To Rotate An Image Patents (Class 382/296)
-
Patent number: 8988455Abstract: A reference character is generated by combining part objects prepared for each site. At least one candidate character object is generated by changing at least one part object among the part objects used in the reference character object. The reference character object and the candidate character object are displayed by a display device, and an input for selection from a user is accepted. Next, a site for which different part objects are used between the selected character object and the reference character object is determined. A new character object is generated by changing the part object used for the determined site with priority. The selected character object is displayed as the reference character, and the newly generated character is displayed as the candidate character.Type: GrantFiled: March 4, 2010Date of Patent: March 24, 2015Assignee: Nintendo Co., Ltd.Inventors: Ryutaro Takahashi, Takafumi Masaoka
-
Patent number: 8958659Abstract: An image registration method is disclosed for processing a distorted image into a registered image that is aligned with reference to an original image. Distortions from the original image may include scaling, rotation, and noise. The method is based on correlating Radon transforms of both images to determine the rotation angle, and the scaling factor is determined by dividing averages of the overall luminance of each image on the assumption that any added noise will cancel. The Fast Fourier Transform (FFT) is used to estimate global spatial shifts. In one embodiment, the distorted image is first scaled to the size of the original image before being rotated. In another embodiment, the original image is first scaled to the size of the distorted image before rotating the distorted image, and finally scaling it to match the original image. A corresponding system for image registration is also provided.Type: GrantFiled: December 21, 2012Date of Patent: February 17, 2015Assignee: Ecole de Technologie SuperieureInventors: Guangyi Chen, Stéphane Coulombe
-
Publication number: 20150036944Abstract: Systems, methods, and computer-readable media acquire an image captured with a mobile device. Motion sensor data of the mobile device at or near a time when the image was captured is acquired. An angle of rotation is computed based on the motion sensor data, and the image is transformed based on the angle of rotation. In another aspect, a user interface enables user control over image transformation. The user interface enables user control over rotating an image on a display at two or more granularities. A point of rotation may be user-defined. Rotated images may be scaled to fit within a viewing frame for displaying the transformed image.Type: ApplicationFiled: August 2, 2013Publication date: February 5, 2015Inventors: Alex Restrepo, Kevin Systrom
-
Publication number: 20150030259Abstract: In one example embodiment, a device includes an object detector configured to: rotate an image multiple times in increments of a predetermined number of degrees, detect upright occurrences of at least one object from the image at each incremental rotation of the image, and divide the detected occurrences of the at least one detected object, at each incremental rotation of the image, into a corresponding classification; and a direction manager configured to: determine a normal direction of the image, based on a number of detected occurrences of the at least one detected object, at each incremental rotation of the image, for each corresponding classification.Type: ApplicationFiled: July 22, 2014Publication date: January 29, 2015Inventors: Jae-cheol KWON, Jongsung KIM
-
Patent number: 8942512Abstract: An image registration method is disclosed for processing a distorted image into a registered image that is aligned with reference to an original image. Distortions from the original image may include scaling, rotation, and noise. The method is based on correlating Radon transforms of both images to determine the rotation angle, and the scaling factor is determined by dividing averages of the overall luminance of each image on the assumption that any added noise will cancel. The Fast Fourier Transform (FFT) is used to estimate global spatial shifts. In one embodiment, the distorted image is first scaled to the size of the original image before being rotated. In another embodiment, the original image is first scaled to the size of the distorted image before rotating the distorted image, and finally scaling it to match the original image. A corresponding system for image registration is also provided.Type: GrantFiled: December 21, 2012Date of Patent: January 27, 2015Assignee: Ecole de Technologie SuperieureInventors: Guangyi Chen, Stephane Coulombe
-
Patent number: 8942513Abstract: A de-warping processing method for digital images includes the following steps. A first image window is segmented into a plurality of first blocks. A second image window is segmented into a plurality of second blocks according to locations and an amount of the first blocks. A coordinate transformation parameter is calculated by a group of first vertex coordinate values of the first block and a group of second vertex coordinate values of the corresponding second block. Each of coordinate values of the first block is transformed into an estimated coordinate value of the corresponding second block according to the coordinate transformation parameter. A pixel content value is obtained from the second image window according to each of the estimated coordinate values, and is written into a pixel with the corresponding coordinate value in the first block. All the first blocks are processed for outputting a first image.Type: GrantFiled: March 18, 2013Date of Patent: January 27, 2015Assignee: Vivotek Inc.Inventor: Jen-Chih Wu
