Using Dynamic Programming Or Elastic Templates (e.g., Warping) Patents (Class 382/215)
  • Patent number: 10346691
    Abstract: There is provided herein an apparatus and method for roadside asset tracking and maintenance monitoring having a mobile unit with data capture devices for capturing roadside asset imagery, global positioning system (GPS) receivers and data interfaces for communicating with an asset management server. As such, the apparatus may take roadside imagery for automated asset identification which may include utilising an asset type image recognition technique for automating the identification of the roadside assets.
    Type: Grant
    Filed: January 15, 2016
    Date of Patent: July 9, 2019
    Inventor: Norman Boyle
  • Patent number: 10147015
    Abstract: Provided is an image processing device that can suppress deterioration in the accuracy of identifying a subject, even in cases where the shape of the subject in an image is deformed. A feature amount calculation means 81 detects feature points from an image, and calculates, for each feature point, a local feature amount for the feature point on the basis of a peripheral region of said feature point, including said feature point. A correlation identifying means 82 specifies the correlation between feature points in a first image and feature points in a second image on the basis of the local feature amount of each feature point in the first image and the local feature amount of each feature point in the second image. A partial region detection means 83 detects, from one of the first image or the second image, partial regions each including a feature point in said image.
    Type: Grant
    Filed: April 24, 2015
    Date of Patent: December 4, 2018
    Assignee: NEC CORPORATION
    Inventor: Kyota Higa
  • Patent number: 9633274
    Abstract: A sensor acquires an input image X of a scene. The image includes noise with a variance ?2. A deep Gaussian conditional random field (GCRF) network is applied to the input image to produce an output image Y, where the output image is denoised, and wherein the deep GCRF includes a prior generation (PgNet) network followed by an inference network (InfNet), wherein the PgNet produces patch covariance priors ?ij for patches centered on every pixel (i,j) in the input image, and wherein the InfNet is applied to the patch covariance priors and the input image to solve the GCRF.
    Type: Grant
    Filed: September 15, 2015
    Date of Patent: April 25, 2017
    Assignee: Mitsubishi Electric Research Laboratories, Inc.
    Inventors: Oncel Tuzel, Ming-Yu Liu, Raviteja Vemulapalli
  • Patent number: 9384729
    Abstract: The application provides a method and system for determinism in non-linear systems for speech processing, particularly automatic speech segmentation for building speech recognition systems. More particularly, the application enables a method and system for detecting boundary of coarticulated units from isolated speech using recurrence plot.
    Type: Grant
    Filed: July 18, 2012
    Date of Patent: July 5, 2016
    Assignee: Tata Consultancy Services Limited
    Inventors: Mohd Bilal Arif Syed, Arijit Sinharay, Tanushyam Chattopadhyay
  • Patent number: 9323865
    Abstract: A method is provided for content alignment. The method includes obtaining a first content sequence and a second content sequence different from the first content sequence. The method also includes representing each of the first content sequence and the second content sequence in a hierarchical structure containing an ordered root element sequence and a sub-tree structure. The ordered root element sequence includes a plurality of root elements and each root element is associated with a sub-tree of elements. The method also includes determining a desired alignment between the first content sequence and the second content sequence using dynamic programming, and outputting results of the desired alignment between the first content sequence and the second content sequence.
    Type: Grant
    Filed: December 24, 2013
    Date of Patent: April 26, 2016
    Assignee: TCL RESEARCH AMERICA INC.
    Inventors: Hao Ding, Jia Huang, Haohong Wang
  • Patent number: 9031357
    Abstract: A temporal information integration dis-occlusion system and method for using historical data to reconstruct a virtual view containing an occluded area. Embodiments of the system and method use temporal information of the scene captured previously to obtain a total history. This total history is warped onto information captured by a camera at a current time in order to help reconstruct the dis-occluded areas. The historical data (or frames) from the total history match only a portion of the frames contained in the captured information. This warping yields warped history information. Warping is performed by using one of two embodiments to match points in an estimation of the current information to points in the captured information. Next, regions of current information are split using a classifier. The warped history information and the captured information then are merged to obtain an estimate for the current information and the reconstructed virtual view.
    Type: Grant
    Filed: May 4, 2012
    Date of Patent: May 12, 2015
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Philip Andrew Chou, Cha Zhang, Zhengyou Zhang, Shujie Liu
  • Patent number: 8983206
    Abstract: A visual quality assessment method and system are based on deriving a quality metric by comparing sub-band approximations of a distorted image and an undistorted version of the same image, providing a good compromise between computational complexity and accuracy. The sub-band approximations are derived from Discrete Wavelet (Haar) transforms of small image blocks of each image. Due to inherent symmetries, the wavelet transform is “blind” to certain types of distortions. But the accuracy of the method is enhanced, and the blindness of the transform is overcome, by computing quality metrics for the distorted image as well as computing quality metrics for a shifted version of the distorted image and combining the results.
