Morphological Operations (i.e., Local Neighborhood Operations) Patents (Class 382/308)
  • Patent number: 10198636
    Abstract: A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and/or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.
    Type: Grant
    Filed: March 14, 2018
    Date of Patent: February 5, 2019
    Inventors: John Eric Eaton, Wesley Kenneth Cobb, Dennis G. Urech, David S. Friedlander, Gang Xu, Ming-Jung Seow, Lon W. Risinger, David M. Solum, Tao Yang, Rajkiran K. Gottumukkal, Kishor Adinath Saitwal
  • Patent number: 9635274
    Abstract: The use of a hybrid camera tool may capture high resolution multispectral images without sacrificing resolution in exchange for spectral accuracy. The capture of a high resolution multispectral image may include forming a high spatial resolution image based on a portion of incoming light and generating a high spectral resolution image that includes multispectral samples based on another portion of the incoming light. The high resolution multispectral image is then synthesized by consolidating the high spatial resolution image with the high spectral resolution image.
    Type: Grant
    Filed: June 15, 2011
    Date of Patent: April 25, 2017
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Stephen S. Lin, Xin Tong, Xun Cao
  • Publication number: 20140321775
    Abstract: Disclosed embodiments relate to systems and methods for facilitating retrieval of information from an image. The one or more image characteristics are modified to degrade the original image. The degraded image is provided as a first task to at least one first remote worker, the first task corresponds to an activity of tagging one or more regions of interest in the degraded image by the at least one first remote worker. Further, one or more second images are generated based on the one or more tagged regions of interest and are provided as one or more second tasks to at least one second remote worker, the one or more second tasks correspond to an activity of retrieving information from the one or more second images.
    Type: Application
    Filed: April 25, 2013
    Publication date: October 30, 2014
    Inventors: Wencheng Wu, Edul N. Dalal
  • Patent number: 8874923
    Abstract: In various example embodiments, a system and method for providing policy-based authentication is provided. In example embodiments, a request to access and sign a document is received from a device of an intended signer. A policy assigned to the intended signer is determined. Based on the policy, a determination is made whether an authentication mechanism is applicable to the intended signer. In response to the determining that the authentication mechanism is applicable to the intended signer, the intended user is required to perform the authentication mechanism. The intended user is provided access to view and sign the document based on the intended user satisfying the authentication mechanism.
    Type: Grant
    Filed: July 24, 2012
    Date of Patent: October 28, 2014
    Assignee: Adobe Systems Incorporated
    Inventor: Dan Foygel
  • Patent number: 8842891
    Abstract: A method, apparatus and computer program product are provided for identifying an unknown subject using face recognition. In particular, upon receiving a plurality of images depicting a subject, the method may include deriving and storing a common component image and a gross innovation component image associated with the subject, wherein the subject can later be identified in a new image using these two stored images. The common component image may capture features that are common to all of the received images depicting the subject, whereas the gross innovation component image may capture a combination of the features that are unique to each of the received images. The method may further include deriving and storing a low-rank data matrix associated with the received images, wherein the low-rank data matrix may capture any illumination differences and/or occlusions associated with the received images.
    Type: Grant
    Filed: May 26, 2010
    Date of Patent: September 23, 2014
    Assignee: Arizona Board of Regents on behalf of Arizona State University
    Inventors: Pradeep Nagesh, Baoxin Li
  • Patent number: 8824801
    Abstract: A method and apparatus for processing video is disclosed. In an embodiment, image features of an object within a frame of video footage are identified and the movement of each of these features is tracked throughout the video footage to determine its trajectory (track). The tracks are analyzed, the maximum separation of the tracks is determined and used to determine a texture map, which is in turn interpolated to provide an unwrap mosaic for the object. The process may be iterated to provide an improved mosaic. Effects or artwork can be overlaid on this mosaic and the edited mosaic can be warped via the mapping, and combined with layers of the original footage. The effect or artwork may move with the object's surface.
    Type: Grant
    Filed: May 16, 2008
    Date of Patent: September 2, 2014
    Assignee: Microsoft Corporation
    Inventors: Andrew Fitzgibbon, Alexander Rav-Acha, Pushmeet Kohli, Carsten Rother
  • Patent number: 8744126
    Abstract: Embodiments of the disclosed invention relate to identifying safe landing sites on a surface. More particularly, three-dimensional image data is obtained from a surface. That image data is processed using morphological operations to create a smoothed surface. The smoothed surface data is then used to calculate slopes, to identify areas of the surface that present a slope hazard. The smooth data obtained for identifying slope hazards can also be used in connection with identifying surface features, including bumps or holes, that create surface feature hazards. After identifying the slope and/or surface feature hazards, a hazard map indicating safe and not safe landing areas can be created.