-
Patent number: 8937593Abstract: A method for calibrating position of light point is used for an interactive projection system including an image capture device. The image capture device includes an image sensor and an optical filter. The method includes the following steps. A plurality of calibrating patterns formed by visible light is individually projected on a screen. The distance between the calibrating pattern with big area and an optical axis of the image sensor is larger than that between the calibrating pattern with small area and the optical axis. Next, the exposure time of the image sensor is adjusted so the image sensor can capture the images of the calibrating patterns through the optical filter. According to the images of the calibrating patterns, a plurality of coordinate positions is gotten. Then, the coordinate positions are adjusted according to a standard coordinate.Type: GrantFiled: March 8, 2013Date of Patent: January 20, 2015Assignee: Everest Display Inc.Inventors: Hei-Tai Hong, Fu-Hsiung Lee
-
Patent number: 8923638Abstract: A technique for selecting a particular reconstruction technique to be applied to an image sequence. The technique may analyze an input image sequence and, based on one or more characteristics of the image sequence, select a reconstruction technique as the appropriate technique for the image sequence from among a set of reconstruction techniques. For example, the set may include two or more of a rotation-based reconstruction technique, a plane-based reconstruction technique, and a general 3D reconstruction technique. The selection technique may be combined with the reconstruction techniques to produce a system that takes as input an image sequence or a set of point trajectories, selects an appropriate reconstruction technique, and applies the selected reconstruction technique to generate an estimate of camera motion and camera intrinsic parameters for the image sequence. The technique may be adapted to select among other types of techniques that may be applied to image sequences.Type: GrantFiled: December 21, 2012Date of Patent: December 30, 2014Assignee: Adobe Systems IncorporatedInventor: Hailin Jin
-
Patent number: 8903141Abstract: An electronic device may include a housing, and a finger sensor carried by the housing to sense a user's finger placement at different rotational angles. The electronic device may also include an orientation sensor carried by the housing to sense an orientation thereof, and a processor coupled to the finger sensor and the orientation sensor. The processor may acquire finger-matching biometric data of the user's finger at an unknown rotational angle relative to a known rotational angle of finger-enrollment data, generate an estimated rotational angle of the acquired finger-matching biometric data and based upon a sensed orientation of the housing, and attempt an authentication of the user based upon the estimated acquired rotational angle.Type: GrantFiled: May 3, 2012Date of Patent: December 2, 2014Assignee: Authentec, Inc.Inventor: Mark Allen Heilpern
-
Patent number: 8885972Abstract: Methods for correcting distortions in an image including text, or an image of a page that includes text, are disclosed. The methods include identifying reliable and substantially straight lines from elements in the image. Vanishing points are determined from the lines. Parameters associated with a rectangle are determined. A coordinate conversion is performed.Type: GrantFiled: July 30, 2012Date of Patent: November 11, 2014Assignee: ABBYY Development LLCInventors: Olga Kacher, Vladimir Rybkin
-
Patent number: 8879817Abstract: A method includes using a pre-scan image to define a scan field of view for a region of interest of a patient to be scanned for at least one image acquisition of a series of image acquisitions of a scan plan, performing an image acquisition of the series based on a corresponding scan field of view for the image acquisition, and determining, via a processor (120), a next field of view for a next image acquisition of the series based on available image related data.Type: GrantFiled: February 24, 2014Date of Patent: November 4, 2014Assignee: Koninklijke Philips N.V.Inventors: Torbjorn Vik, Jorg Bredno, Rafael Wiemker, Mark E. Olszewski
-
Publication number: 20140294321Abstract: An image processing apparatus, includes: a transforming area setter, operable to set at least a part of an area of a target image as a transforming area; a transforming area divider, operable to arrange a plurality of dividing points in the transforming area and to divide the transforming area into a plurality of small areas by using a line connecting the dividing points; and a transforming processor, operable to move a position of at least one of the dividing points to transform at least one of the small areas, thereby transforming an image in the transforming area.Type: ApplicationFiled: June 10, 2014Publication date: October 2, 2014Inventors: Ikuo HAYAISHI, Akio YAMAZAKI
-
