Patents Examined by David P Rashid
-
Patent number: 7894675Abstract: A method and apparatus are provided for identifying linear objects in an image. Terrain types in the image are identified, and a gradient vector image, which identifies a gradient magnitude value and a gradient direction value for each pixel of the image, is generated from the image. Lines in the gradient vector image are identified using the identified terrain types in each portion of the image. It is determined whether the identified lines are perpendicular, collinear, or parallel to another line among the identified lines in the gradient vector image. Lines among the identified line are eliminated which are determined to not be perpendicular, collinear, or parallel to another line among the identified lines in the gradient vector image. Linear objects are identified using the remaining identified lines which have not been eliminated.Type: GrantFiled: March 10, 2008Date of Patent: February 22, 2011Assignee: Lockheed Martin CorporationInventors: Melissa Wiedemann, Larry Phurrough, Colleen Flynn Gratsch, Richard Skoblick, Harry C. Lee
-
Patent number: 7889905Abstract: A novel framework for fast and continuous registration between two imaging modalities is disclosed. The approach makes it possible to completely determine the rigid transformation between multiple sources at real-time or near real-time frame-rates in order to localize the cameras and register the two sources. A disclosed example includes computing or capturing a set of reference images within a known environment, complete with corresponding depth maps and image gradients. The collection of these images and depth maps constitutes the reference source. The second source is a real-time or near-real time source which may include a live video feed. Given one frame from this video feed, and starting from an initial guess of viewpoint, the real-time video frame is warped to the nearest viewing site of the reference source. An image difference is computed between the warped video frame and the reference image.Type: GrantFiled: May 19, 2006Date of Patent: February 15, 2011Assignee: The Penn State Research FoundationInventors: William E. Higgins, Scott A. Merritt, Lav Rai
-
Patent number: 7889920Abstract: According to the claimed invention, an image processing apparatus is provided, wherein the image processing apparatus comprises a color determiner, adapted to determine a color of image data; a color space determiner, adapted to determine a color space for compressing the image data based on the color determined by the color determiner; and a converter, adapted to convert the image data into data on a plurality of planes that constitute the color space determined by the color space determiner and compressing the data on each plane, wherein the color space determiner determines the color space based on the color determined by the color determiner so that AC components of the image data concentrate on a certain plane of the plurality of planes.Type: GrantFiled: June 18, 2007Date of Patent: February 15, 2011Assignee: Canon Kabushiki KaishaInventor: Junya Arakawa
-
Patent number: 7885439Abstract: An identification information creation apparatus and method capable of improving reliability in an identification process. A prescribed number or fewer isolated pixels are eliminated as condition noises from a binarized image created from images obtained by imaging blood vessels unique to a body, and identification information is created based on the blood vessels of the resultant noise-free binarized image. This can reduce a possibility of creating the identification information with the condition noises as a part of the blood vessels, thus making it possible to prevent the identification information from deteriorating due to different imaging conditions and physiologic change of imaging target and thus improving reliability in the identification process.Type: GrantFiled: February 9, 2005Date of Patent: February 8, 2011Assignee: Sony CorporationInventor: Yumi Kato
-
Patent number: 7885341Abstract: An apparatus, method, and carrier medium carrying computer-readable code to implement a method that includes generating a difference picture of an accepted picture of a time sequence of pictures minus an estimate of the previous picture in the sequence. The generating of the difference picture includes forming quantized coefficients and passing the quantized coefficients via a prediction loop to generate the estimate of the previous picture. A spatial filter is applied to at least a component of the difference picture such that the forming of quantized coefficients is from a spatially filtered difference picture. The spatial filter is a noise reducing spatial filter configured such that there is a fixed delay between the filter input picture and the filter output picture. The fixed delay is significantly less than the time between consecutive pictures in the time sequence.Type: GrantFiled: October 21, 2005Date of Patent: February 8, 2011Assignee: Cisco Technology, Inc.Inventors: Wen-hsiung Chen, Philip R. Graham