    Type: Grant
    Filed: March 7, 2012
    Date of Patent: June 3, 2014
    Assignee: Ball Aerospace & Technologies Corp.
    Inventor: Reuben R. Rohrschneider
  • Patent number: 8718352
    Abstract: A computer-aided method, system and computer program product are provided for optical testing of a rope. Such method includes: providing an image data set for at least one portion of the rope; providing target values of a pictorial longitudinal extension of the representation of wires relative to a pictorial longitudinal extension of the rope in the image data set; determining a pictorial longitudinal extension of the wires in the image data set, including adapting an estimated longitudinal extension to the image data set; determining at least one quality value using a quality norm as a function of the determined pictorial longitudinal extension of the wires and the target values of the pictorial longitudinal extension of the wires; discriminating pictorial positions within the image data set of the rope, where at least one quality value exceeds or falls below a predetermined, assigned quality threshold value; and providing the discriminated pictorial positions.
    Type: Grant
    Filed: April 27, 2011
    Date of Patent: May 6, 2014
    Assignee: Winspect GmbH
    Inventors: Sven Winter, Dirk Moll, Ralf Eisinger, Konstantin Kuehner, Egon Guttengeber, Andreas Proehl, Markus Eichinger
  • Patent number: 8666193
    Abstract: Geometric method of transforming a first two-dimensional image into a second two-dimensional image through an image processing applied to the first images or to the second image. In this method, one of said first and second images is divided into several surfaces, each of the surfaces of the divided image is transformed by a bilinear transformation specific to each surface, and the transformed surfaces are grouped together.
    Type: Grant
    Filed: April 27, 2010
    Date of Patent: March 4, 2014
    Assignee: ST-Ericsson (France) SAS
    Inventor: Jean Gobert
  • Patent number: 8620051
    Abstract: A co-registration system provides a means for spatially warping an optical image of an object with another images of a similar object. The optical image may be a scatter image, and the second image may be the same type of image modality, or may be different. The co-registration may use landmarks selected by a user, or may make use of contour information derived from the images. The system may also include processing of three-dimensional volume data in the form of sets of two-dimensional slices for co-registration.
    Type: Grant
    Filed: December 21, 2007
    Date of Patent: December 31, 2013
    Inventors: Salim Djerizi, Niculae Mincu, Mario Khayat
  • Patent number: 8571343
    Abstract: Aspects of the present invention are related to systems and methods for correcting illumination and vignette in a camera-captured document image. A background type may be detected from down-sampled luminance image associated with the camera-captured image, and model parameters may be estimated for a morphologically filtered version of the down-sampled luminance image, wherein the morphological filter may be based on the detected background type. The model parameters may be verified and if deemed acceptable, a rectified image may be formed.
    Type: Grant
    Filed: March 1, 2011
    Date of Patent: October 29, 2013
    Assignee: Sharp Laboratories of America, Inc.
    Inventors: Lawrence Shao-hsien Chen, Richard John Campbell
  • Patent number: 8553928
    Abstract: The present invention relates to an image processing method and image inspecting method with high versatility which enable efficient and highly accurate proof of authenticity of a digital image. The image processing method subjects at least a part of a digital image which can exist temporarily or continuously in a falsification-vulnerable environment, to a first morphology operation using a predetermined structuring element, to process the digital image. The image inspecting method subjects the digital image thus processed, to a second morphology operation using the same structuring element as in the first morphology operation. The morphology operations have the idempotent and the presence or absence of falsification can be detected by determining identity of images before and after the second morphology operation.
    Type: Grant
    Filed: March 6, 2007
    Date of Patent: October 8, 2013
    Assignees: Sumitomo Electric Industries, Ltd., Tokyo Metropolitan University
    Inventors: Hitoshi Kiya, Kiyoshi Nishikawa, Masaaki Fujiyoshi, Yoichi Hata, Toshiaki Kakii, Yoshimitsu Goto
  • Patent number: 8538205
    Abstract: A system for processing an image including multiple pixels and intensity data thereof. An image memory is adapted for storing the image. An arithmetic core is connectible to the image memory and adapted for inputting the intensity data. The arithmetic core includes a multiple function processing units. One or more of the function processing units includes (i) a processing core adapted for computation of a function of the intensity data and for producing results of the computation, (ii) a first and (iii) a second accumulator for summing the results; and storage adapted to store the results. The function processing units are configured to compute the functions in parallel and sum the results simultaneously for each of the pixels in a single clock cycle.