Patent number: 8842135Abstract: Methods and systems of editing a set of images depicting a subject displayed at a plurality of rotational angles is disclosed, comprising defining degrees of angular rotation of the subject about a rotational axis; selecting a subset of images based on the degrees of angular rotation of the subject depicted in the subset; determining image transformation values for the subset; determining interpolated image transformation values by interpolating the image transformation values for at least one of the images in the image set based on the image transformation values for the subset; and transforming at least one of the images in the set based on the image transformation values, and/or the interpolated image transformation values. The methods and systems may further comprise transforming the other images in the set based on both the image transformation values and the interpolated image transformation values, so they appear more precisely centered.Type: GrantFiled: March 19, 2012Date of Patent: September 23, 2014Inventor: Joshua Morgan Jancourtz
-
Publication number: 20140270573Abstract: A method of processing a binary document image to remove non-text elements including long straight lines. The method uses a least squares method to fit the pixels of an image component to a line, and then use the coefficient of determination as a measure of linearity of the image component. For each image component, the line fitting and the coefficient of determination are performed twice, once on the original pixel coordinates and once after the image component is rotated 45 degrees. The higher one of the two calculated coefficients of determination is used to determine whether the image component is a straight line. If it is, and if the line is longer than a certain length, it is removed from the document image as a non-text element.Type: ApplicationFiled: March 12, 2013Publication date: September 18, 2014Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.Inventor: Shugo Ishizaka
-
Publication number: 20140270574Abstract: An image data processing including a storage unit for storing a first pixel block and a second pixel block taken from image data in which pixels are arranged in a first direction and a second direction, and a writing module for writing the first pixel block and the second pixel block stored in the storage unit into a memory, wherein the first pixel block and the second pixel block are arranged one adjacent to the other along the first direction, and the number of pixels arranged in the first direction in each block is equal to an access unit data length of the memory multiplied by a natural number m1, and the writing module writes pixel data equal in length to the access unit data length, and representing pixels contiguously arranged along the first direction across the first and second pixel blocks, into the memory in a single access operation.Type: ApplicationFiled: January 15, 2014Publication date: September 18, 2014Applicant: PFU LIMITEDInventors: Miki Asukai, Hideyo Kawara
-
Patent number: 8837864Abstract: An image synthesis processing apparatus capable of synthesizing a foreground image and a background image into an image, which is sharp and natural in color, with a simple system construction that does not require a special hardware structure and special arithmetic processing, without causing color mixing at a boundary between replacement color pixels and other pixels in the foreground image. The background image is rotated by a first rotation unit of the image synthesis processing apparatus by a predetermined rotation angle in a direction opposite to an instructed rotation direction, the background image after rotation in the opposite direction and the original foreground image are synthesized into a synthesis image by a synthesis unit, and the synthesis image is rotated by a rotation unit by the predetermined rotation angle in the instructed rotation direction, thereby generating a desired image.Type: GrantFiled: October 4, 2011Date of Patent: September 16, 2014Assignee: Canon Kabushiki KaishaInventors: Chisato Mori, Yoshinobu Sato
-
Patent number: 8837865Abstract: The present invention provides an image processing apparatus for performing image processing of image data in which information specifying, on a first coordinate system, a position of a portion of interest in an image is recorded, including an image processing unit configured to perform rotation processing of the image data using a second coordinate system having an origin different from that of the first coordinate system, and a change unit configured to change the information specifying the position of the portion of interest in accordance with a rotation amount of the image data by the rotation processing such that an image of the portion of interest specified by the information specifying the position of the portion of interest after the rotation processing matches that before the rotation processing.Type: GrantFiled: February 22, 2013Date of Patent: September 16, 2014Assignee: Canon Kabushiki KaishaInventor: Ryuhei Konno
-
Patent number: 8831382Abstract: The method of creating image mosaics, comprising performing following operations: component elements of images are analyzed and descriptors of matching points are revealed; pair-wise comparison of descriptors is performed; descriptors are matched with final image and rotation/translation parameters are recovered; component elements one-by-one are complemented in final image, based on recovered rotation/translation parameters.Type: GrantFiled: February 19, 2010Date of Patent: September 9, 2014Assignee: Samsung Electronics Co., Ltd.Inventor: Ekaterina V. Tolstaya
-