    Type: Grant
    Filed: May 3, 2012
    Date of Patent: March 17, 2015
    Assignee: Ecole de Techbologie Superieure
    Inventors: Stephane Coulombe, Soroosh Rezazadeh
  • Patent number: 8897576
    Abstract: Candidate points belonging to a predetermined structure are extracted from image data DV. A shape model which represents a known shape of the predetermined structure and is formed by model labels having a predetermined connection relationship is obtained. Corresponding points corresponding to the model labels are selected from the extracted candidate points under the following constraints: (a) each model label is mapped with only one of the candidate points or none of the candidate points; (b) each candidate point is mapped with only one of the model labels or none of the model labels; and (c) when a path between two candidate points which are mapped with each pair of the model labels connected with each other is determined, each candidate point which is mapped with none of the model labels is included in only one of the determined paths or none of the determined paths.
    Type: Grant
    Filed: September 25, 2012
    Date of Patent: November 25, 2014
    Assignee: FUJIFILM Corporation
    Inventor: Yoshiro Kitamura
  • Publication number: 20140321758
    Abstract: A novel technique for unsupervised feature selection is disclosed. The disclosed methods include automatically selecting a subset of a feature of an image. Additionally, the selection of the subset of features may be incorporated with a congealing algorithm, such as a least-square-based congealing algorithm. By selecting a subset of the feature representation of an image, redundant and/or irrelevant features may be reduced or removed, and the efficiency and accuracy of least-square-based congealing may be improved.
    Type: Application
    Filed: July 3, 2014
    Publication date: October 30, 2014
    Inventors: Xiaoming Liu, Peter Henry Tu, Ya Xue
  • Publication number: 20140321757
    Abstract: A video frame compression system includes a rendering engine that provides a current video frame and current additional rendering information. Additionally, the video frame compression system includes a warping engine that generates a warped video frame, wherein the warped video frame is a transformation of a previous video frame that is based on the current additional rendering information. Further, the video frame compression system includes a video encoder that compresses the current video frame by using the warped video frame as a reference frame and separately compresses the current additional rendering information. Still further, the video frame compression system includes a packetizer that provides main and auxiliary data streams corresponding to the compressed current video frame and the compressed current additional rendering information, respectively. A video frame decompression system and methods of video frame compression and decompression are also provided.
    Type: Application
    Filed: April 26, 2013
    Publication date: October 30, 2014
    Applicant: Nvidia Corporation
    Inventors: Hassane S Azar, Dawid Pajak, Stefan Eckart, Swagat Mohapatra
  • Patent number: 8860813
    Abstract: A computer-implemented method for matching objects is disclosed. At least two images where one of the at least two images has a first target object and a second of the at least two images has a second target object are received. At least one first patch from the first target object and at least one second patch from the second target object are extracted. A distance-based part encoding between each of the at least one first patch and the at least one second patch based upon a corresponding codebook of image parts including at least one of part type and pose is constructed. A viewpoint of one of the at least one first patch is warped to a viewpoint of the at least one second patch. A parts level similarity measure based on the view-invarient distance measure for each of the at least one first patch and the at least one second patch is applied to determine whether the first target object and the second target object are the same or different objects.
    Type: Grant
    Filed: December 11, 2012
    Date of Patent: October 14, 2014
    Assignee: SRI International
    Inventors: Sang-Hack Jung, Ajay Divakaran, Harpreet Singh Sawhney
  • Publication number: 20140270544
    Abstract: In one embodiment, an image editing method, comprising: defining a region as a foreground object and a remaining region as background; applying an image warping process to a predefined object region, wherein a distortion to at least the remaining region occurs based on the image warping process applied to the predefined object region; responsive to the image warping process, determining a region to be repaired, the region to be repaired comprising a missing background; repairing the region to be repaired based on an inpainting process; and generating a repaired image by combining the predefined object region to which the image warping process is applied, one or more non-distorted regions, and the repaired region.
    Type: Application
    Filed: October 9, 2013
    Publication date: September 18, 2014
    Applicant: Cyberlink Corp.
    Inventors: Chia-En Chiang, Ho-Chao Huang, Chia-Chen Kuo
  • Patent number: 8830347
    Abstract: A method for aligning and unwarping distorted images in which lens profiles for a variety of lens and camera combinations are precomputed. Metadata stored with images is used to automatically determine if a set of component images include an excessive amount of distortion, and if so the metadata is used to determine an appropriate lens profile and initial unwarping function. The initial unwarping function is applied to the coordinates of feature points of the component images to generate substantially rectilinear feature points, which are used to estimate focal lengths, centers, and relative rotations for pairs of the images. A global nonlinear optimization is applied to the initial unwarping function(s) and the relative rotations to generate optimized unwarping functions and rotations for the component images. The optimized unwarping functions and rotations may be used to render a panoramic image.
