Using Projections (i.e., Shadow Or Profile Of Characters) Patents (Class 382/174)
  • Patent number: 10970580
    Abstract: To appropriately perform blotting out processing for a portion that a user intends to prevent from being displayed for an electronic document having text information on a character string for search, along with image information. The information processing apparatus according to the present invention, in a case where the electronic document is an electronic document in a format searchable for a character string and where a character string obtained by performing OCR processing for a character image object existing in an area and a character string of an invisible text object existing in the area do not match with each other, a setting unit performs re-setting of an area to which blotting out processing is applied for at least one of the character image object and the invisible text object so that both the character strings match with each other.
    Type: Grant
    Filed: September 24, 2018
    Date of Patent: April 6, 2021
    Assignee: Canon Kabushiki Kaisha
    Inventor: Tadanori Nakatsuka
  • Patent number: 10901516
    Abstract: A programmable data processing circuit is configured for receiving sensor signals indicative of gestures for identification by the processing circuit. The processing circuit applies to the sensor signals finite state machine processing resources to provide identification output signals indicative of gestures identified as a function of the sensor signals. A plurality of finite state machine processing programs loaded into the processing circuit include a data section and an instruction section. The data section including a fixed size part specifying respective processing resources used by the programs in the plurality of finite state machine processing programs and a variable size part with respective sizes for allocating the respective processing resources used by the programs in the plurality of finite state machine processing programs.
    Type: Grant
    Filed: August 1, 2018
    Date of Patent: January 26, 2021
    Assignee: STMICROELECTRONICS S.R.L.
    Inventors: Carlo Crippa, Rossella Bassoli
  • Patent number: 10895459
    Abstract: A vehicle navigation system includes a camera and a controller. The camera is configured to render an image of a host-vehicle in a field-of-view of the camera. The camera located remote from the host-vehicle. The controller is installed on the host-vehicle. The controller is configured to receive the image and determine a vehicle-coordinate of the host-vehicle in accordance with a position of the host-vehicle in the image. The camera may be configured to superimpose gridlines on the image, and the controller may be configured to determine the position in accordance with the gridlines.
    Type: Grant
    Filed: December 29, 2017
    Date of Patent: January 19, 2021
    Assignee: Aptiv Technologies Limited
    Inventors: Divya Agarwal, Keerthi Raj Nagaraja, Michael H. Laur, Brian R. Hilnbrand
  • Patent number: 10685261
    Abstract: A system for partitioning a two-dimensional (2D) array and recognizing elements of the 2D array selects a location in an array comprising pixel data of the 2D array; and selects a direction in which to traverse the array from the selected location to segment the elements of the 2D array. The system uses a model and a reward/penalty function to guide the traversal through the array. The system changes direction when the data encountered while traversing the array in the selected direction represents one of the elements of the 2D array and continues in the selected direction when the data represents a joint between two elements of the 2D array. The system recognizes one or more of the elements of the 2D array segmented by traversing the array.
    Type: Grant
    Filed: June 11, 2018
    Date of Patent: June 16, 2020
    Assignee: GM GLOBAL TECHNOLOGY OPERATIONS LLC
    Inventors: Xuewei Qi, Orhan Bulan, David H. Clifford, David J. Hiemenga, Yehenew G. Mengistu
  • Patent number: 10643094
    Abstract: A method for segmenting an image containing handwritten text into line segments and word segments. The image is horizontally down sampled at a first ratio. Connected regions in the down-sampled image are detected; horizontal neighboring ones are merged to form lines, to segment the original image into line images. Each line image is horizontally down sampled at a second ratio which is smaller than the first ratio. Connected regions in the down-sampled line image are detected to obtain potential word segmentation positions. A path is a way of dividing the line at some or all of the potential word segmentation positions into multiple path segments; for each of all possible paths, word recognition is applied to each path segment to calculate a word recognition score, and an average word recognition score for the path is calculated; the path with the highest score gives the final word segmentation.
    Type: Grant
    Filed: July 23, 2018
    Date of Patent: May 5, 2020
    Assignee: KONICA MINOLTA LABORATORY U.S.A., INC.
    Inventor: Duanduan Yang
  • Patent number: 10606933
    Abstract: The invention converts a document originating in a page-image format into a form suitable for an arbitrarily sized display, by reformatting or “re-flowing” of the document to fit an arbitrarily sized display device. A two-stage system analyzes, or “deconstructs,” page image layout. The deconstruction includes both physical (geometric) and logical (functional) segmentation of page images. The segment that image elements may include blocks, lines, and/or words of text, and other segmented image elements. The segment that image elements are synthesized and converted into an intermediate structure. The intermediate data structure is then distilled or converted or redisplayed into any number of standard print formats.
