Patents Examined by Jonathan Schaffer
-
Patent number: 7430315Abstract: The face detection system and method attempts classification of a test image before performing all of the kernel evaluations. Many subimages are not faces and should be relatively easy to identify as such. Thus, the SVM classifier try to discard non-face images using as few kernel evaluations as possible using a cascade SVM classification. In the first stage, a score is computed for the first two support vectors, and the score is compared to a threshold. If the score is below the threshold value, the subimage is classified as not a face. If the score is above the threshold value, the cascade SVM classification function continues to apply more complicated decision rules, each time doubling the number of kernel evaluations, classifying the image as a non-face (and thus terminating the process) as soon as the test image fails to satisfy one of the decision rules.Type: GrantFiled: June 1, 2004Date of Patent: September 30, 2008Assignee: Honda Motor Co.Inventors: Ming-Hsuan Yang, Jongwoo Lim, David Ross, Takahiro Ohashi
-
Patent number: 7430308Abstract: Computer aided diagnosis techniques in medical imaging are developed for the automated differentiation between benign and malignant lesions and go beyond computer aided detection by providing cancer likelihood for a detected lesion given image and/or patient characteristics. A computer aided detection and diagnosis algorithm for mammographic calcification clusters is developed and evaluated. The emphasis is on the diagnostic component although the algorithm includes automated detection, segmentation, and classification steps based on wavelet filters and artificial neural networks. Classification features are selected primarily from descriptors of the morphology of the individual calcifications and the distribution of the cluster as well as patient's demographics as input to the network.Type: GrantFiled: November 26, 2003Date of Patent: September 30, 2008Assignee: University of South FloridaInventor: Maria Kallergi
-
Patent number: 7428326Abstract: The present invention features a method whereby each vacuum nozzle in a multi-spindle component placement machine is inspected placement cycle. This process also allows for updating calibration of the nozzle position as well as immediate feedback regarding the condition of the vacuum nozzle. A chipped orifice or otherwise damaged nozzle is detected using a vision system and comparing the currently acquired image of each nozzle with the image of an “ideal” nozzle. Likewise, contamination such as adhesive on the nozzle is detected before that contamination can affect placement accuracy. Because of the nozzle inspection during the placement cycle, there is no slowdown of the placement machine cycle rate.Type: GrantFiled: December 2, 2002Date of Patent: September 23, 2008Assignee: Universal Instruments CorporationInventor: Koenraad Gieskes
-
Patent number: 7376246Abstract: A method tracks non-rigid objects in a video acquired of a cluttered scene by a camera. The method uses a particle filter. The tracking includes the following steps: motion transition estimation, contour deformation detection, and contour regulation. The method uses a dynamic affine transform model and employs the particle filter to estimate the parameters of the model. The method generates a probabilistic map of deformation for tracking the contour of the object followed by a projection step to constrain or regulate the contour in a contour subspace.Type: GrantFiled: June 27, 2005Date of Patent: May 20, 2008Assignee: Mitsubishi Electric Research Laboratories, Inc.Inventors: Jie Shao, Fatih M. Porikli
-
Patent number: 7376275Abstract: Systems and methods for performing clustering of a document image are disclosed. A property of an extracted mark from a document is compared to the properties of the existing clusters. If the property of the mark fails to match any of the properties of the existing clusters, the mark is added as a new cluster to the existing cluster. One property that can be utilized is x size and y size, which is the width and height, of the existing clusters. Another property that can be employed is ink size, which refers to the ratio of black pixels to total pixels in a cluster. Yet another property that can be utilized is a reduced mark or image, which is a pixel size reduced version the bitmap of the mark and/or cluster. The above properties can be employed to identify mismatches and reduce the number of bit by bit comparisons performed.Type: GrantFiled: August 5, 2005Date of Patent: May 20, 2008Assignee: Microsoft CorporationInventors: Patrice Y. Simard, Henrique S. Malvar, Erin L. Renshaw
-
Patent number: 7346209Abstract: A detection and classification method of a shape in a medical image is provided. It is based on generating a plurality of 2-D sections through a 3-D volume in the medical image. In general, there are two steps. The first step is feature estimation to generate shape signatures for candidate volumes containing candidate shapes. The feature estimation method computes descriptors of objects or of their images. The second general step involves classification of these shape signatures for diagnosis. A classifier contains, builds and/or trains a database of descriptors for previously seen shapes, and then maps descriptors of novel images to categories corresponding to previously seen shapes or classes of shapes.Type: GrantFiled: September 30, 2003Date of Patent: March 18, 2008Assignee: The Board of Trustees of the Leland Stanford Junior UniversityInventors: Salih B. Gokturk, Carlo Tomasi, Acar Burak, Christopher F. Beaulieu, Sandy A. Napel, David S. Paik
-
Patent number: 7343042Abstract: The present application describes systems and methods for composing documents using a digital pointing instrument. In further configurations, a user utilizes a pen to trace a form serial number that is utilized to identify a form template that is used to process input data from a digital pen.Type: GrantFiled: September 30, 2002Date of Patent: March 11, 2008Assignee: Pitney Bowes Inc.Inventors: John F. Braun, John W. Rojas, James R. Norris, Jean-Hiram Coffy, Arthur Parkos, Alan Leung, Wendy Chui Fen Leung
-