-
Patent number: 7885465Abstract: An efficient technique is provided for determining a portion of a document corresponding to a captured image. Areas of a document in which the pattern is at least partially obscured are identified. A reference pixel in the image is selected, and an offset between the pixel and the pattern is determined. A pixel-by-pixel comparison is then made of the image with the document such that the reference pixel is only compared with locations in the document that are both within the identified areas and have the determined offset from the pattern. The comparison with the highest correspondence between the image pixels and the electronic document then identifies the position of the reference pixel relative to the electronic document.Type: GrantFiled: September 16, 2008Date of Patent: February 8, 2011Inventors: Jian Wang, Yingnong Dang, Qiang Wang, Liyong Chen, Xiaoxu Ma
-
Patent number: 7881551Abstract: Methods and apparatus are disclosed for digital image restoration. The method including the steps of receiving an external deteriorated image, and generating N restoration images by using a preset PSF and an image restoration filter without computing a PSF of the input deteriorated image, dividing the restoration images into window parts of a predetermined window size, computing absolute values of differences among peripheral pixels within the divided window parts, selecting only a high frequency part, and analyzing focus deterioration; determining weights of the N restoration images, selecting window parts having high weights, and integrating the selected window parts into one image and comparing a degree of restoration of the integrated image with a preset degree of restoration, and outputting the integrated image as a resultant image when the degree of restoration of the integrated image is higher than the preset degree of restoration.Type: GrantFiled: December 15, 2006Date of Patent: February 1, 2011Assignee: Chung-Ang University Industry Academic Cooperation FoundationInventors: Joon-Ki Paik, Jeong-Ho Shin, Maik Vivek, Yoon-Jong Yoo
-
Patent number: 7881494Abstract: A characteristic point detection method, including the steps of: detecting a candidate of each of a plurality of characteristic points of a predetermined object from a detection target image; obtaining an existence probability distribution for a target characteristic point with respect to each of the detected candidates of the other characteristic points, which is an existence probability distribution of the target characteristic point when the position of the detected candidate of another characteristic point is taken as a reference, using an existence probability distribution statistically obtained for each combination of two different characteristic points of the plurality of characteristic points; integrating the obtained existence probability distributions by weighting according to the positional relationship between the reference characteristic point and target characteristic point; and estimating the true point of the target characteristic point based on the magnitude of the existence probabilities inType: GrantFiled: February 21, 2007Date of Patent: February 1, 2011Assignee: Fujifilm CorporationInventor: Yoshiro Kitamura
-
Patent number: 7869622Abstract: Within a prioritized mode selection dialog, either a measurement accuracy prioritized mode or a measurement speed prioritized mode is selected. If the measurement accuracy prioritized mode is selected, then processing for entering a tolerable amount of movement is executed. Then, a relative movement speed of a CCD camera to a measurement stage is calculated from the entered amount of movement. Finally, image information is captured at a lower speed than the calculated relative movement speed to execute image measurement. If the measurement speed prioritized mode is selected, then processing for entering a relative movement speed is executed, and image information is captured at the entered relative movement speed to execute image measurement.Type: GrantFiled: May 31, 2006Date of Patent: January 11, 2011Assignee: Mitutoyo CorporationInventors: Sadayuki Matsumiya, Koichi Komatsu
-
Patent number: 7856137Abstract: A correlation value image is generated from an input image and a template image, and separated into a positive correlation value image and a negative correlation value image. The template image is separated into a positive template image and a negative template image. A plurality of positive-negative-separated correlation images are generated by combining the positive correlation value image and the negative correlation value image and the positive template image and the negative template image. A polar-coordinates-converted input image and a polar-coordinates-converted template image are employed as the input image and the template image, respectively.Type: GrantFiled: June 22, 2005Date of Patent: December 21, 2010Assignee: Glory Ltd.Inventors: Toru Yonezawa, Hirofumi Kameyama