    Type: Grant
    Filed: June 3, 2011
    Date of Patent: March 31, 2020
    Assignee: XEROX CORPORATION
    Inventors: Thomas M. Breuel, Henry S. Baird, William C. Janssen, Ashok C. Popat, Daniel S. Bloomberg
  • Patent number: 10552705
    Abstract: A method, an apparatus and an electronic device of character segmentation are disclosed. The method includes obtaining character segmentation points of a character image to be segmented as candidate segmentation points using a predetermined segmentation point generation algorithm, the character image to be segmented being a foreground character image that is obtained by removing a background image from an original grayscale character image; selecting and obtaining correct segmentation points from the candidate segmentation points based on the original grayscale character image and a pre-generated segmentation point classifier; and performing character segmentation for the character image to be segmented based on the correct segmentation points.
    Type: Grant
    Filed: February 2, 2018
    Date of Patent: February 4, 2020
    Assignee: Alibaba Group Holding Limited
    Inventors: Mengchao He, Yuan He, Hongming Zhang
  • Patent number: 10402944
    Abstract: A user device may capture an image including an object, and may identify the object, including determining an outline of the object. The user device may determine a first center point of the object and an angle of orientation of the object in relation to the image. The user device may rotate the image based on the angle of orientation, including changing one or more dimensions of the image. The user device may, after rotating the image, determine the one or more dimensions of the rotated image, calculate one or more offset values associated with changing the one or more dimensions of the rotated image, and determine a second center point of the object based on the first center point and the one or more offset values. The user device may perform an action related to the rotated image based on determining the second center point of the object.
    Type: Grant
    Filed: August 20, 2018
    Date of Patent: September 3, 2019
    Assignee: Capital One Services, LLC
    Inventors: Jason Pribble, Nicholas Capurso, Daniel Alan Jarvis
  • Patent number: 10380173
    Abstract: A method of jointly classifying a plurality of objects in an image using a feature type selected from a plurality of feature types determines classification information for each of the plurality of objects in the image by applying a predetermined joint classifier to at least one feature of a first type. The feature is generated from the image using a first feature extractor, the classification information being based on a probability of each of a plurality of possible classifications. The method estimates, for each of the feature types, an improvement in an accuracy of classification for each of the plurality of objects. The method selects features of a further type, from the plurality of feature types, according to the estimated improvement in the accuracy of the classification of each of the objects, and classifies the plurality of objects in the image using the selected features of the further type.
    Type: Grant
    Filed: August 24, 2015
    Date of Patent: August 13, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Nagita Mehrseresht
  • Patent number: 10346706
    Abstract: An imaging processing device includes an image acquisition unit, a character region estimation unit, and an output unit. The character region estimation unit determines a line indicating a direction in which characters are arranged with high probability in the acquired image and estimates a character region candidate in which characters are arranged with high probability. The output unit outputs information of the region estimated in the character region estimation unit. The character region estimation unit includes a vertical line detector, a horizontal line detector, a color distribution detector, and a character region candidate line determination unit. The image processing device includes an association imaging mode to cause a user to shoot an image of the character region candidate.
    Type: Grant
    Filed: August 26, 2016
    Date of Patent: July 9, 2019
    Assignee: OLYMPUS CORPORATION
    Inventors: Osamu Nonaka, Kunio Yamamiya, Hiroshi Kodama, Shinya Abe, Yuichi Tsuchimochi
  • Patent number: 10339212
    Abstract: Techniques are disclosed for detecting the bounds of borderless open tables in fixed-format structured documents, such as PDF documents, and grouping text lines into predicted borderless tables. The target document comprises a set of text lines each having a respective vertical and horizontal position in the target document. A sorted list of the text lines is generated based upon a vertical and horizontal position of each text line in the target document. For each text line in the sorted list, a respective probability that the text line in the sorted list belongs to a borderless table is then determined. According to one embodiment, the probability may be determined using a classifier that may employ a logistic regression algorithm.
    Type: Grant
    Filed: August 14, 2017
    Date of Patent: July 2, 2019
    Assignee: Adobe Inc.
    Inventors: Ram Bhushan Agrawal, Himanshu Mittal
  • Patent number: 10331326
    Abstract: An apparatus that includes circuitry that controls a display to display an image having a first edge and a second edge, the second edge on an opposite side of the image from the first edge, scroll through the image from the first edge to the second edge in response to a first user input, and continue scrolling past the second edge in response to a second user input, and the second user input is different than the first user input.