    Type: Grant
    Filed: May 14, 2010
    Date of Patent: September 17, 2013
    Assignee: Mobileye Technologies Ltd.
    Inventors: Emmanuel Sixsou, Mois Navon
  • Patent number: 8463054
    Abstract: A pattern recognition process, a non-transitory computer program product, and a mobile terminal for pattern recognition. An input pattern is normalized and a reliable pattern is generated from the normalized pattern by using at least one morphological operator. The distance between the reliable pattern and selected templates which are selected from a template library using a decision tree, is calculated. The reliable patterns are classified into at least one of the classes of the selected templates by at least one non-parametric classification method.
    Type: Grant
    Filed: April 9, 2012
    Date of Patent: June 11, 2013
    Assignee: I.R.I.S.
    Inventors: Pierre De Muelenaere, Michel Dauw, Olivier Dupont, Patrick Verleysen
  • Patent number: 8406491
    Abstract: Image registration of low contrast image sequences is provided. In one aspect, a desired region of an image is automatically segmented and only the desired region is registered. Active contours and adaptive thresholding of intensity or edge information may be used to segment the desired regions. A transform function is defined to register the segmented region, and sub-pixel information may be determined using one or more interpolation methods.
    Type: Grant
    Filed: May 8, 2008
    Date of Patent: March 26, 2013
    Assignee: UT-Battelle, LLC
    Inventors: Timothy F. Gee, James S. Goddard
  • Patent number: 8331672
    Abstract: Disclosed is a method and an apparatus for recognizing a character and efficiently removing a misrecognized character. The method includes detecting character regions including at least one character in an input image, converting the input image into a binary image, discriminating the characters from a non-character, re-classifying the character region including a number of characters equal to or less than a threshold into a non-character region, and outputting only the characters present in the character region.
    Type: Grant
    Filed: June 24, 2009
    Date of Patent: December 11, 2012
    Assignee: Samsung Electronics Co., Ltd
    Inventors: Sang-Wook Oh, Seong-Taek Hwang, Sang-Ho Kim, Hee-Won Jung
  • Patent number: 8270756
    Abstract: An image noise detection method is disclosed. The image noise detection method includes the following steps: obtaining a spatial information of an image; obtaining a temporal information of the image; and determining a spatial noise or a temporal noise of the image according to both the spatial information, and the temporal information.
    Type: Grant
    Filed: December 21, 2007
    Date of Patent: September 18, 2012
    Assignee: Realtek Semiconductor Corp.
    Inventors: Hsin-Ying Ou, Po-Wei Chao
  • Patent number: 8254676
    Abstract: A method for identifying an object within a container is provided. The method includes acquiring image data representing an image, applying a morphological operator to the acquired image data to generate morphed image data, calculating a histogram based on the morphed image data, and classifying the image using the calculated histogram. A classification of the image may be displayed and/or stored in a computer-readable memory.
    Type: Grant
    Filed: December 31, 2007
    Date of Patent: August 28, 2012
    Assignee: Morpho Detection, Inc.
    Inventors: Dimitrios Ioannou, Todd Gable
  • Patent number: 8238666
    Abstract: A method (1100) of creating a document comprising a modifiable shape, is disclosed. The method analyzes an image to detect at least a graphical object. The method matches the detected graphical object with at least one of a plurality of predetermined modifiable closed-form non-textual template shapes (e.g., 420) comprising control parameters for modifying the closed-form non-textual template shape in a non-affine manner. The number of control parameters of the predetermined modifiable closed-form non-textual template shape is less than the number of sections making up the modifiable closed-form non-textual template shape. The method creates a document comprising the at least one modifiable closed-form non-textual template shape.