    Type: Grant
    Filed: February 1, 2013
    Date of Patent: September 9, 2014
    Assignee: Adobe Systems Incorporated
    Inventor: Hailin Jin
  • Patent number: 8818131
    Abstract: Three dimensional models corresponding to a target image and a reference image are selected based on a set of feature points defining facial features in the target image and the reference image. The set of feature points defining the facial features in the target image and the reference image are associated with corresponding 3-dimensional models. A 3D motion flow between the 3-dimensional models is computed. The 3D motion flow is projected onto a 2D image plane to create a 2D optical field flow. The target image and the reference image are warped using the 2D optical field flow. A selected feature from the reference image is copied to the target image.
    Type: Grant
    Filed: November 24, 2010
    Date of Patent: August 26, 2014
    Assignee: Adobe Systems Incorporated
    Inventors: Jue Wang, Elya Shechtman, Lubomir D. Bourdev, Fei Yang
  • Patent number: 8787649
    Abstract: A system and a method for indicating at least one of the internal structures of an organ on an X-ray image are proposed. The system includes an interface adapted to receive the X-ray image and a non-X-ray image pertaining to the organ. The system also includes a database having a geometric model of the internal structures of the organ, a first module for determining at least a dimension of one of the internal structures of the organ from the non-X-ray image, and a second module for indicating the at least one of the internal structures of the organ in the X-ray image based on the geometric model adjusted by the at least one dimension.
    Type: Grant
    Filed: June 20, 2012
    Date of Patent: July 22, 2014
    Assignee: Siemens Aktiengesellschaft
    Inventor: Rajendra Prasad Jadiyappa
  • Patent number: 8726324
    Abstract: An apparatus and method for identifying image capture opportunities. Expert photo agents (526) that process metadata extracted from a captured image are obtained (706) at a user-device (102). Metadata (214) characterizing visual content of a captured image is produced (310) by processing the visual content of the captured image. Image capture opportunities are selected (410) based upon processing of the metadata with the at least one expert photo agent. The image capture opportunity selection specifies content to capture in a subsequent image.
    Type: Grant
    Filed: March 27, 2009
    Date of Patent: May 13, 2014
    Assignee: Motorola Mobility LLC
    Inventors: Thomas Michael Tirpak, Anant Athale
  • Publication number: 20140086494
    Abstract: The invention is related to a method for registering at least one part of a first image and of a second image, including the steps of providing a first image of the real environment and a coordinate system associated to the first image, a second image of the real environment, and measurements of orientation and/or distance of a capturing device with respect to the real environment while capturing the second image. A collineation warping function is then determined from the measurements associated to at least one part of the second image.
    Type: Application
    Filed: March 23, 2011
    Publication date: March 27, 2014
    Applicant: METAIO GMBH
    Inventors: Selim Benhimane, Daniel Kurz
  • Patent number: 8666172
    Abstract: Input image data may be subjected to a spatial convolution to produce a plurality of different filter matrices or kernels. Thus, a single system may be capable of producing a plurality of different filter sizes which may be selected based on particular circumstances, uses and described precision. Thus, a single system may provide variable spatial filtering. By reducing the input data matrix size and by reusing components, in some cases, the computational complexity of producing a plurality of symmetrical filters is not significantly greater than that involved in producing only a single filter.
    Type: Grant
    Filed: March 29, 2001
    Date of Patent: March 4, 2014
    Assignee: Intel Corporation
    Inventor: Dean Rosales
  • Patent number: 8666170
    Abstract: It is provided a computer system for matching between images/graphs comprising a processing unit, a storage unit, an input unit and a data recording unit, wherein the computer system includes a feature pattern generating unit for generating a set of feature patterns of the image and the graph from the received image and the received graph, segmenting each of the image and the graph into a plurality of regions centered on a sample point, and determining characteristics of the plurality of regions; a correspondence computing unit for computing correspondence between the image and the graph to be matched by comparing the generated feature patterns; a transform unit for transforming a coordinate system of at least one of the image and the graph to be matched; and a combination unit for combining the image and the graph that have been subjected to the transform of the coordinate system.
    Type: Grant
    Filed: February 18, 2011
    Date of Patent: March 4, 2014
    Assignee: Hitachi, Ltd.
    Inventor: Tao Guo
  • Patent number: 8649555
    Abstract: A computer program product tangibly embodied in a computer-readable storage medium includes instructions that when executed by a processor perform a method. The method includes identifying a frame of a video sequence, transforming a model into an initial guess for how the region appears in the frame, performing an exhaustive search of the frame, performing a plurality of optimization procedures, wherein at least one additional model parameter is taken into account as each subsequent optimization procedure is initiated. A system includes a computer readable storage medium, a graphical user interface, an input device, a model for texture and shape of the region, the model generated using the video sequence and stored in the computer readable storage medium, and a solver component.