    Type: Grant
    Filed: August 21, 2012
    Date of Patent: June 25, 2019
    Assignee: SONY CORPORATION
    Inventor: Wataru Kawamata
  • Patent number: 10126825
    Abstract: The invention relates to a method for recognizing handwriting on a physical surface on the basis of three-dimensional signals originating from sensors of a terminal, the method being characterized in that the signals are obtained on the basis of at least 3 different types of sensors, and in that it comprises steps of sampling, according to 3 axes and over a sliding time window, of inertial signals originating from the sensors, fusing the sampled signals into a 9-dimensional vector for each sampling period, converting the fused signals into a sequence of characteristic 9-dimensional vectors, and, when a signal characteristic of an input start has been detected, storing the sequence of characteristic vectors in a list of sequences of characteristic vectors, the preceding steps being repeated until the detection of a signal characteristic of an input end, the method furthermore comprising, on detection of said signal characteristic of an input end, a step of recognizing a word on the basis of the list of sequenc
    Type: Grant
    Filed: June 23, 2016
    Date of Patent: November 13, 2018
    Assignee: ORANGE
    Inventor: Gregoire Lefebvre
  • Patent number: 10089510
    Abstract: Various display control methods and apparatuses are provided. A method comprises: acquiring azimuth information of a lens relative to a display plane, determining a desired display area of a display content of the display plane in the display plane according to the azimuth information, and adjusting a display position of the display content on the display plane according to the desired display area. A complicated operation that the lens looks for and/or is aligned with the display content is simplified, and the probability of active discovery of the display content and the probability of capturing the display content displayed in the display plane by the lens are thereby increased.
    Type: Grant
    Filed: June 29, 2016
    Date of Patent: October 2, 2018
    Assignee: BEIJING ZHIGU RUI TUO TECH CO., LTD
    Inventor: Dayong Ding
  • Patent number: 10068146
    Abstract: A detection-based segmentation-free method and system for license plate recognition. An image of a vehicle is initially captured utilizing an image-capturing unit. A license plate region is located in the image of the vehicle. A set of characters can then be detected in the license plate region and a geometry correction performed based on a location of the set of characters detected in the license plate region. An operation for sweeping an OCR across the license plate region can be performed to infer characters with respect to the set of characters and locations of the characters utilizing a hidden Markov model and leveraging anchored digit/character locations.
    Type: Grant
    Filed: February 25, 2016
    Date of Patent: September 4, 2018
    Assignee: CONDUENT BUSINESS SERVICES, LLC
    Inventors: Orhan Bulan, Palghat Ramesh, Vladimir Kozitsky
  • Patent number: 10049476
    Abstract: A method of creating an editable image and editable text from a hand-drawn or other static two-dimensional diagram may include receiving a raw image from an image acquisition device; modifying the raw image to a modified image to reduce noise, normalize raw image data, and reduce pixels; recognizing horizontal, vertical, and diagonal lines in the modified image using a line recognizer; connecting the lines in the modified image to form connected lines using a connector that detects and joins proximally positioned terminal ends of the lines in the modified image; recognizing areas bounded by the connected lines as bounded objects using a bounded object recognizer; and/or identifying and classifying the bounded objects using an object identifier.
    Type: Grant
    Filed: May 15, 2015
    Date of Patent: August 14, 2018
    Assignee: TURBOPATENT,CORP.
    Inventors: Charles Broadus, Ben Demboski, Paul Watts, Masanori King Takee, James A Billmaier, Kristopher C Billmaier, David P Billmaier
  • Patent number: 9788055
    Abstract: Features of various implementations are used to enable identifying and presenting, in real time, Internet-accessible and/or Internet-based functionality, content and/or services associated with a particular television program concurrently playing on a television or display, as a part of an interactive television suite of technologies. In some implementations, the process of identifying Internet-accessible and/or Internet-based functionality, content and/or services associated with a particular television program is enabled to reduce communication between a primary set-top box and a supplemental set-top box and/or television integrated device, thereby reducing the need for one or more provider specific APIs.
    Type: Grant
    Filed: March 14, 2013
    Date of Patent: October 10, 2017
    Assignee: GOOGLE INC.
    Inventors: Michael Verrilli, Nathan Leslie Sandland
  • Patent number: 9773197
    Abstract: A method performed by a mobile terminal may include displaying an image via a display of the mobile device. A first user selection of a portion of the image is received and text in the selected portion of the image is identified. The identified text is displayed via the display. A second user selection of at least a portion of the identified text is received. The portion of the identified text is translated from a first language into a second language that differs from the first language. The translated text, in the second language, is displayed over the image via the display.
    Type: Grant
    Filed: March 6, 2012
    Date of Patent: September 26, 2017
    Assignees: Sony Corporation, Sony Mobile Communications Inc.
