Patents Examined by Claire Wang
-
Patent number: 7724916Abstract: Data may be embedded in rows of text by modulating inter-word spaces in a row. Inter-word spaces in a particular row may be divided into two or more sets of (approximately) equal spacing. The inter-word spaces of one or more of the sets may then be modified to embed data.Type: GrantFiled: January 3, 2006Date of Patent: May 25, 2010Assignee: New Jersey Institute of TechnologyInventors: Yun-Qing Shi, Dekun Zou
-
Patent number: 7715603Abstract: A method and a device are disclosed for processing available time/phase-dependent primary data sets of a computer tomography of a displaced object, preferably a beating heart, in order to produce an image sequence 3D-recording set records for representing the displacement of an object. The method includes the following steps: calculating and representing of a 3D reference display of any particular orientation in relation to any particular displacement phase of an available present primary data sequence of a CT-scan, determining the desired calculation parameters of the image sequence which is to be calculated, single transfer of the calculation parameter to the calculation process and automatic creation of the entire image sequence with the predetermined calculation parameters.Type: GrantFiled: January 30, 2004Date of Patent: May 11, 2010Assignee: Siemens AktiengesellschaftInventor: Matthias Niethammer
-
Patent number: 7706593Abstract: A method for verifying areas within an image corresponding to monetary banknotes includes: dividing the image into a plurality of verification sections; generating a banknote boundary map having border sections corresponding to boundaries of valid monetary banknotes; generating a texture decision map from the image having texture sections each having texture values within a valid range according to a valid monetary banknote, determining objects in the texture decision map by removing texture sections in the texture decision map corresponding to border sections in the banknote boundary map; calculating a texture property value for objects according to texture feature values for each verification section; calculating shape property values for each object; and further removing texture sections from the texture decision map corresponding to objects that do not have the texture property value within a first predetermined range and the shape property value within a second predetermined range.Type: GrantFiled: September 20, 2006Date of Patent: April 27, 2010Assignee: Primax Electronics Ltd.Inventors: Xu-Hua Liu, Byung-Tae Oh, Young-Min Kwak, Chung-Chieh Kuo, Chen-Ning Hsi
-
Patent number: 7706592Abstract: A method for detecting a boundary of a monetary banknote within an image includes dividing the image into a plurality of sections; generating a color feature map containing color histogram data for each section of the image; generating a gray level feature map indicating a gray level value for each section of the image; recording border sections onto a banknote boundary map, the border sections being sections having color histogram data within a first predetermined range and gray level values within a second predetermined range; removing internal border sections enclosed by perimeter border sections from the banknote boundary map; and dilating the perimeter border sections on the banknote boundary map.Type: GrantFiled: September 20, 2006Date of Patent: April 27, 2010Assignee: Primax Electronics Ltd.Inventors: Xu-Hua Liu, Byung-Tae Oh, Young-Min Kwak, Chung-Chieh Kuo, Ying-Jieh Huang
-
Patent number: 7689002Abstract: The invention concerns a method of detecting from a vehicle a bend in a road comprising a surface and road edges, comprising the following operations: taking an image of a road scene unfolding in front of the vehicle and at least partly illuminated by the vehicle, determining, for each pixel in the image a light decrease gradient, analysing these decrease gradients and determining an image of the road edges, mathematically discriminating the gradients from the image of the road edges, analyzing this discrimination and determining edges, and an angle of the bend. The invention also concerns a system for implementing the method of the invention comprising a camera mounted in the vehicle, an image processing unit and a neural network.Type: GrantFiled: December 19, 2003Date of Patent: March 30, 2010Assignee: Valeo VisionInventors: Maurice Milgram, Didierl Dumoncel, Catherine Achard, William Ivaldi
-
Patent number: 7680302Abstract: The present invention is directed to a real-time automated video cognizer that functions as a facial video processor for detecting drowsiness in operators of motorized vehicles, including the use of a video cognizer to provide pattern recognition and control signal generation during monitoring of macroscopic or microscopic biological processes. More specifically, the present invention accepts input from a video monitoring system that continuously captures the operator's facial images; employing three sequential means of processing the digitized video information to extract the position and configuration of drowsy-relevant facial features and numerically processes this information to yield a quantitative estimate of drowsiness probability in each epoch of monitoring.Type: GrantFiled: December 20, 2007Date of Patent: March 16, 2010Inventor: Morris Steffin
-