Patent number: 8831380Abstract: A system for displaying hybrid image data produced by embedding additional media objects within street-level panoramic images includes a user interface through which a user may view, search for, and/or navigate through additional media objects in the context of browsing a virtual environment of a location at street level. In response to user input indicating a request to view a geographic location and/or an additional media object, street-level panoramic image data associated with the geographic location, in which one or more additional media objects also associated with the geographic location have been embedded, may be provided for display through the user interface. The user interface may be provided by a client device including one or more processors that receive hybrid image data produced by one or more processors of a server and display the image data to the user.Type: GrantFiled: April 18, 2013Date of Patent: September 9, 2014Assignee: Microsoft CorporationInventors: Eyal Ofek, Michael Kroepfl, Julian R. Walker, Gonzalo A. Ramos, Blaise Hilary Aguera y Arcas
-
Patent number: 8811681Abstract: A biometric authentication apparatus includes an image shooting unit to capture a vessel image of a person to be authenticated and an authentication unit to verify verification vessel position information of the captured vessel image of the person to be authenticated against registered vessel position information of a registered vessel image registered in advance. When the verification vessel position information is not identical with the registered vessel position information, the authentication unit performs authentication using vessel size information of the registered vessel image registered in advance.Type: GrantFiled: September 4, 2012Date of Patent: August 19, 2014Assignee: Fujitsu LimitedInventor: Masaki Watanabe
-
Patent number: 8804209Abstract: An image processing apparatus including, an input unit for inputting image data including a document region, a storage for storing the brightness of each pixel on a first main scan line outside the document region, a corrector for correcting the brightness of each pixel on the first main scan line in accordance with the brightness of pixels in a first part and the brightness of pixels in a second part on a second main scan line following the first main scan line, and an edge point detector for detecting an edge point of the document region situated on the second main scan line in accordance with the difference between the brightness of each pixel on the first main scan line corrected and the brightness of each pixel on the second main scan line respectively corresponding to each pixel on the first main scan line.Type: GrantFiled: December 13, 2012Date of Patent: August 12, 2014Assignee: PFU LimitedInventors: Akira Iwayama, Masayoshi Hayashi
-
Patent number: 8805119Abstract: A rendering command generator (11) acquires coordinate transformation information and a rendering region that converts and displays a reference image in a display image, and sets a coordinate transformation matrix in a register (21). A rendering block setting unit (22) sets the number of vertical and horizontal pixels of a rectangular region that divides and covers the rendering region in such a way that the region in which the rectangular region is subjected to coordinate transformation from a rendering region to a reference image by a coordinate transformation matrix conforms with the shape on the image of the image cache (15) from which the reference image is read out. A pixel generator (13) scans the rendering region by using the set rectangular region and generates pixel positions, and a coordinate transformation unit (14) reads out from external memory (20) image data on the pixel positions of the reference image corresponding to the pixels of the rendering region.Type: GrantFiled: November 17, 2010Date of Patent: August 12, 2014Assignee: NEC System Technologies, Ltd.Inventor: Junko Yamaji
-
Patent number: 8798387Abstract: An image processing device including: a motion amount estimating unit estimating a first motion amount indicating a displacement amount of a second picture with respect to a first picture; an area setting unit setting an area to be used for post-processing for each of the first picture and a first corrected picture, using feature points extracted from the first picture and the second picture; a post-processing unit generating a first cutout picture from the first picture and a second cutout picture from the first corrected picture and estimating a second motion amount indicating a displacement amount of the second cutout picture with respect to the first cutout picture; and a motion amount obtaining unit obtaining a motion amount indicating a displacement amount between the first picture and the second picture, from the estimated first motion amount and the estimated second motion amount.Type: GrantFiled: November 8, 2011Date of Patent: August 5, 2014Assignee: Panasonic Intellectual Property Corporation of AmericaInventors: Hitoshi Yamada, Jun Ohmiya
-
Patent number: 8793778Abstract: Enables trusted user access of computer systems for example that verifies trusted users and may allow trusted users to bypass challenge-response tests, while limiting access by automated processes and unwanted human challenge-response test solvers. Embodiments may implement an account that may be utilized across websites to enable a valid or trusted user to bypass challenge-response tests. Embodiments of the invention cost time, or cost a nominal fee, or require use of something that may be validated as owned by a user such as a physical address or cell phone, or trusted referral or social graph or any combination thereof, but cost large amounts time or money for spammers using cheap third world labor, thus making it expensive to invoke attacks on sites protected by embodiments of the invention.Type: GrantFiled: August 31, 2012Date of Patent: July 29, 2014Assignee: Spamcaptcher Inc.Inventors: Stefan Marinov, Kieran Miller