    Inventors: Hakan Mats Englund, Simon Lessing
  • Patent number: 9760938
    Abstract: Systems, apparatus and methods for implementing transaction applications using a handheld document data capture device are described herein. The handheld device captures information from a rendered document. The captured information is processed to identify an electronic document corresponding to the rendered document. Information captured from the rendered document by the handheld capture device is used to perform a transaction. In one embodiment, a portable scanner is used to select items from a catalog. Information scanned from the catalog is used to identify the catalog, the items to be purchased, and complete an order via the Internet.
    Type: Grant
    Filed: December 30, 2013
    Date of Patent: September 12, 2017
    Assignee: Google Inc.
    Inventors: Martin T. King, Dale L. Grover, Clifford A. Kushler, James Q. Stafford-Fraser
  • Patent number: 9569674
    Abstract: A movement-amount-estimation device includes an edge-removal unit to generate a first edge-removed image by removing from a first edge-image a first-removal-target edge by on a change in brightness indicated by edge intensity in a direction from an inner side to an outer side of a mobile body, the first edge-image being generated from a first image taken by an imaging device mounted on the mobile body, and to generate a second-edge-removed image by removing from a second edge-image a second-removal-target edge by the change in brightness indicated by the edge intensity in the direction from the inner side to the outer side, the second edge-image being generated from a second image taken at a different clock time than the first image; and an output unit configured to output a movement amount of the mobile body that is estimated based on the first edge-removed image and the second edge-removed image.
    Type: Grant
    Filed: March 16, 2015
    Date of Patent: February 14, 2017
    Assignee: FUJITSU LIMITED
    Inventors: Jun Kanetake, Osafumi Nakayama
  • Patent number: 9569679
    Abstract: Various embodiments enable a device to perform an adaptive sampling method for locating text regions in images of natural scenes. Since only a fraction of pixels in an input image correspond to text regions, it is desirable to eliminate non-text regions early in the text detection process. Therefore, in at least one embodiment, an image is sampled horizontally to identify connected pixel regions indicative of text. In this example, each sampled row of the image is tested for containing Maximally Stable Extremal Regions (MSERs) in order to identify regions containing text. If a respective row contains a connected pixel region indicative of text, the neighboring rows are recursively sampled at finer levels in order to fully contain the text and sampling is terminated for regions which are unlikely to contain text. This sampling process can also be performed for the vertical dimension for regions which are determined to contain text.
    Type: Grant
    Filed: December 4, 2012
    Date of Patent: February 14, 2017
    Assignee: A9.com, Inc.
    Inventors: Douglas Ryan Gray, Arnab Sanat Kumar Dhua, Yu Lou, Ismet Zeki Yalniz
  • Patent number: 9536301
    Abstract: Methods, systems, and computer readable media are disclosed for determining a pixel-to-length ratio between a number of pixels disposed over a predetermined length of a reference object within an image of a siding sample and the predetermined length of the reference object. A first and second distance between respective first and second pairs of points within the image corresponding to respective first and second length measurements of the siding sample are determined, as well as a first and second number of pixels disposed between the first and second pair of points, respectively. Furthermore, the method, system, and computer readable medium disclose determining the first length measurement based on the pixel-to-length ratio and the first number of pixels, determining the second length measurement based on the pixel-to-length ratio and the second number of pixels, and identifying a siding product associated with the first and second length measurements.
    Type: Grant
    Filed: December 29, 2015
    Date of Patent: January 3, 2017
    Assignee: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY
    Inventors: Jonathan D. Maurer, Nicholas U. Christopulos
  • Patent number: 9509884
    Abstract: Presented is a skew detection apparatus. In one form, the apparatus estimates skew based on the locations of a set of foreground content pixels or a set of edge pixels that are nearest to the side of an image of a document. In another form, the apparatus includes a skew estimation unit adapted to estimate skew based on the orientation of foreground or background content in the interior of a document. In another form, the apparatus estimates skew using segments of an image of a document. Also presented is a document image processing apparatus including the skew detection apparatus.
    Type: Grant
    Filed: September 8, 2015
    Date of Patent: November 29, 2016
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: Sitaram Ramachandrula, Serene Banerjee, Pulkit Parikh, Noushath Shaffi, Anjaneyulu Seetha Rama Kuchibhotla, Prasenjit Dey
  • Patent number: 9311531
    Abstract: A method includes receiving or capturing a digital image using a mobile device, and using a processor of the mobile device to: determine whether an object depicted in the digital image belongs to a particular object class among a plurality of object classes; determine one or more object features of the object based at least in part on the particular object class at least partially in response to determining the object belongs to the particular object class; build or select an extraction model based at least in part on the one or more determined object features; and extract data from the digital image using the extraction model. The extraction model excludes, and/or the extraction process does not utilize, optical character recognition (OCR) techniques. Related systems and computer program products are also disclosed.
