lee, Min-kyu Jung, Sung-kuk Chun
  • Patent number: 8879827
    Abstract: Systems and methods may include utilizing a structured light pattern that may be, among other things, decoded in the three directions (e.g., vertical, horizontal, and diagonal). In one example, the method may include detecting a first feature of a target image in a return image, designating a feature type of the first feature, and an index with the letter, wherein the index is associated with the pattern slide. The method may also include calculating a horizontal position in the pattern slide of the first feature, calculating a vertical position in the pattern slide of the first feature, and calculating a depth of the first feature.
    Type: Grant
    Filed: June 29, 2012
    Date of Patent: November 4, 2014
    Assignee: Intel Corporation
    Inventors: Ziv Aviv, David Stanhill, Ron Ferens, Roi Ziss
  • Patent number: 8849031
    Abstract: A method embodiment herein begins by capturing a source image. The source image is segmented into first planes. The first planes can each comprise a mask plane and foreground plane combination. The binary images in the first planes are structurally analyzed to identify different regions of text, tables, handwriting, line art, equations, etc., using a document model that has information of size, shape, and spatial arrangement of possible regions. Then, the method extracts (crops out) these regions from the foreground plane to create second mask/foreground plane pairs. Thus, the method creates “second” planes from the first planes, so that a separate second plane is created for each of the regions. Next, tags are associated with each of the second planes (to create tagged mask/foreground plane pairs) and the second planes and associated tags are combined into a mixed raster content (MRC) document.
    Type: Grant
    Filed: October 20, 2005
    Date of Patent: September 30, 2014
    Assignee: Xerox Corporation
    Inventor: John C. Handley
  • Patent number: 8830241
    Abstract: Conversion of text-based images to vector graphics (VG) is disclosed. The text-based images may include images of equations, custom typefaces, or other types of text that may not be included in a font selection of an optical character recognition (OCR) device or an application stored on a viewing device. A textual image may be converted from a raster graphics (RG) image to a VG image, which may enable resizing and alignment of the VG image with body text. In some aspects, the server may determine a body size of a reference character in the VG image. The server may determine a baseline of the VG image that may be used to align the image with the body text.
    Type: Grant
    Filed: November 30, 2009
    Date of Patent: September 9, 2014
    Assignee: Amazon Technologies, Inc.
    Inventor: Martin Gorner
  • Patent number: 8787702
    Abstract: Methods and apparatus for processing one or more images, e.g., images representing pages including text, to detect and in some instances correct the orientation of the page. In some embodiments the methods and apparatus for processing image data comprise generating a histogram of foreground pixel counts corresponding to a current line of text of the image being processed with the foreground pixel counts corresponding to different rows of pixels corresponding to the current line of text and identifying based on statistical analysis of the generated histogram whether the current page of text is oriented in an inverted or non-inverted position. In some embodiments analysis is performed on multiple lines of text with cumulative statistics being used in to determine the orientation of the page. In some embodiments, a page whose orientation is determined to be upside down is re-oriented to be right-side up.
    Type: Grant
    Filed: December 7, 2012
    Date of Patent: July 22, 2014
    Assignee: Accusoft Corporation
    Inventor: William Douglas Withers
  • Patent number: 8755629
    Abstract: A computer implemented system and method for composing a formatted text input to improve legibility, readability and/or print economy while preserving the format of the text input and satisfying any user selected aesthetic constraints. An information measure (IM) is assigned to each character in a language unit. Multiple different IMs are assigned to each character and combined to form a combined IM (CIM) for each character indicating the predictability of that character to differentiate the language unit from other language units. The process is repeated for at least a plurality of language units and typically until all the text input has been analyzed and information measures assigned to all of the characters.
    Type: Grant
    Filed: September 30, 2012
    Date of Patent: June 17, 2014
    Assignee: Language Technologies, Inc.
    Inventors: Thomas G. Bever, Christopher D. Nicholas, Roeland Hancock, Keith W. Alcock, Steven M. Jandreau
  • Patent number: 8730244
    Abstract: A device includes a character-data rotating section that rotates a regular-position character by a predetermined angle with respect to a reference point that is the center point of the background area of the regular-position character by using regular-position character data having a rotation angle of 0° and a center-point matching processing section that horizontally and/or vertically enlarges the background area of the rotated character data to cause the center point of the rotated character and the center point of BMP data to match each other even with respect to rotated character data. Thus, when multiple pieces of character data are arranged so that the center points thereof lie on a reference line, not only are the center points of the characters aligned along the reference line, but also bottom portions of the characters aligned with respect to the reference line.