-
Patent number: 8787702Abstract: 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: GrantFiled: December 7, 2012Date of Patent: July 22, 2014Assignee: Accusoft CorporationInventor: William Douglas Withers
-
Patent number: 8780998Abstract: Implementations are provided that relate, for example, to view tiling in video encoding and decoding. A particular method includes accessing a video picture that includes multiple pictures combined into a single picture, accessing information indicating how the multiple pictures in the accessed video picture are combined, decoding the video picture to provide a decoded representation of at least one of the multiple pictures, and providing the accessed information and the decoded video picture as output. Some other implementations format or process the information that indicates how multiple pictures included in a single video picture are combined into the single video picture, and format or process an encoded representation of the combined multiple pictures.Type: GrantFiled: April 11, 2008Date of Patent: July 15, 2014Assignee: Thomson LicensingInventors: Purvin Bibhas Pandit, Peng Yin, Dong Tian
-
Patent number: 8781258Abstract: An image processing apparatus, includes: a transforming area setter, operable to set at least a part of an area of a target image as a transforming area; a transforming area divider, operable to arrange a plurality of dividing points in the transforming area and to divide the transforming area into a plurality of small areas by using a line connecting the dividing points; and a transforming processor, operable to move a position of at least one of the dividing points to transform at least one of the small areas, thereby transforming an image in the transforming area.Type: GrantFiled: March 25, 2008Date of Patent: July 15, 2014Assignee: Seiko Epson CorporationInventors: Ikuo Hayaishi, Akio Yamazaki
-
Patent number: 8781151Abstract: A method for use in obtaining input data from an object includes capturing a live image of the object with an image capture device, receiving information related to a tilt angle of the object from one or more sensors other than the image capture device, using the information related to a tilt angle of the object to obtain at least one rotated reference image of the object, comparing the live image of the object with the rotated reference image of the object, and generating an indication in response to the live image matching the rotated reference image. An apparatus and a storage medium storing a computer program executable by a processor based system are also disclosed.Type: GrantFiled: August 16, 2007Date of Patent: July 15, 2014Assignee: Sony Computer Entertainment Inc.Inventors: Richard Marks, Gary M. Zalewski
-
Patent number: 8773739Abstract: An image reading device includes a conveying unit, reading unit, detecting unit, and control unit. The conveying unit conveys two sheets of the original one by one. The reading unit reads a sheet passing past a reading position. The detecting unit detects a sheet passing past a detection position upstream of the reading position in a conveying direction. The control unit controls the reading unit to start a reading process when a leading edge of sheet reaching a position upstream of the reading position by a first distance, controls the reading unit to stop the reading process when a trailing edge of sheet reaching a position downstream of the reading position by a second distance, determines an interspace between the trailing edge of sheet and a leading edge of a subsequently-conveyed sheet, and updates the first distance and the second distance based on the interspace.Type: GrantFiled: September 14, 2012Date of Patent: July 8, 2014Assignee: Brother Kogyo Kabushiki KaishaInventor: Toshiki Motoyama
-
Patent number: 8768101Abstract: A new optical imaging process for how to best fuse information from multiple target images into a single target image is described. The process has two primary components. First, rotating, translating and scaling each target image to register or calibrate them against a reference image and, second, determining weighing factors for each thus registered target image to select those images which add value to a final target image. The first component determines optimal rotational and translation matrices by a least squares measure using singular value decomposition. The second component determines weighing factors using correlations and statistical signal analysis techniques.Type: GrantFiled: June 30, 2011Date of Patent: July 1, 2014Assignee: The United States of America as represented by the Secretary of the Air ForceInventors: Daniel W. Repperger, Rodney G. Roberts, Alan R. Pinkus, Robert D. Sorkin
-