    Type: Grant
    Filed: March 13, 2014
    Date of Patent: April 12, 2016
    Assignee: Kofax, Inc.
    Inventors: Jan W. Amtrup, Anthony Macciola, Stephen Michael Thompson, Jiyong Ma
  • Patent number: 9262861
    Abstract: Methods and apparatus are provided for displaying shadows of polygonal light sources. A computing device can determine a light-source polygon of a polygonal light source, where the light-source polygon includes light-source vertices. The computing device can determine an occluding polygon between the light-source polygon and a background surface. The computing device can determine a shadow of the occluding polygon on the background surface by: for each light-source vertex, determining a vertex-shadow region of the background surface corresponding to a shadow cast upon the background surface by the occluding polygon for light emitted from the light-source vertex, determining an umbra of the shadow based on an intersection of the vertex-shadow regions, and determining a penumbra of the shadow based on a convex representation of a union of vertex-shadow regions. The computing device can display the shadow.
    Type: Grant
    Filed: July 21, 2014
    Date of Patent: February 16, 2016
    Assignee: Google Inc.
    Inventors: Teng-Hui Zhu, John Hoford
  • Patent number: 9256932
    Abstract: Methods, systems, and computer readable media are disclosed for determining a pixel-to-length ratio between a number of pixels disposed over a predetermined length of a reference object within an image of a siding sample and the predetermined length of the reference object. A first and second distance between respective first and second pairs of points within the image corresponding to respective first and second length measurements of the siding sample are determined, as well as a first and second number of pixels disposed between the first and second pair of points, respectively. Furthermore, the method, system, and computer readable medium disclose determining the first length measurement based on the pixel-to-length ratio and the first number of pixels, determining the second length measurement based on the pixel-to-length ratio and the second number of pixels, and identifying a siding product associated with the first and second length measurements.
    Type: Grant
    Filed: May 20, 2015
    Date of Patent: February 9, 2016
    Assignee: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY
    Inventors: Jonathan D. Maurer, Nicholas U. Christopulos
  • Patent number: 9152883
    Abstract: A system and/or method for increasing the accuracy of optical character recognition (OCR) for at least one item, comprising: obtaining OCR results of OCR scanning from at least one OCR module; creating at least one OCR seed using at least a portion of the OCR results; creating at least one OCR learn set using at least a portion of the OCR seed; and applying the OCR learn set to the at least one item to obtain additional optical character recognition (OCR) results.
    Type: Grant
    Filed: November 2, 2009
    Date of Patent: October 6, 2015
    Inventors: Harry Urbschat, Ralph Meier, Thorsten Wanschura, Johannes Hausmann
  • Patent number: 9098537
    Abstract: Techniques for Aligned Run-Length Encoding (ARLE) are described. ARLE is an encoding scheme that transforms sets of same-valued consecutive rows into one or more runs, while enforcing boundaries between the runs at set intervals (e.g. every predetermined number of rows). Consecutive rows that contain the same value, but which cross one or more interval boundaries, are encoded as multiple runs that are divided along those interval boundaries. According to one technique, a database server accelerates query processing by setting the interval size to the word size of the processor performing the predicate comparisons. According to another technique, a database server accelerates row lookup by maintaining an offset array that stores the run offsets into the ARLE data of the run that begins each interval.
    Type: Grant
    Filed: December 20, 2012
    Date of Patent: August 4, 2015
    Assignee: Oracle International Corporation
    Inventors: Kevin Moore, Aarti Basant, Brian Gold
  • Patent number: 9092668
    Abstract: In one embodiment, a method for identifying areas in a document image is provided. The method comprises generating binarized and gradient images based on the document image; and performing a classification operation to classify areas in the document image into one of a noise area and a picture area based on attributes computed on the binarized and gradient images.
    Type: Grant
    Filed: July 16, 2010
    Date of Patent: July 28, 2015
    Assignee: ABBYY Development
    Inventors: Konstantin Statsenko, Dmitry Deryagin
  • Patent number: 9058644
    Abstract: Various embodiments enable regions of text to be identified in an image captured by a camera of a computing device for preprocessing before being analyzed by a visual recognition engine. For example, each of the identified regions can be analyzed or tested to determine whether a respective region contains a quality associated with poor text recognition results, such as poor contrast, blur, noise, and the like, which can be measured by one or more algorithms. Upon identifying a region with such a quality, an image quality enhancement can be automatically applied to the respective region without user instruction or intervention. Accordingly, once each region has been cleared of the quality associated with poor recognition, the regions of text can be processed with a visual recognition algorithm or engine.