    Type: Grant
    Filed: July 1, 2008
    Date of Patent: May 20, 2014
    Assignee: Alpine Electronics, Inc.
    Inventor: Noboru Yamazaki
  • Patent number: 8718610
    Abstract: A communication terminal includes a transceiver and a controller. The transceiver receives electronic messages from another communication terminal. The controller responds to receipt of each of the messages by examining content of the message according to at least one defined rule and to control sound characteristics of an alert tune that is played through a speaker responsive to the examined message content. The controller may attempt to match text from the message to a stored list of words and/or phrases, and to control the sound characteristics of the alert tune in response to an outcome of the matching.
    Type: Grant
    Filed: December 3, 2008
    Date of Patent: May 6, 2014
    Assignees: Sony Corporation, Sony Mobile Communications AB
    Inventors: Erik Johan Vendel Backlund, Andreas Kristensson, Pär-Anders Aronsson
  • Patent number: 8682648
    Abstract: A set of ordered characters is received in association with information specifying the locations of the characters within the image of the document. Language-conditional character probabilities for each character are determined based on a set of language models and the ordering of the characters. Neighbor characters associated with a target character are identified based on the locations of the characters. Language-conditional character probabilities associated with the neighbor characters and language-conditional character probabilities associated with the target character are combined to generate a local language-conditional likelihood associated with the target character, the local language-conditional likelihood representing a concordance of the target character to a language model.
    Type: Grant
    Filed: April 16, 2013
    Date of Patent: March 25, 2014
    Assignee: Google Inc.
    Inventor: Ashok Popat
  • Patent number: 8675260
    Abstract: According to one embodiment, the image processing apparatus includes a printing control unit, an image reading unit, an extracting unit, a difference image extracting unit, and a determination unit. The printing control unit controls printing of a plurality of pages on one sheet of paper according to a print setting information which indicates a printing form, and printing of a code indicating the print setting information on the paper. The image reading unit read the paper. The extracting unit extracts the code from the read image. The difference image extracting unit extracts a difference image between the printed image and the read image.
    Type: Grant
    Filed: March 14, 2012
    Date of Patent: March 18, 2014
    Assignee: Toshiba Tec Kabushiki Kaisha
    Inventors: Shigeo Uchida, Taira Ashikawa, Satoshi Oyama, Katsuhito Mochizuki
  • Patent number: 8666185
    Abstract: A first aspect of the invention relates to a method for creating a binary mask image from an a inputted digital image of a scanned document, comprising the steps of creating a binarized image by binarizing the inputted digital image, detecting first text regions representing light text on a dark background, and inverting the first text regions, such that the inverted first text regions are interpretable in the same way as dark text on a light background. A second aspect of the invention relates to a method for comparing in a binary image a first pixel blob with a second pixel blob to determine whether they represent matching symbols, comprising the steps of detecting a line in one blob not present in the other and/or determining if one of the blobs represents an italicized symbol where the other does not.
    Type: Grant
    Filed: November 17, 2011
    Date of Patent: March 4, 2014
    Assignee: I.R.I.S.
    Inventors: Michel Dauw, Pierre Demuelenaere
  • Patent number: 8655107
    Abstract: An image processing apparatus includes an acquiring unit, a specifying unit, a search unit and a difference extracting unit. The acquiring unit acquires a first image and a second image. The specifying unit specifies one or more image areas included in the first image. The search unit searches the second image for an image area corresponding to each of the one or more image areas specified by the specifying unit. The difference extracting unit extracts a difference between the corresponding image area obtained by the search unit and each of the one or more image areas specified by the specifying unit.
    Type: Grant
    Filed: May 8, 2009
    Date of Patent: February 18, 2014
    Assignee: Fuji Xerox Co., Ltd.
    Inventor: Hitoshi Okamoto
  • Patent number: 8639032
    Abstract: The present invention discloses methods of archiving and optimizing lectures, presentations and other captured video for playback, particularly for blind and low vision individuals. A digital imaging device captures a preselected field of view that is subject to periodic change such as a whiteboard in a classroom. A sequence of frames is captured. Frames associated with additions or erasures to the whiteboard are identified. The Cartesian coordinates of the regions of these alterations within the frame are identified. When the presentation is played back, the regions that are altered are enlarged or masked to assist the low vision user. In another embodiment of the invention, the timing of the alterations segments the recorded audio into chapters so that the blind user can skip forward and backward to different sections of the presentation.