    Type: Grant
    Filed: October 28, 2009
    Date of Patent: February 11, 2014
    Assignee: Lucasfilm Entertainment Company Ltd.
    Inventors: Christoph Bregler, Kiran S. Bhat, Brett A. Allen
  • Patent number: 8649609
    Abstract: An apparatus is provided that includes a plurality of modules, a plurality of memory banks, and a multiplexor. Each module includes at least one agent that interfaces between a module and a memory bank. Each memory bank includes an arbiter that interfaces between the at least one agent of each module and the memory bank. The multiplexor is configured to assign data paths between the at least one agent of each module and a corresponding arbiter of each memory bank based on the assigned data path. The at least one agent of each module is configured to read data from the corresponding arbiter of the memory bank or write modified data to the corresponding arbiter of the memory bank.
    Type: Grant
    Filed: March 24, 2011
    Date of Patent: February 11, 2014
    Assignee: The United States of America as Represented by the Adminstrator of the National Aeronautics and Space Administration
    Inventors: Arin C Morfopoulos, Thang D Pham
  • Patent number: 8644611
    Abstract: A method for text recognition includes generating a number of text hypotheses for an image, for example, using an HMM based approach using fixed-width analysis features. For each text hypothesis, one or more segmentations are generated and scored at the segmental level, for example, according to character or character group segments of the text hypothesis. In some embodiments, multiple alternative segmentations are considered for each text hypothesis. In some examples, scores determined in generating the text hypothesis and the segmental score are combined to select an overall text recognition of the image.
    Type: Grant
    Filed: June 3, 2009
    Date of Patent: February 4, 2014
    Assignee: Raytheon BBN Technologies Corp.
    Inventors: Premkumar Natarajan, Rohit Prasad, Richard Schwartz, Krishnakumar Subramanian
  • Patent number: 8625840
    Abstract: Described are a method and an apparatus for generating a forecast weather image such as a forecast weather radar image. The method uses filters to approximate viscous alignment and to thereby determine displacement fields having meaningful structure. In various embodiments a power-law energy spectrum is utilized for deformations in the displacement field through the application of a set of Gabor filters. The Gabor filters are applied in a sequential manner to gradient error images and values of modes of motions corresponding to the Gabor filters are determined. The values are used to generate the displacement field which can then be applied to an existing weather image to generate a forecast weather image.
    Type: Grant
    Filed: February 14, 2012
    Date of Patent: January 7, 2014
    Assignee: Massachusetts Institute of Technology
    Inventors: Srinivas Ravela, William J. Dupree, Timothy R. Langlois, Marilyn M. Wolfson, Christopher M. Yang
  • Publication number: 20130336589
    Abstract: The present technology relates to an image processing apparatus, an image processing method, and a program capable of improving the image quality of decoded images of images from multiple viewpoints. A warping unit 461 warps a picture of an image of a viewpoint #1 between the image of the viewpoint #1 and an image of a viewpoint #2 different of the viewpoint #1 to generate a picture of a warped image obtained by converting the picture of the image of the viewpoint #1 into an image obtainable in the viewpoint #2. A disparity prediction unit 463 acquires, from header information, a reference index indicating a reference picture that is referred to generate a predicted image of an object block to be decoded of a picture of the image of the viewpoint #2, and selects the reference picture from among reference picture candidates including at least the picture of the warped image based on the reference index.
    Type: Application
    Filed: February 28, 2012
    Publication date: December 19, 2013
    Applicant: Sony Corporation
    Inventors: Yoshitomo Takahashi, Shinobu Hattori
  • Patent number: 8509543
    Abstract: A subject tracking device includes: an input unit that sequentially inputs input images; an arithmetic operation unit that calculates a first similarity level between an initial template image and a target image and a second similarity level between an update template image and the target image; a position determining unit that determines a subject position based upon at least one of the first and the second similarity level; a decision-making unit that decides whether or not to update the update template image based upon the first and the second similarity level; and an update unit that generates a new update template image based upon the initial template image multiplied by a first weighting coefficient and the target image multiplied by a second weighting coefficient, and updates the update template image with the newly generated update template image, if the update template image is decided to be updated.