    Type: Grant
    Filed: March 13, 2013
    Date of Patent: June 16, 2015
    Assignee: AMAZON TECHNOLOGIES, INC.
    Inventors: David Paul Ramos, Chang Yuan, Keith Harrison Goodman, Avnish Sikka
  • Patent number: 9036911
    Abstract: A method of extracting from a picked-up image an object that is situated in the foreground of a projected backdrop. The method includes an extraction step comprising the steps of establishing a correspondence relationship between pixels of the projected backdrop and of the background of the picked-up image, and defining said object as the set of picked-up pixels that present a departure from said correspondence relationship. The method is applicable to video conferences, to remote teaching, and to television shows.
    Type: Grant
    Filed: December 4, 2006
    Date of Patent: May 19, 2015
    Assignee: Orange
    Inventors: Francois Coldefy, Michel Collobert, Mohamed Ali Ben Salah
  • Patent number: 9036907
    Abstract: A set of images is acquired of a scene while illuminating the scene with a set of colors with different hues. The set of colors is generated by a set of light sources arranged in a substantial circular manner around a lens of a camera to form a hue circle, wherein each light source emits a different color. A shadow confidence map is generated from the set of images by using hues and saturations of pixels in the set of images. Then, depth edges are extracted from the shadow confidence map.
    Type: Grant
    Filed: July 16, 2012
    Date of Patent: May 19, 2015
    Assignee: Mitsubishi Electric Research Laboratories, Inc.
    Inventor: Yuichi Taguchi
  • Patent number: 9025043
    Abstract: A system for providing an adjusted image of a scene includes an optical assembly, a capturing system coupled to the optical assembly, and a control system. The optical assembly is adjustable to alternatively be focused on a first focal area and a second focal area that is different than the first focal area. The capturing system captures a first frame of the scene when the optical assembly is focused at the first focal area, and a second frame of the scene when the optical assembly is focused at the second focal area. The first frame includes a plurality of first pixels and the second frame includes a plurality of second pixels. The control system analyzes the first frame and the second frame and utilizes graph cuts techniques to assign a depth label to at least a portion of the first frame.
    Type: Grant
    Filed: September 24, 2008
    Date of Patent: May 5, 2015
    Assignee: Nikon Corporation
    Inventors: Li Hong, Mark Takita, W. Thomas Novak
  • Publication number: 20150117779
    Abstract: A method and an apparatus for performing alpha matting on an image are described. A contour retrieving unit retrieves object contour information for the image. An edge decision unit then determines hard edges based on the retrieved object contour information using an edge model. Finally, an alpha assignment unit assigns alpha values to pixels of the image in a vicinity of a determined hard edge based on the edge model.
    Type: Application
    Filed: October 21, 2014
    Publication date: April 30, 2015
    Inventors: Markus SCHLOSSER, Jobst HORENTRUP, Lars KRUMWIEDE
  • Patent number: 8953039
    Abstract: An auto-commissioning system provides automatic parameter selection for an intelligent video system based on target video provided by the intelligent video system. The auto-commissioning system extracts visual feature descriptors from the target video and provides the one or more visual feature descriptors associated with the received target video to an parameter database that is comprised of a plurality of entries, each entry including a set of one or more stored visual feature descriptors and associated parameters tailored for the set of stored visual feature descriptors. A search of the parameter database locates one or more best matches between the extracted visual feature descriptors and the stored visual feature descriptors. The parameters associated with the best matches are returned as part of the search and used to commission the intelligent video system.
    Type: Grant
    Filed: July 1, 2011
    Date of Patent: February 10, 2015
    Assignee: UTC Fire & Security Corporation
    Inventors: Zhen Jia, Jianwei Zhao, Penghe Geng, Ziyou Xiong, Jie Xi, Zhengwei Jiang, Alan Matthew Finn
  • Patent number: 8910073
    Abstract: A visual indicator distinguishes between newly displayed content and previously displayed content during and/or after a scrolling operation. The newly displayed content is displayed in a different format, or with a different background, or with some other visual indication, as compared with content that was previously displayed and is still displayed after the scrolling operation. In this manner, the user is given a visual context for scrolling operations that provides an intuitive reference point when scrolling through a document. A user can easily determine where the newly displayed content picks up from where the previously displayed content left off. The visual indicator can be transitory if desired, so that it gradually fades after some period of time.