-
Patent number: 7852940Abstract: The disclosure is directed to scalable motion estimation techniques for video encoding. According to the motion estimation techniques, a motion vector search is scaled according to the computing resources available. For example, the extent of the search may be dynamically adjusted according to available computing resources. A more extensive search may be performed when computing resources permit. When computing resources are scarce, the search may be more limited. In this manner, the scalable motion estimation technique balances video quality, computing overhead and power consumption. The scalable motion estimation technique may search a series of concentric regions, starting at a central anchor point and moving outward across several concentric regions. The number of concentric regions searched for a particular video frame or macroblock is adjusted according to computing resources.Type: GrantFiled: October 20, 2005Date of Patent: December 14, 2010Assignee: QUALCOMM IncorporatedInventor: Narendranath Malayath
-
Patent number: 7844134Abstract: A motion detecting part detects moving regions in a plurality of frame images captured by rolling shutter type exposure, and obtains a motion vector of the moving regions. A moving region correcting part corrects the moving region in a to-be-corrected frame image of the plurality of frame images on the basis of the motion vector, information on an image-capturing time interval between the plurality of frame images, information on an exposure starting time difference resulting from the difference in position in one frame image caused by the rolling shutter type exposure and information on an exposure start sequence depending on the position in one frame image captured by the rolling shutter type exposure.Type: GrantFiled: November 16, 2006Date of Patent: November 30, 2010Assignee: MegaChips CorporationInventors: Gen Sasaki, Yusuke Nara
-
Patent number: 7840076Abstract: An image retrieval program (IRP) may be used to query a collection of digital images. The IRP may include a mining module to use local and global feature descriptors to automatically rank the digital images in the collection with respect to similarity to a user-selected positive example. Each local feature descriptor may represent a portion of an image based on a division of that image into multiple portions. Each global feature descriptor may represent an image as a whole. A user interface module of the IRP may receive input that identifies an image as the positive example. The user interface module may also present images from the collection in a user interface in a ranked order with respect to similarity to the positive example, based on results of the mining module. Query concepts may be saved and reused. Other embodiments are described and claimed.Type: GrantFiled: November 22, 2006Date of Patent: November 23, 2010Assignee: Intel CorporationInventors: Jean-Yves Bouguet, Carole Dulong, Igor V. Kozintsev, Yi Wu, Ara V. Nefian
-
Patent number: 7840031Abstract: A computer-implemented method, system, and program product includes a movement processing system for capturing a first three-dimensional movement of a user and capturing at least another three-dimensional movement of the user, wherein the three-dimensional movement is determined using at the at least one image capture device aimed at the body of the user. A projected movement system predicts a movement baseline based on the first three-dimensional movement of the user and predicts at least one subsequent movement range based on the at least another three-dimensional movement of the user. Based on a comparison of the movement baseline with the at least one subsequent movement, the projected movement systems predicts a projected movement of a user for tracking changes in a range of body movement of a user.Type: GrantFiled: January 12, 2007Date of Patent: November 23, 2010Assignee: International Business Machines CorporationInventors: Jacob C. Albertson, Kenneth C. Arnold, Steven D. Goldman, Michael A. Paolini, Anthony J. Sessa
-
Patent number: 7822258Abstract: A mobile platform is provided which has at least one component having an array of distributed piezoelectric transmitters and an associated array of distributed receivers. The receivers are configured to receive ultrasonic transmissions from the transmitters. Data from the receivers is stored in memory and processed through an algebraic reconstruction tomography algorithm which forms an image of the defect within the component. An algorithm is used to determine the position and size of the defect.Type: GrantFiled: November 15, 2005Date of Patent: October 26, 2010Assignee: The Boeing CompanyInventors: Simon D Senibi, David L Banks, Chris K Carrell, Mark A Curry