    Type: Grant
    Filed: November 28, 2007
    Date of Patent: August 7, 2012
    Assignee: Canon Kabushiki Kaisha
    Inventors: James Austin Besley, Eric Wai-Shing Chong, Khanh Phi Van Doan, Steven Richard Irrgang
  • Patent number: 8189960
    Abstract: An image processing apparatus includes: an imaging information calculation unit acquiring a first image and higher-resolution second images, and calculating coordinate positions of the second images to the first image and differences in imaging direction between second cameras and a first camera; an eyepoint conversion unit generating eyepoint conversion images obtained by converting the second images based on the differences in imaging direction so that eyepoints of the second cameras coincide with an eyepoint of the first camera and matching the first image with the eyepoint conversion images to calculate phase deviations of the eyepoint conversion images from the first image; and an image synthesizing unit extracting high-frequency images, having frequency components higher than or equal to a predetermined frequency band, from the second images, and pasting the high-frequency images at the coordinate positions in correspondence with the first image to eliminate the phase deviations to generate a synthesize
    Type: Grant
    Filed: June 24, 2009
    Date of Patent: May 29, 2012
    Assignee: Sony Corporation
    Inventors: Tetsujiro Kondo, Tetsushi Kokubo, Kenji Tanaka, Hitoshi Mukai, Hirofumi Hibi, Kazumasa Tanaka, Hiroyuki Morisaki
  • Patent number: 8174611
    Abstract: A digital camera function, such as can be implemented in a cellular telephone handset, and that includes automated segmentation of foreground subjects in acquired digital photos and images. Successive images are captured by the digital camera function at different flash exposure levels, for example using existing light only and using flash exposure. After alignment and registration of the images, luminance difference values in the two images are determined for each pixel, and the luminance difference values compared against a threshold value on a pixel-by-pixel basis. Those pixels with luminance difference values exceeding the threshold are segmented from the image as foreground subjects.
    Type: Grant
    Filed: March 26, 2009
    Date of Patent: May 8, 2012
    Assignee: Texas Instruments Incorporated
    Inventors: Leonardo William Estevez, Aziz Umit Batur
  • Patent number: 8160296
    Abstract: A method of determining change in a state of an object using images of the object, the method including providing a first image and a second image of the object, the first image and the second image being spaced apart in time, performing a plurality of pixel-based change detection algorithms to obtain a plurality of output difference products/images containing change information and pseudo change information, combining the plurality of output difference products to form a hybrid output difference product and thresholding the output difference product to detect changes in the object.
    Type: Grant
    Filed: April 14, 2006
    Date of Patent: April 17, 2012
    Assignee: Mississippi State University Research and Technology Corporation
    Inventors: Charles G. O'Hara, Anil Cheriyadat, Suyoung Seo, Veeraraghavan Vijayaraj
  • Patent number: 8160382
    Abstract: Methods for detecting areas of interest in an image using combined edge magnitude and edge direction analysis techniques are presented. One embodiment features using thermal imaging data to detect hotspots in maritime settings that may be potential targets for tracking or weapons systems. The edge magnitude and edge direction data are derived from the intensity image and then combined with the intensity image and analyzed morphologically to remove noise and background elements. The combined image data is then selectively filtered to remove horizontal non-target elements and then analyzed further against target size information to determine which detected and analyzed hotspots are valid targets. Another embodiment features receiving as input an intensity image along with its associated edge magnitude and edge direction images, which have both been created by a means outside the detection method. Yet another embodiment features a detection method that does not selectively filter out horizontal image elements.
    Type: Grant
    Filed: October 15, 2007
    Date of Patent: April 17, 2012
    Assignee: Lockheed Martin Corporation
    Inventor: Jason A. Sefcik
  • Patent number: 8120808
    Abstract: A user decides images to be laid out on one image. For each image showing presence of face among the decided images, a region decision means decides a display region including at least one face in the corresponding image, according to the number of faces therein and according to a distance between the faces in the case where the number of the faces is larger than 1. A layout image generation unit extracts the display regions from the respective images, and generates a layout image by laying out the extracted display regions on a background image.
    Type: Grant
    Filed: October 4, 2006
    Date of Patent: February 21, 2012
    Assignee: Fujifilm Corporation
    Inventor: Mika Sugimoto
  • Patent number: 8073281
    Abstract: A dilation image is generated from an original digital image utilizing a processing image (b) and a target image (T), where each pixel in the target image is processed in parallel. The process entails, for each target pixel, i) determining coordinate values for the target pixel, ii) determining a surrounding pixel area for the target pixel, iii) and processing each pixel in the surrounding pixel area to determine whether or not to updated the value of the target pixel. In processing each surrounding pixel, a determination is made whether the pixel has a value of 1. If not, then the next surrounding pixel is processed. If so, then a determination is made which pixel element of the structuring element overlays the target pixel, and whether that pixel has a value of 1. If so, then the value of the target pixel is updated. If not, then the next pixel in the surrounding pixel area is processed. Once the target pixel has been updated one time, the processing of the remaining surrounding pixels is terminates.