    Type: Grant
    Filed: August 29, 2008
    Date of Patent: January 28, 2014
    Assignee: Freedom Scientific, Inc.
    Inventors: Garald Lee Voorhees, Robert Anders Steinberger, Ralph Ernest Ocampo
  • Patent number: 8621349
    Abstract: A system for processing a visual capture operation as described. The system receives an indication of a visual capture operation performed from a rendered document. The indication specifies both a text sequence capture As part of the capture operation and a supplemental marking captured as part of the capture operation. The system determines an action to perform in response to receiving the indication, based both upon the text sequence specified in the indication and the supplemental markings specified by the indication.
    Type: Grant
    Filed: October 5, 2010
    Date of Patent: December 31, 2013
    Assignee: Google Inc.
    Inventors: Martin T. King, Dale L. Grover, Clifford A. Kushler, James Q. Stafford-Fraser
  • Patent number: 8620079
    Abstract: Various embodiments of the invention provide systems and methods for extracting information from digital documents, including physical documents that have been converted to digital documents. For example, some embodiments are configured to extract information from a field in a digital document by identifying a block of tokens before (i.e., a prior block) and a block of tokens after (i.e., a post block) the field from which the information is to be extracted, where both the prior block and post block are known to be associated with the field type of the field (e.g., name, address, phone number, etc.).
    Type: Grant
    Filed: May 10, 2011
    Date of Patent: December 31, 2013
    Assignee: First American Data Tree LLC
    Inventors: Christopher Lawrence Rubio, Vladimir Sevastyanov
  • Patent number: 8577155
    Abstract: A system for duplicate text recognition includes a first means for dividing an electronic text into a plurality of phrase segments; a second means for converting each of the phrase segments into a unique and fixed-length bit string; a third means for storing a plurality of groups of the bit strings, each group of bit strings (string group) including a plurality of bit strings respectively corresponding to the phrase segments in a particular electronic text; and a fourth means for determining whether a predefined similarity between any two string groups in the third means reaches a first threshold, and for determining the two electronic texts corresponding to the two string groups are duplicate texts if the predefined similarity between the two string groups reaches the first threshold.
    Type: Grant
    Filed: November 17, 2009
    Date of Patent: November 5, 2013
    Assignee: Wisers Information Limited
    Inventors: Tat Ming Damein Wu, Ka Yeung Sin
  • Patent number: 8564826
    Abstract: To shift an image in order to prevent the image from overlapping with a finishing position, the amount of shift for preventing the overlap may be increased and a desired result of layout may not be obtained. In addition, if the image is not shifted in order to obtain the desired result of layout, the image may overlap with the finishing position and toner or the like may come off. When it is determined that a position where the finishing process is to be executed overlaps with a content data placement area, an avoidance area where printing is not performed is placed at a position in which the position where the finishing process is to be executed overlaps with the content data placement area without changing the position and size of the content data placement area.
    Type: Grant
    Filed: August 4, 2010
    Date of Patent: October 22, 2013
    Assignee: Canon Kabushiki Kaisha
    Inventor: Hidekazu Morooka
  • Patent number: 8467608
    Abstract: A method and an apparatus for character string recognition may be provided that enables prevention of a decrease in recognition accuracy for a character string even when distortion of an image appears in a direction perpendicular to a medium transfer direction.
    Type: Grant
    Filed: March 31, 2008
    Date of Patent: June 18, 2013
    Assignee: Nidec Sankyo Corporation
    Inventor: Hiroshi Nakamura
  • Patent number: 8467614
    Abstract: The present invention provides a method for an Optical Character Recognition (OCR) system providing recognition of characters that are partly hidden by crossing outs due to for example an imprint of a stamp, handwritten signatures, etc. The method establishes a set of template images of certainly recognized characters from the image of the text being processed by the OCR system, wherein the effect of the crossed out section is modelled into the template images before comparing these images with the image of a visually impaired crossed out character. The modelled template image having the highest similarity with the visually impaired crossed out character is the correct identification for the visually impaired character instance.