    Type: Grant
    Filed: June 2, 2010
    Date of Patent: August 13, 2013
    Assignee: Nikon Corporation
    Inventor: Yuichi Ito
  • Patent number: 8483472
    Abstract: A paper sheet identification apparatus capable of identifying an authenticity of a watermark area formed on a paper sheet is provided without increasing the cost. The paper sheet identification apparatus includes: a light receiving part receiving reflected light from a watermarked image formed on a paper sheet to be conveyed, a converter converting the reflected light from the watermarked image received by the light receiving part for each pixel as a unit of a predetermined size including color information having brightness; and an identification processing part identifying the authenticity of the watermarked image based on a correlation coefficient, which is calculated from a density value for each pixel converted by the converter and a density value for each pixel by the transmitted light from the watermarked image of the bill serving as a reference.
    Type: Grant
    Filed: January 30, 2009
    Date of Patent: July 9, 2013
    Assignee: Universal Entertainment Corporation
    Inventor: Kunihiro Manabe
  • Patent number: 8437502
    Abstract: Per one embodiment, a method is provided for refining a pose estimate of a model. The model is coarsely aligned with a run-time image, and it represents a 2D pattern. The pose estimate includes at least one pose estimate parameter. The model has a plurality of model features, and the run-time image has a plurality of run-time features. A given distance value is determined representing a given distance between a given one of the plurality of the model features mapped by a given pose estimate and a corresponding given run-time feature. A two-dimensional model description of the two-dimensional model pattern is provided. The two-dimensional model pattern is mapped using the given pose estimate to create a transformed version of the two-dimensional model pattern. The transformed version represents a non-linear movement of at least portions of the two-dimensional model pattern in a direction orthogonal to a plane of the two-dimensional model description.
    Type: Grant
    Filed: September 25, 2004
    Date of Patent: May 7, 2013
    Assignee: Cognex Technology and Investment Corporation
    Inventors: Matheen Siddiqui, Jason Davis
  • Patent number: 8406486
    Abstract: To provide an inter-pattern feature corresponding device (1) for determining a feature correspondence relationship with high accuracy even if a pattern to be collated has distortion.
    Type: Grant
    Filed: December 19, 2008
    Date of Patent: March 26, 2013
    Assignee: NEC Corporation
    Inventor: Huang Lei
  • Patent number: 8385629
    Abstract: The present invention provides a band-pass filter, being capable of fitting a frequency spectrum area having phase information in a frequency spectrum image, to obtain a spectrum information corresponding to the phase information during the process of obtaining the phase information from the frequency spectrum image with respect to an object's surface profile. In another embodiment, the present invention further provides a method to optimize the spectrum range of the band-pass filter so as to enhance measuring accuracy and efficiency while restoring the surface of the object. In addition, by employing the foregoing method, the present invention further provides a measurement system for measuring three-dimensional surface shapes in which a deformed fringe pattern with respect to the measured object's surface is acquired and the phase information is obtained from the fringe pattern according to the foregoing method so as to restore the surface profile of the measured object.
    Type: Grant
    Filed: July 29, 2009
    Date of Patent: February 26, 2013
    Assignee: National Taipei University of Technology
    Inventors: Liang-Chia Chen, Hsuan-Wei Ho
  • Patent number: 8368773
    Abstract: A method for aligning and unwarping distorted images in which lens profiles for a variety of lens and camera combinations are precomputed. Metadata stored with images is used to automatically determine if a set of component images include an excessive amount of distortion, and if so the metadata is used to determine an appropriate lens profile and initial unwarping function. The initial unwarping function is applied to the coordinates of feature points of the component images to generate substantially rectilinear feature points, which are used to estimate focal lengths, centers, and relative rotations for pairs of the images. A global nonlinear optimization is applied to the initial unwarping function(s) and the relative rotations to generate optimized unwarping functions and rotations for the component images. The optimized unwarping functions and rotations may be used to render a panoramic image.
    Type: Grant
    Filed: August 29, 2008
    Date of Patent: February 5, 2013
    Assignee: Adobe Systems Incorporated
    Inventor: Hailin Jin
  • Publication number: 20130016914
    Abstract: Performing word recognition operations to determine what an image of a word represents. The method includes accessing a first image. The first image represents an image version of a word. The method further includes accessing a second image. The second image also represents an image version of a word. Using a warp mesh, the method includes warping the second image to cause the second image to approximately match the first image by applying a mesh to the second image and moving vertices of the mesh to warp the second image. The difference between the warped second image and the unwarped first image are determined.
    Type: Application
    Filed: July 10, 2012
    Publication date: January 17, 2013
    Applicant: BRIGHAM YOUNG UNIVERSITY
    Inventors: Douglas J. Kennard, William Arthur Barrett, Thomas Warren Sederberg
  • Patent number: 8335382
    Abstract: A method and system for increasing the certainty of a silhouette matching process, where the process is being used for attitude determination of an object of interest, for example an aircraft. The method involves using one or more mask images that include structure or features that may or may not always be associated with the object of interest, and overlaying the mask image(s) onto a library image of the aircraft. Each pixel of the library image is compared against corresponding pixels of the mask image(s) to determine which pixels represent ambiguous areas of the library image. Those pixels are eliminated from consideration in determining a Fit score, where the Fit score represents a percentage value indicative of a certainty of the matching process in identifying the attitude of the aircraft. The method and system is applicable to a wide ranging variety of object detection applications.