Patent number: 8768023Abstract: A method for determining an axial direction of a bore of a bone fixator includes the following steps: obtaining X-ray images of the bore, calculating perpendicular bisectors, determining spatial planes, and obtaining the axial direction of the bore. After X-ray images of the bore are taken from two X-ray source positions, two overlapping images of the bore are obtained for calculating two perpendicular bisectors therein respectively. Each perpendicular bisector and its corresponding X-ray source position define one spatial plane. The intersection of the two spatial planes defines the axial direction of the bore. Now that the axial direction of the bore can be derived from only two X-ray images of the bore taken during an orthopedic surgery, radiation exposure of the patient and of the medical personnel involved can be significantly reduced.Type: GrantFiled: November 16, 2012Date of Patent: July 1, 2014Assignee: National Central UniversityInventors: Ching-Shiow Tseng, Pei-Chun Chen, Hung-Kang Wu
-
Patent number: 8768096Abstract: A method and apparatus for estimating stereo misalignment using modified affine or perspective model. The method includes dividing a left frame and a right frame into blocks, comparing horizontal and vertical boundary signals in the left frame and the right frame, estimating the horizontal and the vertical motion vector for each block in a reference frame, selecting a reliable motion vectors from a set of motion vectors, dividing the selected block into smaller features, feeding the data to an affine or a perspective transformation model to solve for the model parameters, running the model parameters through a temporal filter, portioning the estimated misalignment parameters between the left frame and right frame, and modifying the left frame and the right frame to save some boundary space.Type: GrantFiled: November 17, 2011Date of Patent: July 1, 2014Assignee: Texas Instruments IncorporatedInventors: Ibrahim Ethem Pekkucuksen, Wei Hong, Aziz Umit Batur, Buyue Zhang
-
Patent number: 8761543Abstract: In various embodiments, systems and methods are provided for using an expanded image format to facilitate image transformations. The expanded image format can include at least a first set of boundaries and a second set of boundaries. The first set of boundaries corresponds to the image for transform, while the second set of boundaries provide a region beyond the image that can assist a graphics processing unit with performing a transform. Optionally, the expanded information can also include pixel value information for pixels in the region between the image boundary and the overboundary.Type: GrantFiled: August 30, 2011Date of Patent: June 24, 2014Assignee: Microsoft CorporationInventors: Jeffrey R. Bloomfield, Michael Vincent Oneppo, Stephen P. Proteau
-
Patent number: 8749571Abstract: An information processing section of a game apparatus executes a program for implementing a step S100 of acquiring a camera image; a step S200 of detecting a marker; a step S400 of calculating a position and an orientation of a virtual camera; a step S600 of generating an animation in which a hexahedron is caused to appear on the marker when the start of a game is requested; a step S800 of generating an animation in which the hexahedron is unfolded so as to position thereon virtual objects representing targets; a step S900 of mapping the photographed image on objects; a step S1000 of taking an image of the objects by means of the virtual camera; and a step S1100, S1200 of displaying the camera image and an object image which is superimposed on the camera image.Type: GrantFiled: October 29, 2010Date of Patent: June 10, 2014Assignees: Nintendo Co., Ltd., Hal Laboratory Inc.Inventor: Tetsuya Noge
-
Patent number: 8744216Abstract: An omnidirectional image processing apparatus enables the visibility of a specified monitoring object in an omnidirectional image to be improved while maintaining the continuity of that omnidirectional image. The omnidirectional image processing apparatus performs image processing on an omnidirectional image, and has a monitoring object specification section that specifies a monitoring object photographed in the omnidirectional image. The omnidirectional image processing apparatus also has an image rotating section that rotates the omnidirectional image so that the position of a specified monitoring object becomes upper-central, and a center position moving section that moves the center position of the omnidirectional image rotated by the image rotating section downward by means of warping processing.Type: GrantFiled: January 26, 2011Date of Patent: June 3, 2014Assignee: Panasonic CorporationInventors: Yuko Arai, Yuichiro Takemoto, Masataka Sugiura
-
Patent number: 8744195Abstract: A perimeter around a detected object in a frame of image data can be generated in a first coordinate system. The perimeter can be converted from the first coordinate system into a second coordinate system having the same aspect ratio as the first coordinate system. A first metadata entry can include dimensions of image data in the second coordinate system. A second metadata entry can provide a location and dimensions of the converted perimeter in the second coordinate space. Additional metadata can indicate matching objects between frames, position of an object relative to other objects in a frame, a probability that an object is correctly detected, and a total number of objects detected across multiple frames of image data.Type: GrantFiled: August 7, 2013Date of Patent: June 3, 2014Assignee: Apple Inc.Inventors: David William Singer, Courtney Ann Kennedy
-
