Patents Examined by Daniel Zeilberger
-
Patent number: 8055074Abstract: A method of approximating the inner or outer boundary of an iris comprises generating an approximate boundary representation (20) comprising a least squares approximation by a Fourier Series of a function of the angle (?) about a fixed point (A) of the distance of measured points (10) on the boundary from the fixed point (A). More broadly, the method may be used to approximate the shape of any two-dimensional curve or figure.Type: GrantFiled: January 17, 2007Date of Patent: November 8, 2011Inventor: Donald Martin Monro
-
Patent number: 8055047Abstract: Improved surface feature recognition in CT images is provided by extracting a triangulated mesh representation of the surface of interest. Shape operators are computed at each vertex of the mesh from finite differences of vertex normals. The shape operators at each vertex are smoothed according to an iterative weighted averaging procedure. Principal curvatures at each vertex are computed from the smoothed shape operators. Vertices are marked as maxima and/or minima according to the signs of the principal curvatures. Vertices marked as having the same feature type are clustered together by adjacency on the mesh to provide candidate patches. Feature scores are computed for each candidate patch and the scores are provided as output to a user or for further processing.Type: GrantFiled: August 14, 2007Date of Patent: November 8, 2011Assignee: The Board of Trustees of the Leland Stanford Junior UniversityInventors: Padmavathi Sundaram, Sandy A. Napel, Christopher F. Beaulieu, Afra J. Zomorodlan
-
Patent number: 8045782Abstract: A computer-based method for the development of an image analysis protocol for analyzing image data, the image data containing images including image objects, in particular biological image objects such as biological cells. The image analysis protocol, once developed, is operable in an image analysis software system to report on one or more measurements conducted on selected ones of the image objects. The development process includes providing functions for selecting predetermined image analysis procedures, the functions allowing the user to define: at least one first target identification setting for identifying a first target set of image objects in the image data; at least one second target identification setting for identifying a second target set of image objects in the image data; a relationship between the first and second set of image objects; and one or more measurements which are to be reported for the image data, the measurements being conducted using the defined relationship.Type: GrantFiled: December 7, 2004Date of Patent: October 25, 2011Assignee: GE Healthcare Niagara, Inc.Inventors: Xudong Li, Louis Ernest Dagenais, William Mark Durksen, Del Archer
-
Patent number: 8041124Abstract: Computer graphics may be detected in digital images by extracting a first set of features from an input digital image, extracting a second set of features from a prediction-error image derived from the input digital image, and applying a classification algorithm to the first set of features and the second set of features to determine if the combined sets of features indicate that the input digital image corresponds to computer graphics.Type: GrantFiled: January 18, 2007Date of Patent: October 18, 2011Assignee: New Jersey Institute of TechnologyInventors: Yun Qing Shi, Wen Chen
-
Patent number: 8036423Abstract: A system for identifying artifacts in an image. The system includes an input for receiving images from an imager, the images comprising a pixel of interest. The images can be generated by reflecting light off an object. The system further includes a processor coupled to the input for defining and using at least one contrast value of a second pixel associated with the pixel of interest to identify artifacts in the image.Type: GrantFiled: October 11, 2006Date of Patent: October 11, 2011Assignee: Avago Technologies General IP (Singapore) Pte. Ltd.Inventor: Richard Haven
-
Patent number: 8036466Abstract: A method of approximating the inner or outer boundary of an iris comprises generating an approximate boundary representation (20) comprising a least squares approximation by a cosine transform series of a function of the angle (?) about a fixed point (A) of the distance of measured points (10) on the boundary from the fixed point (A). More broadly, the method may be used to approximate the shape of any two-dimensional curve or figure.Type: GrantFiled: January 17, 2007Date of Patent: October 11, 2011Inventor: Donald Martin Monro
-
Patent number: 8031916Abstract: The biometric information input apparatus comprises a fingerprint sensor which detects biometric information, and moisture absorbing units and which are arranged adjacent to the fingerprint sensor and absorb moisture. The moisture absorbing units and have a groove structure which generates a capillary phenomenon. The fingerprint sensor is of the sweep type which scans biometric information through relative displacement with the finger, and is formed in parallel with the direction of relative displacement between the groove structure and the finger. The groove structure has a width smaller than the pitch of the ridges of an average fingerprint.Type: GrantFiled: April 19, 2006Date of Patent: October 4, 2011Assignee: Fujitsu LimitedInventors: Yukihiro Abiko, Takashi Shinzaki, Kiyohiko Ikeda, Fumie Shiroyama
-