    Type: Grant
    Filed: May 18, 2007
    Date of Patent: December 18, 2012
    Assignee: The Boeing Company
    Inventors: Thomas P. Weismuller, David L. Caballero
  • Patent number: 8295613
    Abstract: Disclosed is a method for determining the absence or presence of one or more instances of a predetermined pattern in an image, and for determining the location of each found instance within a multidimensional space. A model represents the pattern to be found, the model including a plurality of probes. Each probe represents a relative position at which a test is performed in an image at a given pose, each such test contributing evidence that the pattern exists at the pose. The method further includes a comparison of the model with a run-time image at each of a plurality of poses. A match score is computed at each pose to provide a match score surface. Then, the match score is compared with an accept threshold, and used to provide the location any instances of the pattern in the image.
    Type: Grant
    Filed: December 31, 2004
    Date of Patent: October 23, 2012
    Assignee: Cognex Corporation
    Inventors: William M. Silver, E. John McGarry, Sanjay Nichani, Adam Wagman
  • Patent number: 8295604
    Abstract: An image search method that is robust and fast (with computational complexity of logarithmic order relative to the number of models). The image search method including: extracting a plurality of specific regions possessing such a property that a shape can be normalized regardless of an affine transformation thereof, as affine-invariant regions from one or more learning images; calculating, with respect to a reference affine-invariant region, other neighboring affine-invariant regions as a set; deforming the neighboring affine-invariant regions by a transformation to normalize the shape of the reference affine-invariant region; and outputting the deformed shapes of the neighboring affine-invariant regions, together with combination of the reference affine-invariant region and the neighboring affine-invariant regions.
    Type: Grant
    Filed: August 31, 2006
    Date of Patent: October 23, 2012
    Assignees: Toyota Jidosha Kabushiki Kaisha, Czech Technical University in Prague
    Inventors: Katsuhiro Sakai, Ondrej Chum, Jiri Matas
  • Patent number: 8295614
    Abstract: A 2D model fitting means 1201 estimates values of parameters optimum to generate a probe model image similar to a probe image and a gallery model image similar to a gallery image with an image variation model 1204. At that time, among a plurality of parameters of the image variation model 1204, the value of a parameter of which sameness between the probe image and the gallery image is to be judged as a target parameter is set to be the same for both images. A model goodness-of-fit evaluation means 1202 computes a model goodness of fit for the probe model image and the gallery model image to the probe image and the gallery image under the estimated parameters. A collation means 1203 compares the model goodness of fit with a threshold value to judge the sameness between the probe image and the gallery image.
    Type: Grant
    Filed: April 12, 2007
    Date of Patent: October 23, 2012
    Assignee: NEC Corporation
    Inventor: Rui Ishiyama
  • Patent number: 8289340
    Abstract: A method for creating a coordinated image display by designing a digital template for the image display. The template includes a number of openings for displaying digital images. Each of the openings has at least one stored required image attribute that must be satisfied to a programmed degree according to the artistic design of the template. A template recipe includes an image attribute for a dependent opening, which means that it's defined to be dependent upon at least one image attribute of an image in another opening of the template. The computer system automatically searches an image database for an image satisfying the required image attribute for the dependent opening. If a user of the computer system manually replaces or modifies an image upon which another image depends, the computer system will automatically search the image database for a new image that satisfies the required dependency upon the replaced or modified image, if necessary.
    Type: Grant
    Filed: July 30, 2009
    Date of Patent: October 16, 2012
    Assignee: Eastman Kodak Company
    Inventors: Raymond W. Ptucha, Laura R. Whitby, William Bogart
  • Patent number: 8274523
    Abstract: A method for creating an artistically coordinated image display. A digital template is provided for said image display and it includes of openings for placing images each having at least one required attribute for an image. A programmed computer system automatically searches a database of images for images to be placed in the openings and each of the images satisfy the openings required image attributes. One or more vertical and horizontal lines are demarcated in the so that subjects in the image can be placed on the lines or their intersecting points by modifying and shifting the image appropriately. A subject of the image can also be measured and its size can be set as a reference measurement unit to assist in aesthetically placing subjects proportionally within the image.