Patent number: 7672503Abstract: A direction-recognizing apparatus has a photographing unit, an image database, an image-recognizing unit, and a direction-recognizing unit. The database stores registered images and direction-data items associated with the registered images. The image-recognizing unit receives an input image and compares the input image with the registered images stored in the database. The image-recognizing unit selects one registered image that is identical or similar to the input image. The direction-recognizing unit recognizes a direction from the direction data associated with the registered image selected by the image-recognizing unit. The database may store N direction-data items associated with N surface segments SN of the circumferential surface of a pole. If so, the images registered in the database represent direction-recognition regions ASN that are larger than the N surface segments SN.Type: GrantFiled: August 9, 2004Date of Patent: March 2, 2010Assignee: Sony CorporationInventors: Hidehiko Morisada, Shingo Tsurumi
-
Patent number: 7646904Abstract: Candidate anomalies in an anatomical structure are processed for classification. For example, false positives can be reduced by techniques related to the anomaly's neck, wall thickness associated with the anomaly, template matching performed for the anomaly, or some combination thereof. The various techniques can be combined for use in a classifier, which can determine whether the anomaly is of interest. For example, a computed tomography scan of a colon can be analyzed to determine whether a candidate anomaly is a polyp. The technologies can be applied to a variety of other scenarios involving other anatomical structures.Type: GrantFiled: July 9, 2007Date of Patent: January 12, 2010Assignee: The United States of America as represented by the Department of Health and Human ServicesInventors: Ronald M. Summers, Marek Franaszek, Gheorghe Iordanescu
-
Patent number: 7646889Abstract: A rain sensor provided in a vehicle includes a camera and a processor. The camera takes an image of a scene outside of the vehicle through a windshield of the vehicle with an infinite focal length. The processor detects rain based on a variation degree of intensities of pixels in the image from an average intensity of the pixels.Type: GrantFiled: March 16, 2006Date of Patent: January 12, 2010Assignee: DENSO CORPORATIONInventor: Takeshi Tsukamoto
-
Patent number: 7639850Abstract: An apparatus for and a method of analyzing components using microscopic regions. The apparatus includes: an image obtainer obtaining an image of a part of a living body; a color information generator generating color information of an image having a matrix pattern from a size of the microscopic regions and the obtained image; a first data transformer transforming the color information of the image into a product of first and second matrixes; and a component analyzer analyzing components of the obtained image using at least one of the first and second matrixes. When the obtained image is divided into a plurality of microscopic regions, the size of the microscopic regions is determined so that concentrations of components of the part fluctuate in each of the microscopic regions.Type: GrantFiled: June 6, 2005Date of Patent: December 29, 2009Assignee: Samsung Electronics Co., Ltd.Inventor: Sang-Joon Han
-
Patent number: 7636482Abstract: One embodiment disclosed relates to a method for encoding and decoding a video sequence in which a keyframe is used to bi-directionally predict frames in the sequence. The keyframe is coded independently of other frames in the sequence. Both a prior frame occurring before the keyframe and a subsequent frame occurring after the keyframe are predicted using data from the keyframe. Another embodiment disclosed relates to a method for allocating bits to a keyframe during video encoding. Effects of a plurality of keyframe bit allocations on quality of a predicted frame are measured. Said effects are used to determine a near optimal keyframe bit allocation.Type: GrantFiled: July 24, 2008Date of Patent: December 22, 2009Assignee: Altera CorporationInventors: David B. Kita, Tser-Yuan Brian Yang, Dylan SeLegue
-
Patent number: 7630530Abstract: Segmenting a digitized image includes providing a diffusion tensor field image, partitioning the image into 2 regions, each point being assigned to one of the regions, associating a level-set function with each region, the level-set function having a negative value in one region and a positive value in the other region, calculating a mean value of the diffusion tensor field over each of 2 regions, initializing an energy defined as a functional of level-set functions and diffusion tensor field, changing the region membership of each point in the image if the energy functional value decreases as a result of region membership change and updating said mean value of said diffusion tensor field over each of 2 regions, and obtaining a segmentation of the image when the magnitude of the change of the energy function value resulting from changing the region membership of a point is less then a predetermined threshold.Type: GrantFiled: January 9, 2006Date of Patent: December 8, 2009Assignee: Siemens Medical Solutions USA, Inc.Inventors: Tim McGraw, Zhizhou Wang
-
Patent number: 7623679Abstract: A method and apparatus for approximating a path of movement of a target. The method includes referencing a temporal sequence of images, identifying a plurality of data points associated with a selected volume element of the volume of interest, and calculating an estimated location of the selected volume element based on a cost function having a constraint which favors continuous spatial motion of the selected volume element over time. Each of the images of the temporal sequence of images depicts a volume of interest. Each of the plurality of data points corresponds to one of the images.Type: GrantFiled: December 13, 2006Date of Patent: November 24, 2009Assignee: Accuray IncorporatedInventors: Jay B. West, Calvin R. Maurer, Jr.