Patent number: 8031931Abstract: A spatial mask printer may be used in conjunction with an optical inspection tool. The tool can be used to obtain a Fourier image of an inspected object, and a filter mask image can be designed to block certain aspects of the object's image in the Fourier plane corresponding to repetitive aspects of the imaged object. The filter mask image can then be printed and used in the tool during the inspection process. The mask image may be designed by hand or by computer and may be stored for later use. Filters may be automatically placed into the optical path of the inspection tool by a filter wheel, or may be housed in other filter banks. The printer may be configured to operate in a clean room environment, and may be integrated into the optical inspection tool.Type: GrantFiled: April 24, 2006Date of Patent: October 4, 2011Assignee: Applied Materials South East Asia Pte. Ltd.Inventors: Dan T. Fuchs, Shai Silberstein
-
Patent number: 8031914Abstract: Face-based image clustering systems and methods are described. In one aspect, face regions are detected in images. At least one respective parameter value is extracted from each of the face regions. Ones of the face regions associated with parameter values satisfying a cluster seed predicate are classified as cluster seed face regions. The cluster seed face regions are clustered into one or more clusters. A respective face model is built for each of the clusters. The face models are stored. In another aspect, face regions are detected in images. At least one respective parameter value is extracted from each of the face regions. The face regions are ranked based on the extracted parameter values. The face regions are clustered in rank order into one or more clusters. Representations of ones of the clusters are rendered on a display.Type: GrantFiled: October 11, 2006Date of Patent: October 4, 2011Assignee: Hewlett-Packard Development Company, L.P.Inventor: Tong Zhang
-
Patent number: 8014586Abstract: Apparatus, systems, and methods to recognize features on bottom surfaces of containers on a container production line, detect defects in the containers, and correlate the defects to specific production equipment of the container production line, based in part on the recognized features. The system includes imaging apparatus, programmable processing devices, and encoders. The methods include synchronization techniques and correlation techniques.Type: GrantFiled: May 24, 2007Date of Patent: September 6, 2011Assignee: Applied Vision CorporationInventors: Richard A. Sones, Carl E. Sebeny, Brian M. Baird, Michael A. Kress, Michael L. Kress
-
Patent number: 8014587Abstract: Disclosed is a pattern test method in which a drawing region is divided into a plurality of deflection regions determined by the deflection width of a deflector of a charged beam lithography apparatus, the charged beam lithography apparatus draws a pattern in each divided deflection region on the basis of pattern design data to obtain a sample, and a defect of the pattern on the sample is tested. The method determines the coordinates of a connecting portion of the deflection regions, divides the pattern design data into boundary region pattern data as the connecting portion of the deflection regions and pattern data except for the boundary region pattern data, and obtains image data of the pattern formed on the sample. The method then compares the boundary region pattern data with the image data.Type: GrantFiled: August 27, 2007Date of Patent: September 6, 2011Assignee: Kabushiki Kaisha ToshibaInventor: Yumi Watanabe
-
Patent number: 8009896Abstract: A coplanarity inspection device for a printed circuit board includes a base, a supporting disk, a driver, a printed circuit board, a light source, an image acquisition means, and a controller. The supporting disk is arranged on the base, and the driver rotates the supporting disk. The printed circuit board is placed on the supporting disk, and includes a to-be measured side facing downward. The light source projects light beams on the to-be measured side of the printed circuit board. The image acquisition means aims at a specific area of the to-be measured side for image acquisition. The controller is to control the driver, and to store image taken by the image acquisition means. As such, the coplanarity inspection device for a printed circuit board can be employed to inspect whether the coplanarity of the printed circuit board satisfies the standard of setting values in a certain range.Type: GrantFiled: March 4, 2008Date of Patent: August 30, 2011Assignee: King Yuan Electronics Co., Ltd.Inventor: Chiu-Fang Chang
-
Patent number: 8009873Abstract: A method of providing identification of an entity includes maintaining a database of identification data specific to the appearance and condition of entities, providing a unique description for each entity enabling access to the entity's identification data in the database, providing identification means adapted for portage with the entity and containing the unique description and maintaining secondary databases containing the entity's identification data as acquired from prior encounters so that multiple comparisons can be made to assure that the individual bearing the identification means is the same individual to whom the identification means were issued.Type: GrantFiled: June 6, 2005Date of Patent: August 30, 2011Assignee: Neotec Holdings LimitedInventor: Bryan P. Chapman
-