Patent number: 8737768Abstract: A device for processing an input image may include a degree-of-symmetry calculation unit, which may be configured to receive the input image and calculate a degree of symmetry of the input image. The device may also include a parting line detection unit, which may be configured to receive the input image and detect a parting line that separates two sides of the input image. Additionally, the device may include a classification unit, which may be configured to classify the input image based on the degree of symmetry and the parting line. The classification unit may also be configured to generate a classification signal to cause at least one of display or storage of the classification.Type: GrantFiled: August 11, 2011Date of Patent: May 27, 2014Assignee: Sony CorporationInventor: Shinichiro Gomi
-
Publication number: 20140140609Abstract: In some implementations, a method rotates images based on image content to correct image orientation. In some implementations, a method includes obtaining one or more identifications of content depicted in an image and determining a current orientation of the content depicted in the image. The current orientation is determined based on the one or more identifications of the content. An amount of rotation for the image is determined that orients the content closer to a predetermined reference orientation than to the current orientation. The image is rotated by the determined amount.Type: ApplicationFiled: November 16, 2012Publication date: May 22, 2014Inventors: Aravind Krishnaswamy, Nicholas Butko
-
Patent number: 8731336Abstract: The present invention provides a method of correcting alignment of an image. The method includes identifying an image of a document, and detecting a plurality of lines within the image. The method also includes classifying at least a subset of the plurality of lines as either horizontal or vertical lines, and determining whether a variance exists within a subset of the plurality of lines. Furthermore, the method includes applying a corrective transformation to adjust the image, where the variance within the subset of the plurality of lines is at least partially reduced as compared to the variance prior to the application of the corrective transformation.Type: GrantFiled: December 14, 2011Date of Patent: May 20, 2014Assignee: Ancestry.com Operations Inc.Inventors: Jack Reese, Shawn Reid
-
Patent number: 8731335Abstract: A method and apparatus for correcting a rotation of a video frame are described. According to a method, an amount of the rotation of the video frame with respect to a reference is determined. The rotation of the video frame is corrected based at least in part on the detected amount of the rotation of the video frame.Type: GrantFiled: November 28, 2011Date of Patent: May 20, 2014Assignee: ATI Technologies ULCInventors: Yubao Zheng, Philip L. Swan
-
Patent number: 8724924Abstract: Systems and methods for matching a received image with a template image are disclosed herein. Such systems and methods can advantageously enable an image captured by a mobile device (such as a smartphone or digital camera) to be correctly identified by the processing application. In some embodiments, the received image is first resized in one or both dimensions in order to match or approximately match the dimensions of a given template. The received image and template image can then be superimposed. Next, an optimal translative transformation value can be calculated in order to generate a confidence level for the current possible match. After confidence levels for each template are generated and recorded, the template with the highest confidence level can be selected as the best match for the received image.Type: GrantFiled: March 15, 2013Date of Patent: May 13, 2014Assignee: Mitek Systems, Inc.Inventors: Grigori Nepomniachtchi, Vitali Kliatskine, Vladimir Kluzner
-
Patent number: 8724913Abstract: A method for decoding run-length encoded (RLE) data includes the steps of receiving the RLE data and storing a predetermined value (e.g., zero) in each of a plurality of consecutively-accessible storage locations of a buffer. The method further includes writing a first value different than the predetermined value to a first storage location based on the RLE data, jumping over (i.e., skipping) a number of the consecutively-accessible storage locations from the first storage location to a next storage location based on the RLE data, and writing a next value different than the predetermined value to the next storage location based on the RLE data. In the case of JPEG, the values stored in the storage locations of the buffer are quantized coefficients associated with a block of image data. A run-length decoder is also described.Type: GrantFiled: July 19, 2012Date of Patent: May 13, 2014Assignee: Omnivision Technologies, Inc.Inventor: Xuanming Du
-
Patent number: 8693807Abstract: A computer-implemented method may include receiving, over a network, an image from an image capture device, determining an image adjustment to the image, and communicating, over the network, the image adjustment to the image capture device.Type: GrantFiled: February 23, 2012Date of Patent: April 8, 2014Assignee: Google Inc.Inventors: Richard Carl Gossweiler, III, Shumeet Baluja, Maryam Kamvar
-
Patent number: 8687921Abstract: It is an object of the present invention is to provide an image processing technique that can detect the rotation of an observation image of a specimen with high accuracy. An image processing apparatus according to the present invention indirectly corrects a rotation gap between measurement image data and reference image data through wide-angle image data including a measurement part of a specimen (FIG. 1).Type: GrantFiled: March 25, 2011Date of Patent: April 1, 2014Assignee: Hitachi High-Technologies CorporationInventors: Shinichi Shinoda, Yasutaka Toyoda, Ryoichi Matsuoka