    Type: Grant
    Filed: July 30, 2009
    Date of Patent: September 25, 2012
    Assignee: Eastman Kodak Company
    Inventors: Raymond W. Ptucha, Laura R. Whitby, William Bogart
  • Patent number: 8260059
    Abstract: The present invention provides a system and method for detecting deformable objects in images even in the presence of partial occlusion, clutter and nonlinear illumination changes. A holistic approach for deformable object detection is disclosed that combines the advantages of a match metric that is based on the normalized gradient direction of the model points, the decomposition of the model into parts and a search method that takes all search results for all parts at the same time into account. Despite the fact that the model is decomposed into sub-parts, the relevant size of the model that is used for the search at the highest pyramid level is not reduced. Hence, the present invention does not suffer the speed limitations of a reduced number of pyramid levels that prior art methods have.
    Type: Grant
    Filed: May 5, 2008
    Date of Patent: September 4, 2012
    Assignee: MVTec Software GmbH
    Inventors: Andreas Hofhauser, Carsten Steger
  • Patent number: 8249362
    Abstract: Disclosed is a method for determining the absence or presence of one or more instances of a predetermined pattern in an image, and for determining the location of each found instance within a multidimensional space. A model represents the pattern to be found, the model including a plurality of probes. Each probe represents a relative position at which a test is performed in an image at a given pose, each such test contributing evidence that the pattern exists at the pose. The method further includes a comparison of the model with a run-time image at each of a plurali of poses. A match score is computed at each pose to provide a match score surface. Then, the match score is compared with an accept threshold, and used to provide the location any instances of the pattern in the image.
    Type: Grant
    Filed: December 31, 2004
    Date of Patent: August 21, 2012
    Assignee: Cognex Corporation
    Inventors: William M. Silver, E. John McGarry
  • Patent number: 8238627
    Abstract: The method is for the identification and characterization of structures in electron micrographs. Structures in a first image are selected. The structures have a first shape type deformed in a first direction. The selected structures are transformed to a second shape type different from the first shape type. The transformed structures of the second shape type are used to form a plurality of templates. A new structure in a second image is identified. The new structure has the first shape type. The second shape type structure of each template is deformed in the first direction. It is determined which template is a preferred template that best matches the new structure.
    Type: Grant
    Filed: September 12, 2006
    Date of Patent: August 7, 2012
    Assignee: Intelligent Virus Imaging Inc.
    Inventors: Mohammed Homman, Martin Ryner
  • Patent number: 8208694
    Abstract: There is described a system and a method for generating a metatag indicative of an attribute of a person represented in an image, the method comprising: performing a computer-based analysis of the image; identifying a feature related to the attribute of the person in the image using results from the computer-based analysis; generating the metatag based on the identified feature; and associating the metatag to the image, the metatag being thereby related to the attribute of the person.
    Type: Grant
    Filed: June 6, 2007
    Date of Patent: June 26, 2012
    Inventors: Thomas Jelonek, Peter Whaite, René Saint-Pierre
  • Patent number: 8184909
    Abstract: A method for comparing a plurality of geometrical data representations each representing a spatial boundary surface of a corresponding geometrical object which surface changes over a selected extent of the object bounded thereby through providing the plurality of geometrical data representations on a common format basis, including scaling so as to each to have a common selected extent, to thereby result in a plurality of standardized spatial boundary surface geometrical data representations and comparing them at a plurality of matching section locations along each of the common extents at each of which there is a section outline curve representations. Comparing selected features of the commonly scaled section outline curve representations for such representations at corresponding ones of the selected matched section locations provides a basis for determining similarity therebetween.
    Type: Grant
    Filed: June 25, 2008
    Date of Patent: May 22, 2012
    Assignee: United Technologies Corporation
    Inventors: Michael S. Miarecki, Jeffrey D. Lancaster
  • Patent number: 8135199
    Abstract: Methods and apparatuses process images. The method according to one embodiment accesses digital image data representing an image including an object; accesses reference data including a shape model relating to shape variation of objects from a baseline object, the objects and the baseline object being from a class of the object; and removes from the image an element not related to the object, by representing a shape of the object using the shape model.
    Type: Grant
    Filed: December 19, 2006
    Date of Patent: March 13, 2012
    Assignee: Fujifilm Corporation
    Inventor: Daniel Russakoff
  • Patent number: 8121347
    Abstract: A system and method for tracking features, e.g., facial features, is provided, which allows for the tracking of features which move in a series of images and whose shape changes nonlinearly due to perspective projection and complex 3D movements. A training set of images is processed to produce clustered shape subspaces corresponding to the set of images, such that non-linear shape manifolds in the images are represented as piecewise, overlapping linear surfaces that are clustered according to similarities in perspectives. A landmark-based training algorithm (e.g., ASM) is applied to the clustered shape subspaces to train a model of the clustered shape subspaces and to create training data.