-
Patent number: 7623680Abstract: An image processing system includes an image sensor that picks up a front-view image in front of an own vehicle. Image processing regions are set to cover on the front-view image, picked up by the image sensor, various portions one after another, which narrow, in area, with different positions in a direction remote from the own vehicle. A feature is extracted out of image processing a portion of the front-view image covered by the image processing regions. The extracted feature is used for vehicle detection.Type: GrantFiled: July 1, 2005Date of Patent: November 24, 2009Assignee: Nissan Motor Co., Ltd.Inventors: Taku Takahama, Takeshi Kimura, Naotaka Usui
-
Patent number: 7620222Abstract: Tumors are judged by a medical image diagnosis aiding apparatus that employs a computer, based on image patterns, which are obtained from the density values of images and which are inherent in medical images, in a manner approximating human visual perception. Candidate regions of patterns are extracted from medical image data. The type of pattern of the candidate regions is judged by employing characteristic amounts of an inner/outer outline image, which is an image of the vicinity of the outline of the extracted candidate region.Type: GrantFiled: March 19, 2004Date of Patent: November 17, 2009Assignee: FUJIFILM CorporationInventor: Akira Oosawa
-
Patent number: 7616789Abstract: In a first image forming method, a medical image of an object is inputted, and a normal structure image, which corresponds to the inputted medical image and represents a normal structure of the object, is artificially formed. In a second image forming method, a normal image signal corresponding to a normal image, which is a medical image representing a normal structure of an object, is acquired, a plurality of structure altering vectors for altering the structure of the object are set, and an addition process for adding the plurality of the structure altering vectors to the normal image signal is performed, and a normal structure image signal, which represents a normal structure image of the object, is formed.Type: GrantFiled: May 13, 2003Date of Patent: November 10, 2009Assignee: FUJIFILM CorporationInventor: Akira Oosawa
-
Patent number: 7613320Abstract: A digital watermark embedding apparatus comprises below units. A first generation unit generates a plurality of symbol sequences each of which includes a plurality of symbols including ranks, each of the ranks being uniquely numbered among each of the symbol sequences, each of the symbol sequences uniquely corresponding to each of a plurality of identification information items to be embedded as digital watermark information into each of copies of digital contents. A second generation generates a plurality of to-be-embedded codes corresponding to each of the symbols in each of the symbol sequences. An embedding unit embeds the to-be-embedded codes in each of the copies.Type: GrantFiled: October 6, 2008Date of Patent: November 3, 2009Assignee: Kabushiki Kaisha ToshibaInventor: Hirofumi Muratani
-
Patent number: 7609872Abstract: A method for verifying the authenticity of a document utilizes artifacts of the printing process. The method includes optically capturing at a predetermined magnification a first image of an indicia printed on the authentic document. A corresponding indicia on a document to be authenticated is optically captured at a predetermined magnification. The captured images and the printing process artifacts depicted therein are characterized. Authenticity is verified where the characterization indicates the captured images are sufficiently identical. An indication is issued as to whether the document is authentic.Type: GrantFiled: March 24, 2005Date of Patent: October 27, 2009Assignee: Eastman Kodak CompanyInventors: Thomas M. Plutchak, John R. Lawson
-
Patent number: 7609854Abstract: In a method for representation of medical image information on a display medium an image representation parameter is varied dependent on the position of the observer. Superimpositions of data sets from different medical examinations are thereby displayed. The observer thus has simultaneous access to information from the medical examinations, which makes the diagnosis easier for him or her.Type: GrantFiled: June 7, 2005Date of Patent: October 27, 2009Assignee: Siemens AktiengesellschaftInventors: Rudolf Ackermann, Holger Dresel, Sultan Haider, Rainer Kuth, Klaus Ludwig
-
Patent number: 7590262Abstract: Real-time visual tracking using depth sensing camera technology, results in illumination-invariant tracking performance. Depth sensing (time-of-flight) cameras provide real-time depth and color images of the same scene. Depth windows regulate the tracked area by controlling shutter speed. A potential field is derived from the depth image data to provide edge information of the tracked target. A mathematically representable contour can model the tracked target. Based on the depth data, determining a best fit between the contour and the edge of the tracked target provides position information for tracking. Applications using depth sensor based visual tracking include head tracking, hand tracking, body-pose estimation, robotic command determination, and other human-computer interaction systems.Type: GrantFiled: April 21, 2008Date of Patent: September 15, 2009Assignee: Honda Motor Co., Ltd.Inventors: Kikuo Fujimura, Harsh Nanda