    Type: Grant
    Filed: December 22, 2008
    Date of Patent: December 6, 2011
    Assignee: Canon Kabushiki Kaisha
    Inventors: Manoj Mathew, Allison Bajo
  • Patent number: 8064723
    Abstract: The invention provides a method and apparatus for fast volume rendering of 3D ultrasound image, comprising a dividing step, a calculating step, a determining step, a morphological closing operation step and a filling step, wherein each flat grid can be entirely filled by obtaining gray-scale values for all pixels inside the grid through interpolating; for the non-flat grid, the steps of dividing, calculating, determining and filling are performed repeatedly until the non-flat grid is subdivided into atomic grids to calculate gray-scale values for remaining pixels by projection. As the method can be finished in the rear end, no difficulty occurs in the implementation, and no process for being adapted to previous frames is required. Therefore, the method can improve the rendering speed effectively without degrading the quality of image to put 3D ultrasound imaging to the best use.
    Type: Grant
    Filed: October 22, 2007
    Date of Patent: November 22, 2011
    Assignee: Shenzhen Mindray Bio-Medical Electronics Co., Ltd.
    Inventors: Yong Tian, Bin Yao
  • Patent number: 8059862
    Abstract: A method of determining change in a state of an object using images of the object, the method including providing a first image and a second image of the object, the first image and the second image being spaced apart in time, performing a plurality of pixel-based change detection algorithms to obtain a plurality of output difference products/images containing change information and pseudo change information, combining the plurality of output difference products to form a hybrid output difference product and thresholding the output difference product to detect changes in the object.
    Type: Grant
    Filed: April 14, 2006
    Date of Patent: November 15, 2011
    Assignee: Mississippi State University Research and Technology Corporation
    Inventors: Charles G. O'Hara, Anil Cheriyadat, Suyoung Seo, Veeraraghavan Vijayaraj
  • Patent number: 8013910
    Abstract: An image by using a solid-state imaging sensor, the imaging apparatus including: a compression section configured to compress image data by dividing the image data into blocks each composed of same color component pixels adjacent to each other as a unit of compression; a memory used for temporarily storing compressed image data; a decompression section configured to decompress the compressed image data read out from the memory; and a signal processing section configured to carry out an image-quality correction process on decompressed image data, wherein each of the blocks is split in advance into two quantization-subject areas, block types are distinguished from each other by the position of the inter-area boundary between the two quantization-subject areas, and the compression section has a dynamic-range computation sub-section, a block-type select sub-section, and a quantization processing sub-section are provided.
    Type: Grant
    Filed: May 19, 2008
    Date of Patent: September 6, 2011
    Assignee: Sony Corporation
    Inventors: Fumiaki Kato, Ken Nakajima
  • Patent number: 8009880
    Abstract: A subregion-based image parameter recovery system and method for recovering image parameters from a single image containing a face taken under sub-optimal illumination conditions. The recovered image parameters (including albedo, illumination, and face geometry) can be used to generate face images under a new lighting environment. The method includes dividing the face in the image into numerous smaller regions, generating an albedo morphable model for each region, and using a Markov Random Fields (MRF)-based framework to model the spatial dependence between neighboring regions. Different types of regions are defined, including saturated, shadow, regular, and occluded regions. Each pixel in the image is classified and assigned to a region based on intensity, and then weighted based on its classification.
    Type: Grant
    Filed: May 11, 2007
    Date of Patent: August 30, 2011
    Assignee: Microsoft Corporation
    Inventors: Zhengyou Zhang, Zicheng Liu, Gang Hua, Yang Wang
  • Patent number: 8000555
    Abstract: A method for detecting a defective image of the present invention includes obtaining an edge image by performing an edge tracking process on an original image, detecting an isolation point whose size is equal to or smaller than a predetermined size from a processed image obtained by performing an erosion process after an expansion process on the edge image, and detecting a defective image in the original image based on the isolation point.
    Type: Grant
    Filed: May 15, 2007
    Date of Patent: August 16, 2011
    Assignee: Seiko Epson Corporation
    Inventors: Keiji Hirose, Kon Ko
  • Patent number: 7974499
    Abstract: Disclosed is an algorithm for applying a morphological operation to an image. In one embodiment, the morphological operation is iteratively applied to a focal pixel of the image and to another pixel of the image. The other pixel is located at an offset with respect to the focal pixel. The offset is based on an operation count. In another embodiment, the algorithm includes performing a morphological operation on an image using a convex structuring element. A work structuring element having dimensions corresponding to the outer-most dimensions of the convex structuring element is iteratively applied to the image. The dimensions of the work structuring element are then adjusted to correspond to the remaining outer dimensions of the convex structuring element not yet covered by the previous work structuring element. The applying and adjusting steps are repeated until a predetermined number of morphological operations have been performed.