Patent number: 8005273Abstract: Methods and systems are provided for analyzing and assessing documents using a writing profile for documents, such as a payment instrument. A method may include providing a document to a computer system. In an embodiment, the method may further include comparing writing in one or more non-signature information fields of the document to at least one forger writing profile representation. In some embodiments, at least one forger writing profile representation may be obtained from at least one non-signature information field of at least one document that includes forged information. In an embodiment, the document may be identified as a document including forged information from an approximate match of at least one forger writing profile representation with writing in the document.Type: GrantFiled: April 26, 2010Date of Patent: August 23, 2011Assignee: Computer Sciences CorporationInventors: Gilles Houle, Ronny Bakker, Johan Willem Piere Berkhuysen, Malayappan Shridhar, James G. Mason, Katerina Blinova, Babur Nugmanov
-
Patent number: 7983472Abstract: A method detects a position of a mark based on an image signal of the mark. The method includes steps of obtaining a first position of the mark by performing a first process for the image signal, extracting plural feature values from the image signal based on the first position, and detecting the position of the mark by obtaining an offset value for the first position based on the plural feature values.Type: GrantFiled: October 5, 2005Date of Patent: July 19, 2011Assignee: Canon Kabushiki KaishaInventor: Satoru Oishi
-
Patent number: 7961947Abstract: A method of cleaning facial marker data, the method comprising: decimating frames of survey facial marker data into representative frames of key facial poses; generating a facial pose matrix using the representative frames of key facial poses; and cleaning incoming frames of facial marker data using the facial pose matrix.Type: GrantFiled: July 27, 2007Date of Patent: June 14, 2011Assignees: Sony Corporation, Sony Pictures Entertainment Inc.Inventors: Demian Gordon, Parag Havaldar
-
Patent number: 7957584Abstract: A detection method is based on a statistical analysis of the appearance of model patches from all possible viewpoints in the scene, and incorporates 3D geometry during both matching and pose estimation processes. By analyzing the computed probability distribution of the visibility of each patch from different viewpoints, a reliability measure for each patch is estimated. That reliability measure is useful for developing industrial augmented reality applications. Using the method, the pose of complex objects can be estimated efficiently given a single test image.Type: GrantFiled: March 4, 2010Date of Patent: June 7, 2011Assignee: Siemens CorporationInventors: Hesam Najafi, Yakup Genc
-
Patent number: 7949196Abstract: A method and apparatus is disclosed herein for decoding data (e.g., video data) using transforms. In one embodiment, the decoding process comprises scaling a block of coefficients using a scaling factor determined for each coefficient by computing an index for said each coefficient and indexing a look-up table (LUT) using the index. The index is based on a quantization parameter, a size of the block of coefficients, and a position of said each coefficient within the block. The method also comprises applying a transform to the block of scaled coefficients.Type: GrantFiled: October 13, 2009Date of Patent: May 24, 2011Assignee: NTT Docomo, Inc.Inventor: Frank Jan Bossen
-
Patent number: 7929770Abstract: A handwriting processing apparatus and method effective for search of, e.g., a document file including handwriting is provided. When a handwriting characters are input to a coordinate input unit as a search key, a corresponding character in a dictionary is recognized for each of the handwritten characters, a search unit searches for a text code stored in a document file storage unit based on a text code of the corresponding character if the corresponding character is recognized and the search unit searches for handwriting trail data stored in a handwriting trail storage unit based on a handwriting trail of the handwriting character if the corresponding character is not recognized, thereby finding a desired document file.Type: GrantFiled: May 22, 2007Date of Patent: April 19, 2011Assignee: Canon Kabushiki KaishaInventor: Tsunekazu Arai
-
Patent number: 7929756Abstract: A method for associating with a digital image a class of a plurality of predefined classes having respective models, the method including the phases of dividing the digital image pixel by pixel into one or more regions belonging to a set of predefined regions that differ from each other on account of their type of content, the division being effected by establishing whether or not a pixel of the image belongs to a respective region on the basis of an operation of analyzing the parameters this pixel, the analysis operation being carried out by verifying that the parameters satisfy predefined conditions and/or logico-mathematical relationships of belonging to the respective region, acquiring from the digital image divided into regions information regarding the regions that are present in it, comparing this information with at least one model characterizing a respective class of said plurality, and associating with the digital image a class on the basis of the comparison phase.Type: GrantFiled: June 5, 2009Date of Patent: April 19, 2011Assignee: STMicroelectronics S.r.l.Inventors: Salvatore Curti, Sebastiano Battiato, Emiliano Scordato, Marcello Tortora, Edoardo Ardizzone, Marco La Cascia