    Type: Grant
    Filed: November 26, 2007
    Date of Patent: December 9, 2014
    Assignee: QUALCOMM Incorporated
    Inventor: Paul Mercer
  • Patent number: 8903163
    Abstract: A method for determining a location of a target includes, at a first location, determining first location coordinates of a measuring device using one or more GNSS signals, determining a first gravitational direction, and capturing a first image using the camera. The method also includes, at a second location, determining second location coordinates of the measuring device, and capturing a second image. The method further includes determining a plurality of correspondence points between the first and second images, determining a first plurality of image coordinates for the plurality of correspondence points in the first image, determining a second plurality of image coordinates for the plurality of correspondence points in the second image, and determining the location of the target using at least the first plurality of image coordinates, the second plurality of image coordinates, and the first gravitational direction.
    Type: Grant
    Filed: August 9, 2012
    Date of Patent: December 2, 2014
    Assignee: Trimble Navigation Limited
    Inventors: Kevin Sharp, Shawn Weisenburger
  • Patent number: 8897527
    Abstract: In accordance with at least some embodiments of the present disclosure, a process for enhancing a motion-blurred image is presented. The process may include receiving a plurality of projections, wherein the plurality of projections contain computed tomography (CT) data obtained in multiple motion phases. The process may include generating an enhanced multi-phase image by performing an enhancement operation based on the plurality of projections. The process may further include generating a plurality of phase-correlated images based on the plurality of projections and the enhanced multi-phase image.
    Type: Grant
    Filed: June 7, 2011
    Date of Patent: November 25, 2014
    Assignee: Varian Medical Systems, Inc.
    Inventors: Josh Star-Lack, Mingshan Sun
  • Patent number: 8873890
    Abstract: A reading machine that operates in various modes includes image correction processing is described. The reading device pre-processes an image for optical character recognition by receiving the image and determining whether text in the image is too large or small for optical character recognition processing by determining that text height falls outside of a range in which optical character recognition software will recognize text in a digitized image. If necessary the image is resized according to whether the text is too large or too small.
    Type: Grant
    Filed: April 1, 2005
    Date of Patent: October 28, 2014
    Assignee: K-NFB Reading Technology, Inc.
    Inventors: Raymond C. Kurzweil, Paul Albrecht, Lucy Gibson
  • Patent number: 8855408
    Abstract: An image processing apparatus and method may estimate binocular disparity maps of middle views from among a plurality of views through use of images of the plurality of views. The image processing apparatus may detect a moving object from the middle views based on the binocular disparity maps of the frames. Pixels in the middle views may be separated into dynamic pixels and static pixels through detection of the moving object. The image processing apparatus may apply bundle optimization and a local three-dimensional (3D) line model-based temporal optimization to the middle views so as to enhance binocular disparity values of the static pixels and dynamic pixels.
    Type: Grant
    Filed: March 29, 2012
    Date of Patent: October 7, 2014
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Jiwon Kim, Guofeng Zhang, Du Sik Park, Ho Young Lee, Hujun Bao, Wenzhuo Yang
  • Patent number: 8842925
    Abstract: A method and apparatus for encoding an image is provided. An image coding unit, including a region that deviates from a boundary of a current picture, is divided to obtain a coding unit having a smaller size than the size of the image coding unit, and encoding is performed only in a region that does not deviate from the boundary of the current picture. A method and apparatus for decoding an image encoded by the method and apparatus for encoding an image is also provided.
    Type: Grant
    Filed: November 11, 2013
    Date of Patent: September 23, 2014
    Assignee: Samsung Electronics Co., Ltd.
    Inventor: Min-su Cheon
  • Patent number: 8830545
    Abstract: A document image processing system includes an extraction portion, an estimation portion, a calculation portion, a substitution portion, and a generation portion. The extraction portion extracts first and second document elements of an inputted document image and a preprint data. The estimation portion estimates first and second representative colors due to first and second document elements in a color space, respectively. The calculation portion calculates first and second planes to separate the color space into first and second sub-spaces which each includes each of the first and second representative colors, respectively. The substitution portion substitutes a color of a first pixel of the first document elements with the first representative color and a color of a second pixel of the second document elements with the second representative color. The generation portion subtracts each of the substituted first pixel from each of the substituted second pixel to generate a difference image.
    Type: Grant
    Filed: February 14, 2011
    Date of Patent: September 9, 2014
    Assignees: Kabushiki Kaisha Toshiba, Toshiba Solutions Corporation
    Inventor: Naoaki Kodaira
  • Patent number: 8832549
    Abstract: Some embodiments provide a for analyzing a document that includes a number of primitive elements. The method identifies boundaries between sets of primitive elements and identifies regions bounded by the boundaries. The method uses the identified regions to define structural elements for the document. The method defines a structured document based on the primitive elements and the structural elements.
    Type: Grant
    Filed: June 7, 2009
    Date of Patent: September 9, 2014
    Assignee: Apple Inc.