    Type: Grant
    Filed: December 13, 2005
    Date of Patent: July 5, 2011
    Assignee: Siemens Medical Solutions USA, Inc.
    Inventors: Michael Vaz, Atilla Peter Kiraly
  • Patent number: 7940982
    Abstract: A method of performing color space conversion includes maintaining a data structure that has a plurality of dimensions and that contains a plurality of locations storing information in each of the dimensions. Each of the dimensions corresponds to a different one of a plurality of input color signal components. The number of locations which the data structure contains in a first one of the dimensions is different from the number of locations which the data structure contains in a second one of the dimensions. The method further includes inputting first data defined according to a first color space, and generating second data defined according to a second color space, by applying information contained in the data structure to the first data.
    Type: Grant
    Filed: May 31, 2007
    Date of Patent: May 10, 2011
    Assignee: Zoran Corporation
    Inventor: Ben-Zion Shaick
  • Publication number: 20110064331
    Abstract: Apparatuses, computer media, and methods for altering a submitted image of a person. The submitted image is transformed in accordance with associated data regarding the person's condition. Global data may be processed by a statistical process to obtain cluster information, and the transformation parameter is then determined from cluster information. The transformation parameter is then applied to a portion of the submitted image to render a transformed image. A transformation parameter may include a texture alteration parameter, a hair descriptive parameter, or a reshaping parameter. An error measure may be determined that gauges a discrepancy between a transformed image and an actual image. A transformation model is subsequently reconfigured with a modified model in order to reduce the error measure. Also, the transformation model may be trained to reduce an error measure for the transformed image.
    Type: Application
    Filed: August 5, 2010
    Publication date: March 17, 2011
    Inventor: Ana Cristina Andres del Valle
  • Patent number: 7881508
    Abstract: Notice is given when a medical image does not include an appropriate region imaged therein. At least one anatomical structure is extracted from a medical image obtained by an imaging apparatus. Whether a diagnostic region imaged within the medical image is appropriate for conducting diagnosis is judged, employing the at least one extracted anatomical structure as a reference. Further, display is performed on a console, based on the obtained judgment results.
    Type: Grant
    Filed: October 16, 2006
    Date of Patent: February 1, 2011
    Assignee: FUJIFILM Corporation
    Inventor: Keigo Nakamura
  • Patent number: 7873235
    Abstract: An imaging processing system adapted for use with a vehicle is provided in one aspect of the present invention. The system generally includes an image capturing device and an image processing device. The image capturing device is operable to capture an original image of a scene exterior to the vehicle. The captured original image is generally defined by a group of pixels. The image processing device is operable to receive the captured original image and morphologically process the captured original image to remove distortion from the captured original image to produce a final filtered image.
    Type: Grant
    Filed: January 29, 2007
    Date of Patent: January 18, 2011
    Assignee: Ford Global Technologies, LLC
    Inventor: Reid Steiger
  • Patent number: 7844107
    Abstract: Disclosed is a stereo image matching method for re-creating 3-dimensional spatial information from a pair of 2-dimensional images. The conventional stereo image matching method generates much noise from a disparity value in the vertical direction, but the present invention uses disparity information of adjacent image lines as a constraint condition to eliminate the noise in the vertical direction, and compress the disparity by using a differential coding method to thereby increase a compression rate.
    Type: Grant
    Filed: August 14, 2009
    Date of Patent: November 30, 2010
    Assignee: Postech Foundation
    Inventors: Hong Jeong, Sungchan Park
  • Patent number: 7831099
    Abstract: A pattern matching device includes a dilated image generating unit that generates a dilated image based on a resultant image obtained by logical operation between a first image pattern and a second image pattern, and a comparing unit that compares the first image pattern with the second image pattern, based on a ratio of overlap between the first image pattern and the dilated image generated by the dilated image generating unit, and a ratio of overlap between the second image pattern and the dilated image generated by the dilated image generating unit.
    Type: Grant
    Filed: January 3, 2007
    Date of Patent: November 9, 2010
    Assignee: Fuji Xerox Co., Ltd.