    Type: Grant
    Filed: November 21, 2008
    Date of Patent: June 18, 2013
    Assignee: Lumex AS
    Inventors: Knut Tharald Fosseide, Hans Christian Meyer
  • Patent number: 8451346
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, are described for rendering a mosaic from digital images using information about location and orientation of an image capturing device, and further about optics settings for the image capturing device when the digital images were captured. In one aspect, methods include generating respective virtual image sheets for frames captured from different camera locations and different camera orientations. Generating the virtual image sheets includes projecting texture maps of the captured frames over wire frames corresponding to optics settings of the camera. The methods further include positioning the generated virtual image sheets at locations and orientations within a viewing space that correspond to the different camera locations and the different orientations. The methods also include rendering the positioned virtual image sheets into a mosaic viewed from a reference point of the viewing space.
    Type: Grant
    Filed: June 30, 2010
    Date of Patent: May 28, 2013
    Assignee: Apple Inc.
    Inventor: Robert Mikio Free
  • Patent number: 8446432
    Abstract: Methods and apparatus for presenting image data to include a graphic element. In one embodiment a method includes acquiring image data from a display buffer of a device, analyzing the image data to identify active and passive regions of the image data and ranking passive regions to determine a confidence measure for each passive region. The method may further include modifying the image data for display on the device to include a graphic element, wherein the graphic element is presented in a passive region based on the ranking.
    Type: Grant
    Filed: July 12, 2011
    Date of Patent: May 21, 2013
    Assignee: Sony Corporation
    Inventors: Suranjit Adhikari, Steven Friedlander
  • Patent number: 8339642
    Abstract: An apparatus, method, and system for processing character data is provided, which selects a format of the character data to be used for generating print data. When a user instruction for printing character data according to character command data specifying the output of the character data is received, the format of the character data is selected based on the character command data.
    Type: Grant
    Filed: February 12, 2009
    Date of Patent: December 25, 2012
    Assignee: Ricoh Company, Ltd.
    Inventor: Akiyoshi Ono
  • Patent number: 8331706
    Abstract: A first aspect of the invention relates to a method for creating a binary mask image from an a inputted digital image of a scanned document, comprising the steps of creating a binarized image by binarizing the inputted digital image, detecting first text regions representing light text on a dark background, and inverting the first text regions, such that the inverted first text regions are interpretable in the same way as dark text on a light background. A second aspect of the invention relates to a method for comparing in a binary image a first pixel blob with a second pixel blob to determine whether they represent matching symbols, comprising the steps of detecting a line in one blob not present in the other and/or determining if one of the blobs represents an italicized symbol where the other does not.
    Type: Grant
    Filed: November 17, 2011
    Date of Patent: December 11, 2012
    Assignee: I.R.I.S.
    Inventors: Michel Dauw, Pierre Demuelenaere
  • Patent number: 8320629
    Abstract: A system and method, which enable precise and automatic identification of characters, perform and calibrate data verification to ensure data reliability. The system can process these identified characters, such as override adverse conditions, adjusting and correcting unclear characters and their images.
    Type: Grant
    Filed: February 11, 2008
    Date of Patent: November 27, 2012
    Assignee: Hi-Tech Solutions Ltd.
    Inventors: Yoram Hofman, Alexandra Margolin
  • Patent number: 8306356
    Abstract: A computer implemented system, plug-in application and method for composing a formatted text input to improve legibility, readability and/or print economy while preserving the format of the text input and satisfying any user selected aesthetic constraints. This is accomplished by reading in blocks of text input having defined characters including letters and punctuation in a given input format. A language unit such as a lexical or sub-lexical unit, a subset of punctuation or another defined unit for a particular language is examined and an information measure (IM) is assigned to each character in the language unit indicating the predictability of that character to differentiate the language unit from other language units. Typically, multiple different IMs are assigned to each character and combined to form a combined IM (CIM).
    Type: Grant
    Filed: September 23, 2008
    Date of Patent: November 6, 2012
    Assignee: Language Technologies, Inc.
    Inventors: Thomas G Bever, Christopher D Nicholas, Roeland Hancock, Keith W Alcock, Steven M Jandreau
  • Patent number: 8238609
    Abstract: A system and a method are disclosed for generating video. Object information is received. A path of motion of the object relative to a reference point is generated. A series of images and ground for a reference frame are generated from the ground truth and the generated path. A system and a method are disclosed for generating an image. Object information is received. Image data and ground truth may be generated using position, the image description, the camera characteristics, and image distortion parameters. A positional relationship between the document and a reference point is determined. An image of the document and ground truth are generated from the object information and the positional relationship and in response to user specified environment of the document.