    Inventors: Philip Andrew Mansfield, Michael Robert Levy
  • Patent number: 8731295
    Abstract: Disclosed is a method for identifying lawn grass which includes capturing an image of the terrain in front of a mower, segmenting the image into neighborhoods, calculating at least two image statistics for each of the neighborhoods, generating a binary representation of each image statistic. The binary representation of each image statistic is generated by comparing the calculated image statistic values to predetermined image statistic values for grass. The method further includes weighting each of the binary representations of each image statistic, and summing corresponding neighborhoods for all image statistics. A binary threshold is applied to each of the summed neighborhoods to generate a binary map representing grass containing areas and non-grass containing areas.
    Type: Grant
    Filed: July 1, 2010
    Date of Patent: May 20, 2014
    Assignee: MTD Products Inc.
    Inventors: Alexander Schepelmann, Kathryn A. Daltorio, Amaury D. Rolin, Jonathan Beno, Bradley E. Hughes, James M. Green, Michael S. Branicky, Roger D. Quinn, Henry H. Snow, Francis L. Merat, Richard E. Hudson
  • Publication number: 20140126822
    Abstract: A method and apparatus for processing images, the method comprising: using a radar (4), generating a first image of an area of terrain (8); using a sensor (5), generating a second image of the area of terrain (8); performing an image segmentation process on the first image to identify a point in the first image as corresponding to a ground surface of the area of terrain (8); and projecting the identified point in the first image from the first image into the second image to identify a point in the second image as corresponding to the ground surface of the area of terrain (8). The method may further comprise: for the identified point in the second image, defining a sub-image of the second image containing that point; and performing a feature extraction process on the sub-image to identify points in the sub-image that correspond to the ground surface.
    Type: Application
    Filed: March 9, 2012
    Publication date: May 8, 2014
    Applicant: THE UNIVERSITY OF SYDNEY
    Inventors: James Patrick Underwood, Bertrand Douillard, Giulio Reina, Annalisa Milella
  • Patent number: 8693804
    Abstract: According to one embodiment, an image processing apparatus includes first and second computation portions, a selection portion, a projection portion, and a weighted averaging portion. The first computation portion is configured to obtain magnitudes of correlations between a first vector and plural basis vectors. The selection portion is configured to select basis vectors from the plural basis vectors. The projection portion is configured to select a second region, obtain a first projection vector by projecting the first vector onto a subspace formed by the selected basis vectors and obtain a second projection vector for each second region by projecting a second vector onto the subspace. The second computation portion is configured to compute a distance between the first and second projection vectors. The weighted averaging portion is configured to weighted average a pixel value of the second pixel to obtain an output pixel value of a first pixel.
    Type: Grant
    Filed: July 13, 2012
    Date of Patent: April 8, 2014
    Assignee: Kabushiki Kaisha Toshiba
    Inventors: Satoshi Kawata, Kenzo Isogawa, Nobuyuki Matsumoto, Toshimitsu Kaneko
  • Patent number: 8687241
    Abstract: Method for security printing. A digital model of a feature for printing is received, wherein the feature is for authentication by an external device. Deviation from the digital model is compensated for, to a printed instance of the feature.
    Type: Grant
    Filed: June 6, 2007
    Date of Patent: April 1, 2014
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: Steven J. Simske, Malgorzata M. Sturgill, Jason S. Aronoff, Juan C. Villa, Galia Golodetz
  • 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
  • Publication number: 20140056520
    Abstract: A system and method are provided for segmenting an image. The method includes computing an image signature for an input image. One or more similar images are identified from a first set of images, based on the image signature of the input image and image signatures of images in the first set of images. The similar image or images are used to define a cropped region of the input image and a second image signature is computed, this time for the cropped region. One or more similar images are identified from a second set of images, based on the cropped image signature and the image signatures of images in the second set of images. The input image is segmented based on a segmentation map of at least one of the similar images identified in the second set of images.
    Type: Application
    Filed: August 23, 2012
    Publication date: February 27, 2014
    Applicant: Xerox Corporation
    Inventor: José Antonio Rodriguez Serrano
  • Patent number: 8639010
    Abstract: According to a radiographic apparatus of this invention, an image correcting unit corrects offset for every pixel relative to a detection value outputted from a radiation detector having pixels for detecting radiation arranged in a two-dimensional array. In addition, the image correcting unit corrects the offset while holding noise components contained in the detection value. Thus, upon quantitative evaluation of the noises contained in the detection values outputted from the radiation detector, the noises of not only positive values but also negative values can be considered. Consequently, accurate evaluation may be achieved.
    Type: Grant
    Filed: October 21, 2009
    Date of Patent: January 28, 2014
    Assignee: Shimadzu Corporation
    Inventor: Susumu Adachi