-
Patent number: 7822230Abstract: An image measuring system comprises a measurement point acquire, a measurement direction calculator, a synthesized direction calculator operative to calculate a synthesized direction resulted from synthesis of movement directions before and after the measurement point, a fore/aft-running point calculator operative to calculate a forerunning point at a position spaced a certain distance backward in the synthesized direction from the measurement point and to calculate an aft-running point at a position spaced a certain distance forward in the synthesized direction from the measurement point, a way point calculator operative to calculate a plurality of way points arranged on a path smoothly connecting the aft-running point to the forerunning point, and a measurement path setter operative to set a measurement path following the synthesized directions and passing through the calculated way points and the measurement points.Type: GrantFiled: February 26, 2007Date of Patent: October 26, 2010Assignee: Mitutoyo CorporationInventors: Shigeru Fujimaki, Koichi Komatsu
-
Patent number: 7822240Abstract: The invention concerns an image processing device, including an input for receiving a time series of data sets representing comparable volume digital images, each data having a position component and an intensity component, pre-processing means for modifying the data sets so as to obtain images updated in position and intensity, and comparative processing means for examining sets of time series of image elements and to detect therein signs of variations. The processing means include a modeling function for adjusting a parametric model separately on some of the sets of time series of image elements, to obtain pairs of data (image element, time) and a function for statistical analysis of said pairs of data to isolate the pairs of data representing a significant variation.Type: GrantFiled: October 4, 2002Date of Patent: October 26, 2010Assignee: Inria Institut National de Recherche en Informatique et en AutomatiqueInventors: Nicholas Ayache, Grégoire Malandain, David Rey, Jonathan Stoeckel
-
Patent number: 7817843Abstract: A mobile platform is provided which has at least one component having an array of distributed piezoelectric transmitters and an associated array of distributed receivers. The receivers are configured to receive ultrasonic transmissions from the transmitters. Data from the receivers is stored in memory and processed through an algebraic reconstruction tomography algorithm which forms an image of the defect within the component. An algorithm is used to determine the position and size of the defect.Type: GrantFiled: March 4, 2004Date of Patent: October 19, 2010Assignee: The Boeing CompanyInventors: Simon D Senibi, David L Banks, Chris K Carrell, Mark A Curry
-
Patent number: 7809206Abstract: An image processing apparatus generates a sub-self-similar set F, which is a subset of a self-similar set A with respect to contraction maps f1, . . . , fn and forms an image expressing the sub-self-similar set F. The apparatus includes a base-address-set designating section, a generation-rule acquiring section and a sub-self-similar set generating section. The base-address-set designating section selects m addresses each of which formed of infinite sequence of {1, . . . , n} and generates a base address set M including the selected addresses. The generation-rule acquiring section acquires a rule of generating a hypothetical sub-self-similar set G, which is a subset of a hypothetical self-similar set B with respect to n hypothetical contraction maps g1, . . . , gn, by using the generated base address set M. The sub-self-similar set generating section generates a sub-self-similar set F, which is a subset of the self-similar set A.Type: GrantFiled: November 16, 2006Date of Patent: October 5, 2010Assignee: Fuji Xerox Co., Ltd.Inventor: Kanya Ishizaka
-
Patent number: 7805021Abstract: A method to detect edges based on chrominance information alone or in combination with gray level values includes comparing chrominance values to a registration parameter based on chromacity measurements of a backing. To calibrate a system, a small scan obtains sample image data for the backing in the document feeder. Using the sampled image data, average chrominance values for the backing are determined. Based on the averages, a channel having a low chrominance contribution is selected as the registration channel. A registration parameter is calculated for automatic registration of documents based on the average chrominance and chrominance deviation for the registration channel.Type: GrantFiled: July 8, 2003Date of Patent: September 28, 2010Assignee: Xerox CorporationInventors: William Yeoh, Ramesh Nagarajan, James M. Maryniak