    Type: Grant
    Filed: June 24, 2011
    Date of Patent: August 7, 2012
    Assignee: Ricoh Co., Ltd.
    Inventors: Andrew Lookingbill, Emilio Antunez, Berna Erol, Jonathan J. Hull, Qifa Ke
  • Patent number: 8212833
    Abstract: A method for entering secure data at an input device includes displaying a graphical input region having input elements, such as a number keypad, and receiving selections of the input elements via a display selection device, such as a mouse or touch screen. An attribute of the displayed graphical input region is changed so that inputs by the display selection device change for the same data input. Examples include changing the position, size and/or layout of the input elements and/or graphical input region. The graphical input elements may instead be provided with two characters so that typing one character results in input of the corresponding character, and then changing the association of the characters on the displayed input elements.
    Type: Grant
    Filed: February 24, 2009
    Date of Patent: July 3, 2012
    Assignee: IPDEV Co.
    Inventor: James B. Kargman
  • Patent number: 8208737
    Abstract: The present invention relates to systems and methods for identifying captions associated with images in media material. A captioner includes a selector module and a caption identifier module. The selector module identifies text-blocks potentially associated with images in the media material. The caption identifier module identifies which text-blocks are captions associated with images in the media material, based on the textual and proximity features of the text-block and the images. The captioner may also include a caption feedback module to modify the determining of the caption identifier module.
    Type: Grant
    Filed: April 17, 2009
    Date of Patent: June 26, 2012
    Assignee: Google Inc.
    Inventor: Eugene Ie
  • Patent number: 8200043
    Abstract: A system and method for character recognition with document orientation determination is shown. The method is a detection of simple page orientation based on a limited version of character recognition. The method includes binairizing an input image which has a plurality of alphanumeric characters with a first orientation. The method continues with extracting the connected components and determining a second orientation where the second orientation is based on a 90° turn clockwise or counterclockwise or, in the alternative, no turn from the first orientation. The second orientation will result in a 180° variance from the proper orientation or it will be the proper orientation. The method continues with implementing a limited version of optical character recognition for an analysis of a character and determining if that second orientation is upside down, based at least in part on the analysis. This method generally uses the character “i” for analysis.
    Type: Grant
    Filed: May 1, 2008
    Date of Patent: June 12, 2012
    Assignee: Xerox Corporation
    Inventors: Zhigang Fan, Michael R. Campanelli, Dennis Venable
  • Patent number: 8189961
    Abstract: An image deskew system and techniques are used in the context of optical character recognition. An image is obtained of an original set of characters in an original linear (horizontal) orientation. An acquired set of characters, which is skewed relative to the original linear orientation by a rotation angle, is represented by pixels of the image. The rotation angle is estimated, and a confidence value may be associated with the estimation, to determine whether to deskew the image. In connection with rotation angle estimation, an edge detection filter is applied to the acquired set of characters to produce an edge map, which is input to a linear hough transform filter to produce a set of output lines in parametric form. The output lines are assigned scores, and based on the scores, at least one output line is determined to be a dominant line with a slope approximating the rotation angle.
    Type: Grant
    Filed: June 9, 2010
    Date of Patent: May 29, 2012
    Assignee: Microsoft Corporation
    Inventors: Djordje Nijemcevic, Sasa Galic
  • Patent number: 8189960
    Abstract: An image processing apparatus includes: an imaging information calculation unit acquiring a first image and higher-resolution second images, and calculating coordinate positions of the second images to the first image and differences in imaging direction between second cameras and a first camera; an eyepoint conversion unit generating eyepoint conversion images obtained by converting the second images based on the differences in imaging direction so that eyepoints of the second cameras coincide with an eyepoint of the first camera and matching the first image with the eyepoint conversion images to calculate phase deviations of the eyepoint conversion images from the first image; and an image synthesizing unit extracting high-frequency images, having frequency components higher than or equal to a predetermined frequency band, from the second images, and pasting the high-frequency images at the coordinate positions in correspondence with the first image to eliminate the phase deviations to generate a synthesize
    Type: Grant
    Filed: June 24, 2009
    Date of Patent: May 29, 2012
    Assignee: Sony Corporation
    Inventors: Tetsujiro Kondo, Tetsushi Kokubo, Kenji Tanaka, Hitoshi Mukai, Hirofumi Hibi, Kazumasa Tanaka, Hiroyuki Morisaki
  • Patent number: 8149432
    Abstract: An information processing apparatus that can be connected to an image-forming apparatus, a method, and a program used for the information processing apparatus are disclosed. The information processing apparatus comprises a control unit for controlling print-setting information set for document data to be printed, a recognition unit for recognizing information about a first function specified by the print-setting information by translating the print-setting information controlled by the control unit, an obtaining unit for obtaining information about a second function of the image-forming apparatus connected to the information processing apparatus, a determination unit for determining whether or not the image-forming apparatus can perform the first function recognized by the recognition unit based on the second-function information obtained by the obtaining unit, and a modification unit for modifying the print-setting information controlled by the control unit based on the determination result.