    Inventor: Masanori Sekino
  • Patent number: 7756363
    Abstract: In image processing, parallel and synchronous pixel processing elements have a pixel value register, a neighbor value register, and a processor receiving adjacent pixel and neighbor values for four adjacent pixels. In a series of iterations, the neighbor value register is updated with—in one mode—the maximum and—in another mode—the minimum of: the current value; the pixel value from any adjacent pixel whose pixel value is different from the current pixel value and the neighbor value from an adjacent pixel whose pixel value is the same as the current pixel value. The pixel value is then replaced by the minimum or maximum (depending on the mode) of the current pixel and neighbor values. The modes may alternate with the number of iterations in each series remaining constant or growing.
    Type: Grant
    Filed: February 12, 2004
    Date of Patent: July 13, 2010
    Inventor: Michael James Knee
  • Publication number: 20100142855
    Abstract: The image processing system using morphological macrocells comprises: an image acquisition device, a set of memories, a computation block, and a control system. The computation block includes k morphological macrocells (50) each including a set of basic morphological cells (51, 52, 61, 62) organized into parallel branches (f, g), each cell (51, 52, 61, 62) executing a basic erosion, dilation or identity function based on the use of linear structuring elements, the functionality of each morphological cell and the size of the structuring elements being programmable dynamically and the parallel streams coming from the basic morphological cells being combined at the output by an arithmetic and logic unit (70). At least one system for parallelizing the data for processing a plurality of lines, respectively a plurality of columns, in parallel breaks down a word into p parallel data streams and is connected to the p morphological macrocell inputs.
    Type: Application
    Filed: November 27, 2007
    Publication date: June 10, 2010
    Inventors: Eva Dokladalova, Philippe Fauvel, Stéphane Guyetant, Christophe Clienti
  • Patent number: 7706625
    Abstract: A sequence of medical images is filtered. The filtering adapts as a function of spatial closeness, similarity of display values, and temporal vicinity. The kernel weights are based on combined spatial and temporal considerations as well as similarity for trilateral filtering. The similarity is a function of time. The similarity may be between display values separated by time or space and time.
    Type: Grant
    Filed: June 9, 2006
    Date of Patent: April 27, 2010
    Assignee: Siemens Aktiengesellschaft
    Inventor: Roland Friedrich
  • Patent number: 7697742
    Abstract: A method of detecting a junction between a lesion and a wall in a CT scan image may include determining the boundary (B) of the wall to an internal space (L), identifying critical points (c1, c2) along the boundary, and selecting one critical point at either side of the lesion as a junction point between the wall and the lesion. The critical points may be points of maximum local curvature and/or points of transition between straight and curved sections of the boundary. The critical points may be selected by receiving first and second seed points (p1, p2) at either side of the lesion, moving the seed points to the boundary if they are not already located on the boundary, and finding the closest critical points to the seed points. The seed points may be determined by displacing the determined junction points (j1, j2) from an adjacent slice of the image into the current slice.
    Type: Grant
    Filed: September 8, 2004
    Date of Patent: April 13, 2010
    Assignee: Medicsight PLC
    Inventor: Jamshid Dehmeshki
  • Patent number: 7684633
    Abstract: A system and method for controlling the work flow or processing of scanned images is disclosed. The system and method identify appropriate image processing techniques, particularly techniques well-suited to enable image compression yet maintain image quality so as to facilitate the storage and transmission of scanned image data.
    Type: Grant
    Filed: June 28, 2005
    Date of Patent: March 23, 2010
    Assignee: Xerox Corporation
    Inventors: Yingjun Bai, Xing Li
  • Patent number: 7672013
    Abstract: Methods and apparatus are provided for electronically trapping a selected digital color image pixel. A plurality of pixels that surround the selected pixel are identified, a colorant value of each of the surrounding pixels is compared with a corresponding colorant value of the selected pixel, one of the surrounding pixels is identified to control trapping of the selected pixel, and the selected pixel is trapped based on a relationship between a colorant value of the selected pixel and a corresponding colorant value of the identified controlling pixel.
    Type: Grant
    Filed: November 20, 2003
    Date of Patent: March 2, 2010
    Assignee: Electroncics for Imaging, Inc.
    Inventors: Yigal Accad, Richard Falk, Mark Kelley
  • Patent number: 7630558
    Abstract: A method of detecting lines in an image comprises using one or more masks for detecting lines in one or more directions out of horizontal, vertical, left diagonal and right diagonal, and further comprises one or more additional masks for detecting lines in one or more additional directions.