    Type: Grant
    Filed: December 12, 2007
    Date of Patent: February 21, 2012
    Assignee: Rutgers, The State University of New Jersey
    Inventors: Dimitris Metaxas, Atul Kanaujia
  • Patent number: 8094895
    Abstract: A method for selecting vertices for performing deformable registration of imaged objects is provided. The selected vertices form corresponding pairs, each pair including a vertex from a first imaged object and a vertex from a second imaged object. The corresponding vertex pairs are sorted in order of distance between the vertices making up the corresponding vertex pair. The corresponding vertex pair with the greatest distance is given top priority. Corresponding vertex pairs that lie within a selected distance from the selected corresponding vertex pair are discarded. In this manner, the number of vertex pairs used for deformable registration of the imaged objects is reduced and therefore allows for processing times that are clinically acceptable.
    Type: Grant
    Filed: May 31, 2006
    Date of Patent: January 10, 2012
    Assignee: Koninklijke Philips Electronics N.V.
    Inventors: Michael Kaus, Todd McNutt, Vladimir Pekar
  • Patent number: 8027538
    Abstract: Methods and apparatus, including systems and computer program products, for creating high dynamic range images. One method includes actions of establishing a current set of digital image; displaying a high dynamic range image and information identifying the current set of images, the high dynamic range image being computed from the current set of images; and repeatedly, as long as the user provides user input changing the current set of images, receiving user input changing the current set of images and in response to each user input displaying a high dynamic range image and information identifying the current set of images, where the high dynamic range image is computed from the current set of images.
    Type: Grant
    Filed: February 5, 2010
    Date of Patent: September 27, 2011
    Assignee: Adobe Systems Incorporated
    Inventor: John W. Peterson
  • Patent number: 7933464
    Abstract: A scene-based non-uniformity correction method super-resolution for eliminating fixed pattern noise in a video having a plurality of input images is disclosed, comprising the steps of warping each of the plurality of images with respect to a reference image to obtain a warped set of images; performing one of averaging and deblurring on the warped set of images to obtain an initial estimate of a reference true scene frame; warping the initial estimate of the reference true scene frame with respect to each of the plurality of images to obtain a set of estimated true signal images; performing a least square fit algorithm to estimate a gain image and an offset image given the set of estimated true signal images; applying the estimated gain image and estimated offset image to the plurality of images to obtain a clean set of images; and applying a super-resolution algorithm to the clean set of images to obtain a higher resolution version of the reference true scene frame.
    Type: Grant
    Filed: October 16, 2007
    Date of Patent: April 26, 2011
    Assignee: SRI International
    Inventors: Chao Zhang, Wenyl Zhao
  • Patent number: 7907768
    Abstract: Methods and an apparatus process images. The method according to one embodiment accesses digital image data representing a plurality of objects with a plurality of features; generates a shape model for shapes of the plurality of objects, the step of generating a shape model including generating a baseline object by aligning the plurality of objects, and determining deformation modes to describe shape deformations between shapes of the plurality of objects and the baseline object; performs shape registration for the plurality of objects by fitting shapes of the plurality of objects using combinations of the deformation modes, to obtain registered shapes; and generates a probabilistic atlas by mapping the plurality of features from the plurality of objects to the baseline object, using the registered shapes for the plurality of objects.
    Type: Grant
    Filed: December 19, 2006
    Date of Patent: March 15, 2011
    Assignee: Fujifilm Corporation
    Inventor: Daniel Russakoff
  • Patent number: 7885455
    Abstract: A method of producing an enhanced Active Appearance Model (AAM) by combining images of multiple resolutions is described herein. The method generally includes processing a plurality of images each having image landmarks and each image having an original resolution level. The images are down-sampled into multiple scales of reduced resolution levels. The AAM is trained for each image at each reduced resolution level, thereby creating a multi-resolution AAM. An enhancement technique is then used to refine the image landmarks for training the AAM at the original resolution level. The landmarks for training the AAM at each level of reduced resolution is obtained by scaling the landmarks used at the original resolution level by a ratio in accordance with the multiple scales.
    Type: Grant
    Filed: January 5, 2007
    Date of Patent: February 8, 2011
    Assignee: UTC Fire & Security Americas Corporation, Inc
    Inventors: Xiaoming Liu, Frederick Wilson Wheeler, Peter Henry Tu
  • Patent number: 7853085
    Abstract: A method and system for detecting a source multifeatured three-dimensional object from two-dimensional source imagery, and for locating a best-matching three-dimensional object from a candidate database of such objects by performing a viewpoint and lighting invariant search among the candidate objects. The invention further includes the method and system for determining the optimally-fitting viewpoint, lighting, and deformation of the located three-dimensional candidate and basing an identification of the candidate with the source on the quality of fit between projections of the candidate and the source imagery.
    Type: Grant
    Filed: March 5, 2004
    Date of Patent: December 14, 2010
    Assignee: Animetrics, Inc.
    Inventor: Michael Miller