    Type: Grant
    Filed: October 19, 2010
    Date of Patent: April 3, 2012
    Assignee: Canon Kabushiki Kaisha
    Inventors: Junichiro Kizaki, Satoshi Nishikawa
  • Patent number: 8121412
    Abstract: A number of regions and partitions may be created based on input handwritten atoms and a grammar parsing framework. Productions for tabular structures may be added to the grammar parsing framework to produce an extended grammar parsing framework. Each of the regions may be searched for a tabular structure. Upon finding a tabular structure, a type of tabular structure may be determined. Configuration partitions may be created, based on the added productions, and added to the created partitions. A set of configuration regions may be created based on the configuration partitions and added to the created regions. The productions for tabular structures and productions of the grammar parsing framework may be applied, as rewriting rules, to the atoms to produce possible recognition results. A best recognition result may be determined and displayed. A mechanism for correcting misrecognition errors, which may occur while recognizing tabular structures, may be provided.
    Type: Grant
    Filed: June 6, 2008
    Date of Patent: February 21, 2012
    Assignee: Microsoft Corporation
    Inventors: Goran Predovic, Bodin Dresevic
  • Patent number: 8086039
    Abstract: A method and system generates fine-grained fingerprints for identifying content in a rendered document. It includes applying image-based techniques to identify patterns in a document rendered by an electronic document rendering system, irrespective of a file format in which the rendered document was electronically created. The applying of the image-based technique includes identifying candidate keypoints at locations in a local image neighborhood of the document, and combining the locations of the candidate keypoints to form a fine-grained fingerprint identifying patterns representing content in the document.
    Type: Grant
    Filed: February 5, 2010
    Date of Patent: December 27, 2011
    Assignee: Palo Alto Research Center Incorporated
    Inventor: Doron Kletter
  • Patent number: 8068684
    Abstract: A first aspect of the invention relates to a method for creating a binary mask image from an a inputted digital image of a scanned document, comprising the steps of creating a binarized image by binarizing the inputted digital image, detecting first text regions representing light text on a dark background, and inverting the first text regions, such that the inverted first text regions are interpretable in the same way as dark text on a light background. A second aspect of the invention relates to a method for comparing in a binary image a first pixel blob with a second pixel blob to determine whether they represent matching symbols, comprising the steps of detecting a line in one blob not present in the other and/or determining if one of the blobs represents an italicized symbol where the other does not.
    Type: Grant
    Filed: May 4, 2007
    Date of Patent: November 29, 2011
    Assignee: I.R.I.S.
    Inventors: Michel Dauw, Pierre Demuelenaere
  • Patent number: 8049905
    Abstract: A computer readable recording medium bearing a printer driver program for controlling a print device, which is installed in a print job data processing apparatus constituting a printing system together with the printing device, the printer driver program comprising computer executable instructions of; receiving a print job data from an application program which has a print command; analyzing the received print job data from the application program to identify respective objects included in the page description language data; calculating a position where each object is arranged on a printable area designated depending on output paper size; and modifying the object to allow the object to be accommodated within the printable area, thereby accomplishing a correct print operation such that a print region designated by a user is accommodated to a predetermined output paper size without depending on a function of an application.
    Type: Grant
    Filed: May 27, 2003
    Date of Patent: November 1, 2011
    Assignee: Minolta Co., Ltd.
    Inventor: Yukinori Matsumoto
  • Patent number: 8041113
    Abstract: A first area extracting unit extracts a first document area from document image data by dividing the document image data in units of a document area. A language determining unit determines a type of a language used in the document image data. A second area extracting unit extracts a second document area by dividing or combining the first document area based on a rule corresponding to the type of the language determined by the language determining unit.