-
Patent number: 8687920Abstract: A method for the recognition of objects in at least one digital image includes: a) simulating from the digital image a plurality of digital rotations and at least two digital tilts different from 1 in order to develop a simulated image for each rotation-tilt pair; and b) applying an algorithm generating values that are invariant in translation, rotation and zoom onto the simulated images in order to determine so-called SIF (scale invariant features) local characteristics used for recognizing objects. The SIFT method can be used in step b.Type: GrantFiled: May 18, 2009Date of Patent: April 1, 2014Assignees: Ecole Polytechnique, Ecole Normale SuperieureInventors: Jean-Michel Morel, Guoshen Yu
-
Patent number: 8682080Abstract: In an image processing apparatus that determines tilt angles of an image, coordinates of points in the image are each transformed into a distance ? and an angle ?, and votes are cast to a vote table having the distance ? and the angle ? as headers. A predetermined number of points having numbers of votes ranked high are extracted from the vote table, and an extraction angle ?x is determined to achieve maximum consistency with angles ? at the predetermined number of points, and the tilt angles of the image are determined based on the determined extraction angle ?x.Type: GrantFiled: January 25, 2010Date of Patent: March 25, 2014Assignee: Murata Machinery, Ltd.Inventors: Toshiyuki Soutsuka, Tomoki Suruga
-
Patent number: 8670817Abstract: A liquid injector (400) injects a medical liquid into a patient whose fluoroscopic image data is to be picked up, and generates injection history data corresponding to the injection. A control box (500) allocates identification data associated with the fluoroscopic image data to the injection history data, and PACS (300) stores the fluoroscopic image data and the injection history data allocated with the identification data. The injection history data is also stored in association with the fluoroscopic image data to be stored, and hence the injection history data can also be confirmed when viewing the fluoroscopic image data.Type: GrantFiled: April 2, 2007Date of Patent: March 11, 2014Assignees: Resource One Inc, Nemoto Kyorindo Co., Ltd.Inventors: Masashi Goto, Shigeru Nemoto
-
Patent number: 8655081Abstract: To provide a lane recognition system which can improve the lane recognition accuracy by suppressing noises that are likely to be generated respectively in an original image and a bird's-eye image. The lane recognition system recognizes a lane based on an image. The system includes: a synthesized bird's-eye image creation module which creates a synthesized bird's-eye image by connecting a plurality of bird's-eye images that are obtained by transforming respective partial regions of original images picked up at a plurality of different times into bird's-eye images; a lane line candidate extraction module which detects a lane line candidate by using information of the original images or the bird's-eye images created from the original images, and the synthesized bird's-eye image; and a lane line position estimation module which estimates a lane line position based on information of the lane line candidate.Type: GrantFiled: January 8, 2009Date of Patent: February 18, 2014Assignee: NEC CorporationInventor: Kazuyuki Sakurai
-
Patent number: 8648871Abstract: An information processing section of a game apparatus executes a program for implementing a step S100 of acquiring a camera image; a step S200 of detecting a marker; a step S400 of calculating a position and an orientation of a virtual camera; a step S600 of generating an animation in which layed-flat surfaces of a hexahedron appear, and the hexahedron is folded so as to confine virtual objects representing targets therein when a stage is cleared; a step S800 of generating an animation in which the folded hexahedron is unfolded so as to position different virtual objects thereon; a step S900 of mapping the photographed image on objects; a step S1000 of taking an image of the objects by means of the virtual camera; and a step S1100, S1200 of displaying the camera image and an object image which is superimposed on the camera image.Type: GrantFiled: October 28, 2010Date of Patent: February 11, 2014Assignees: Nintendo Co., Ltd., HAL Laboratory Inc.Inventor: Tetsuya Noge
-
Patent number: 8649576Abstract: A method and system comprising: generating at least one slice image by carpeting a multitude of digital images based upon a two-dimensional (2-D) reference system, each of the multitude of digital images associated with a location in the 2-D reference system and each showing a representation of an arborization and/or landmark such that digital images not showing a representation of an arborization and/or landmark are excluded; carpeting the multitude of digital images together to create a slice image; aligning the slice image with other similarly created slice images using landmark information to determine the amount of 2-D rotation and/or translation to be applied to each slice image; vectorizing the representation of the arborization on each slice image, the vectorization creating a series of segments; assigning a type to at least one of the series of segments based on a unique characteristic of arborization; and grouping related segments together.Type: GrantFiled: June 15, 2007Date of Patent: February 11, 2014Assignee: George Mason Intellectual Properties, Inc.Inventors: Ruggero Scorcioni, Giorgio Ascoli, Bonnie Lasher