    Type: Grant
    Filed: June 10, 2005
    Date of Patent: December 8, 2009
    Assignee: Mitsubishi Denki Kabushiki Kaisha
    Inventors: Carlos Santamaria, Miroslaw Bober
  • Patent number: 7606445
    Abstract: Methods and systems for measuring indications in an image are provided. The method includes acquiring image data that includes a potential indication, processing the data such that features of the indication are enhanced, thresholding the data such that the indication is separated from the remaining data, determining a size of the indication, and displaying a determined size of the indication.
    Type: Grant
    Filed: November 30, 2005
    Date of Patent: October 20, 2009
    Assignee: General Electric Company
    Inventor: Patrick Joseph Howard
  • Patent number: 7573513
    Abstract: An image processing apparatus having an arithmetic circuit for generating pixel data of output pixels by arithmetically processing the pixel data of M horizontally adjoining pixels and N vertically adjoining pixels. A first temporary storage section readably stores the pixel data of the pixels ranging from the Mth pixel to the last pixel in each horizontal pixel line of an image. A second temporary storage section readably stores the pixel data of the pixels ranging from the head pixel to the (M?1)th pixel in each horizontal pixel line of the image. A third temporary storage section delays the pixel data stored in the first temporary storage section, receives the pixel data from the second temporary storage section, and simultaneously outputs pixel data of the M horizontally adjoining pixels and the N vertically adjoining pixels.
    Type: Grant
    Filed: March 26, 2003
    Date of Patent: August 11, 2009
    Assignee: Panasonic Corporation
    Inventor: Yoshimasa Okabe
  • Patent number: 7570794
    Abstract: A method and system are provided for non-contact evaluation of a machined surface of a cast-metal part, including a vision-based porosity inspection station. A digital image of the machined surface is acquired, oriented and scaled to an XY coordinate system, filtered, and inverted. A second image is generated with known design surface features eliminated. Each pixel of the inverted digital image is XOR-compared with a corresponding pixel of the second image. Identified common surface features common to both images is analyzed statistically for conformance to a threshold. A defect is identified as any identified surface feature common to both images which exceeds the threshold. The system moves the part for further processing if a statistical analysis of defects indicates an acceptable component, and alternatively, removes the part from further processing if the analysis indicates a flawed component.
    Type: Grant
    Filed: September 2, 2005
    Date of Patent: August 4, 2009
    Assignee: GM Global Technology Operations, Inc.
    Inventors: Michael E. Swanger, John S. Agapiou, Robert J. Hogarth
  • Patent number: 7529397
    Abstract: The present invention discloses methods for automatically generating regions of seeding points for fiber tracking in diffusion tensor images. These methods are based on connected region grow. Seeding point selection criteria involving Fractional Anisotropy thresholding and Dominant Eigen Vector similarity are also disclosed.
    Type: Grant
    Filed: January 17, 2006
    Date of Patent: May 5, 2009
    Assignee: Siemens Medical Solutions USA, Inc.
    Inventors: Zhizhou Wang, Yuanhsi (Tony) Chen, Mariappan S. Nadar
  • Patent number: 7515764
    Abstract: An image processing apparatus which uses morphology is provided. A masked image is provided to a morphological processing section of the image processing apparatus. The morphological processing section calculates the opening gap of the masked image, calculates the minimum number N of iterations of dilations required for filling the opening gap and, after performing N dilations, executes N erosions to remove a mesh pattern. Then, an edge detecting section detects the edges of a wiring pattern in the image and a measuring section calculates the distance between the edges, which is the width of the wiring.
    Type: Grant
    Filed: April 25, 2005
    Date of Patent: April 7, 2009
    Assignee: Mitutoyo Corporation
    Inventors: Naoki Mitsutani, Masaki Kurihara
  • Patent number: RE43479
    Abstract: Disclosed is a color interpolation method. The present invention decides a precise position of an edge with use of a G value in a unit pixel structure with a size of 3×3, thereby using different color interpolations according to the position of the edge. Also, the present invention provides an effect of emphasizing an edge by emphasizing a brightness and lowering colors when the edge is placed in the vertical center or the horizontal center of the unit pixel structure of 3×3 with use of a property that the edge has stronger brightness than the colors and prevents an incorrect color.
    Type: Grant
    Filed: February 21, 2011
    Date of Patent: June 19, 2012
    Assignee: Intellectual Ventures II LLC
    Inventor: Byung-Geun Jung