    Type: Grant
    Filed: September 12, 2006
    Date of Patent: October 18, 2011
    Assignee: Ricoh Company, Ltd.
    Inventor: Hirobumi Nishida
  • Patent number: 8023725
    Abstract: A method for identifying a predefined graphic symbol having a plurality of graphical characters. The method comprises the following steps: a) receiving a digital image having a plurality of pixels depicting a scene, b) identifying a plurality of first groups of contiguous pixels in the proximity of one another, members of each one the first group having a first common pixel defining property, and c) identifying at least one of the plurality of first groups as one of the plurality of graphical characters, thereby detecting the predefined graphic symbol in the digital image.
    Type: Grant
    Filed: April 12, 2007
    Date of Patent: September 20, 2011
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Yoav Schwartzberg, Tom Shenhav
  • Patent number: 8004731
    Abstract: An image forming apparatus is provided which includes: an image acquisition section (110) which reads an original and acquires an original image; a specific-pattern storage section (141) which stores a specific pattern which expresses, using a dot pattern, apparatus identification information for identifying an apparatus that prints the original image on a sheet of recording paper; an extraction section (132) which extracts an actual image area except a blank area in the original image, and base on the extracted actual image area, extracts a specific area corresponding to an area for printing the specific pattern; and a print section (150) which prints the specific pattern within the actual image area, using a yellow toner.
    Type: Grant
    Filed: February 14, 2008
    Date of Patent: August 23, 2011
    Assignee: Kyocera Mita Corporation
    Inventor: Kunihiko Tanaka
  • Patent number: 7970171
    Abstract: A system and a method are disclosed for generating video. Object information is received. A path of motion of the object relative to a reference point is generated. A series of images and ground for a reference frame are generated from the ground truth and the generated path. A system and a method are disclosed for generating an image. Object information is received. Image data and ground truth may be generated using position, the image description, the camera characteristics, and image distortion parameters. A positional relationship between the document and a reference point is determined. An image of the document and ground truth are generated from the object information and the positional relationship and in response to user specified environment of the document.
    Type: Grant
    Filed: January 18, 2007
    Date of Patent: June 28, 2011
    Assignee: Ricoh Co., Ltd.
    Inventors: Andrew Lookingbill, Emilio Antunez, Berna Erol, Jonathan J. Hull, Qifa Ke
  • Patent number: 7965904
    Abstract: A position and orientation measuring apparatus comprising, a storage unit adapted to store character region specifying information and position information in association with a character region place in a physical space, a detection unit adapted to detect the character region from first captured image data obtained by capturing an image of the physical space by an image sensing apparatus, using the character region specifying information stored in the storage unit, and an estimation unit adapted to estimate a position and orientation of the image sensing apparatus upon capturing the captured image data based on image position information of the character region, detected by the detection unit, in the first captured image data, and the position information which is stored in the storage unit and corresponds to the detected region.
    Type: Grant
    Filed: July 30, 2007
    Date of Patent: June 21, 2011
    Assignee: Canon Kabushiki Kaisha
    Inventor: Kazuhiko Kobayashi
  • Patent number: 7950804
    Abstract: A system employed in a projector for protecting eyes when the projector is in use, includes an initialization module, a light emitting-receiving device, a time-measuring module, a comparison module, and an image-outputting device. The initialization module is configured for initializing a standard time value. The light emitting-receiving device is configured for emitting a light and receiving a reflection of the light. The time-measuring module is configured for measuring time elapsed between emitting the light and receiving the reflection to generate a time-cost value. The comparison module is configured for comparing the standard time value with the time-cost value to generate a signal. The image-outputting device is configured for outputting an eye-protective image or a general image corresponding to the signal.
    Type: Grant
    Filed: April 21, 2008
    Date of Patent: May 31, 2011
    Assignee: Hon Hai Precision Industry Co., Ltd.
    Inventor: Sheng-Hung Chen
  • Patent number: 7916972
    Abstract: A form reader includes a landmarks extractor configured to select textboxes of a converted document as form landmarks based on textual characteristics. A set of positional constraints constrain the form entries relative to the identified form landmarks. A constraints solver selects textboxes of the converted document as form entries by solving the set of positional constraints respective to a set of facts including the selected form landmarks and converted document. In some embodiments, the constraints solver includes a query engine configured to (i) construct a query in a logic programming language setting forth the set of positional constraints and the set of facts and to (ii) input said query to a logic programming language query solving engine and to (iii) receive a response from the query solving engine responsive to the input.
    Type: Grant
    Filed: July 31, 2006
    Date of Patent: March 29, 2011
    Assignee: Xerox Corporation
    Inventor: Jean-Luc Meunier
  • Patent number: 7903881
    Abstract: An image processing device is structured such that an appropriate judgement of an image, at which blurring or disappearance or the like will occur, is possible. When pixels, which form a line image at which there is the possibility that blurring or disappearance will occur at the time of printing by using a printing plate, are extracted, a line image warning function gives notice by displaying a warning message on a monitor of a client terminal. Thereafter, image converting and print setting are carried out such that an extracted line image is clarified. In this way, when a proof is prepared, an image, at which there is the possibility that blurring or disappearance will occur on a printed matter obtained by using a printing plate, is clarified, and appropriate proofing is possible.
    Type: Grant
    Filed: October 9, 2008
    Date of Patent: March 8, 2011
    Assignee: Fuji Xerox Co., Ltd.
    Inventors: Ryuichi Ishizuka, Mari Kodama, Yasushi Nishide
  • Patent number: 7853039
    Abstract: In a workflow management system for managing a workflow processing in which a processing object is document data read and digitized by an image reading apparatus, a technique to improve processing efficiency in the workflow processing is provided. The workflow management system includes a document data acquisition unit to acquire, as the processing object in the workflow processing, the document data made to correspond to reliability information as information indicating reliability of an image reading processing in the image reading apparatus, a reliability information acquisition unit to acquire the reliability information made to correspond to the document data acquired by the document data acquisition unit, and a processing execution unit to execute, based on the reliability information acquired by the reliability information acquisition unit, a specified processing relating to an approval processing in the workflow concerning the document data acquired by the document data acquisition unit.
    Type: Grant
    Filed: January 29, 2007
    Date of Patent: December 14, 2010
    Assignees: Kabushiki Kaisha Toshiba, Toshiba Tec Kabushiki Kaisha
    Inventor: Kazunori Hirabayashi
  • Patent number: 7813005
    Abstract: An apparatus includes: a reading unit that obtains image data by reading a document through a reading glass; a detecting unit that detects a dirty place on the reading glass; a determining unit that determines a type of each area in the image data; an edge enhancing unit that applies an edge enhancement to each area based on the type determined; and a control unit that controls, when the type of an area determined is a text area, and when the area overlaps the dirty place detected, an amount of the edge enhancement for the area.
    Type: Grant
    Filed: June 17, 2005
    Date of Patent: October 12, 2010
    Assignee: Ricoh Company, Limited
    Inventor: Hiroshi Arai
  • Patent number: 7792356
    Abstract: An imaging device includes an image sensor having a plurality of chromatic color pixels and high-sensitivity pixels having higher sensitivity to incident light than the chromatic color pixels arranged in a checkerboard pattern, a correlation detector that detects correlation of an imaged subject from a signal component of the high-sensitivity pixels and a signal component of the chromatic color pixels, a color judgment block that judges whether or not the imaged subject is of chromatic color from the signal component of the chromatic color pixels, and a pixel interpolator that switches between pixel interpolation methods according to the signal judged in the color judgment block that judges whether or not the subject is of chromatic color, the pixel interpolator giving high priority to interpolation using pixels showing strong correlation based on the information from the correlation detector when the color judgment block judges that the subject is of chromatic color.
    Type: Grant
    Filed: April 11, 2007
    Date of Patent: September 7, 2010
    Assignee: Sony Corporation
    Inventors: Masaaki Sato, Shinichiro Saito, Hirotake Cho
  • Publication number: 20100201871
    Abstract: A caption detection system wherein all detected caption boxes over time for one caption area are identical, thereby reducing temporal instability and inconsistency. This is achieved by grouping candidate pixels in the 3D spatiotemporal space and generating a 3D bounding box for one caption area. 2D bounding boxes are obtained by slicing the 3D bounding boxes, thereby reducing temporal instability as all 2D bounding boxes corresponding to a caption area are sliced from one 3D bounding box and are therefore identical over time.
    Type: Application
    Filed: February 9, 2010
    Publication date: August 12, 2010
    Inventors: Dong-Qing Zhang, Sitaram Bhagavathy