Patent number: 7327882Abstract: The invention is a method for locating characters in digital images, using an image layering process. The method includes the transforming the digital data of the digital image into normalized digital color image data and into digital grayscale image data; discarding redundant components of the normalized digital color image data and/or the digital grayscale image data; generating binary image layers from the non-discarded grayscale and normalized color image data according to a layering process; and using a recognition algorithm on the binary image layers to recognize connected components that can represent characters or part of characters contained in the digital image.Type: GrantFiled: May 7, 2002Date of Patent: February 5, 2008Assignee: Nokia CorporationInventors: Kongqiao Wang, Jan Kangas
-
Patent number: 7327887Abstract: System and method for estimating a rotational shift between a first discrete curve and a second discrete curve, where the second discrete curve is a rotationally shifted version of the first discrete curve. First and second discrete curves are received. A rotational shift between the first discrete curve and the second discrete curve is estimated based on the first discrete curve and the second discrete curve. A cumulative rotational shift is updated based on the estimated rotational shift. A rotationally shifted version of the second discrete curve is generated based on the cumulative rotational shift. The estimating, updating, and generating are performed in an iterative manner using the respective rotationally shifted discrete curve for each iteration until a stopping condition occurs, thereby determining a final estimate of the rotational shift between the first discrete curve and the second discrete curve. The final estimate may be used to perform curve matching.Type: GrantFiled: May 6, 2003Date of Patent: February 5, 2008Assignee: National Instruments CorporationInventor: Lothar Wenzel
-
Patent number: 7327890Abstract: A method is provided for determining an area of importance in an archival image. In accordance with the method, an evaluation images is obtained during composition of an archival image and the archival image is obtained. The evaluation image is compared to the archival image to determine common image elements and area of importance data is determined that identifies the common image elements. The area of importance data is associated with the archival image.Type: GrantFiled: December 20, 2002Date of Patent: February 5, 2008Assignee: Eastman Kodak CompanyInventor: John R. Fredlund
-
Patent number: 7321678Abstract: A banknote identifying machine and method for testing a banknote for genuineness stably without being affected by a sensor or contamination on the banknote. Transmission photosensors 61 are moved over a banknote to be tested to scan the banknote with a light beam along reading lines L to obtain patterns of an amount of transmitted light through the banknote (FIGS. 3(b) and 3(c)). Patterns (1a, 1b) of an amount of transmitted light corresponding to watermark portions are evaluated with maximum values (11, 12) of patterns of an amount of transmitted light corresponding to ordinary design portions other than the watermarks to determine whether or not there is any watermark in the banknote and to authenticate it.Type: GrantFiled: November 11, 2002Date of Patent: January 22, 2008Assignee: Kabushiki Kaisha Nippon ConluxInventor: Eiji Itako
-
Patent number: 7319790Abstract: An image comparing apparatus for comparing a particular inspect image with a search image containing a subject shown on the inspect image, including a search-image supplying unit storing therein a plurality of search images, an image acquisition unit acquiring information characterizing the subject image, the image acquisition unit selectively extracting at least one search image from the search image supplying unit according to the acquired information, and an image specifying unit specifying a particular search image by comparing the inspect image with each of the search-images extracted by the image acquisition unit.Type: GrantFiled: June 25, 2002Date of Patent: January 15, 2008Assignee: FUJIFILM CorporationInventor: Shuji Ono
-
Patent number: 7315634Abstract: A method and a system for comparing a set of minutiae of a current image with a set of minutiae of a reference image, according to which the minutiae are sorted by their Cartesian coordinates in the image plane from a predetermined point of origin, a common path of similar minutiae is searched in the reference set and in the current set, and it is considered that there is an identity between the two images if the common path is comprised of a number of segments greater than a first threshold.Type: GrantFiled: September 4, 2002Date of Patent: January 1, 2008Assignee: STMicroelectronics S.A.Inventor: Lionel Martin
-
Patent number: 7313267Abstract: A method and computer program product are disclosed for automatically encoding a complex system architecture for a pattern recognition classifier. A plurality of subclassifier states are defined as a plurality of sets of state variables, each set of variables corresponding to a subclassifier state. A set of rules are then determined for a state machine governing transitions between the plurality of subclassifier states. The plurality of sets of state variables and the determined rules are encoded into a configuration file. This configuration file is provided to a generic classifier system, including a state machine and a predefined generic classifier object.Type: GrantFiled: November 13, 2002Date of Patent: December 25, 2007Assignee: Lockheed Martin CorporationInventors: Charles Call, Elliott D. Reitz, II, Dennis A. Tillotson
-
Patent number: 7310433Abstract: An overlapped portion of a plurality of partial images of a fingerprint that are input from a fingerprint input device (7) is corrected to be reconfigured at a reconfiguration process section (106). The characteristics are extracted from the input partial images at the fingerprint characteristic information extracting section (110) and the extracted characteristic information is stored in an input characteristic information memory. A verification process section executes DP comparison (dynamic programming method) between the characteristic information stored in the input characteristic information memory and the characteristic information stored in the registered characteristic information memory. The distance value obtained by the DP comparison is compared to a threshold that is previously set. If the distance value is smaller than the threshold, it is judged the fingerprint is identified and if the distance value is larger than the threshold, it is judged that the fingerprint is not identified.Type: GrantFiled: July 11, 2001Date of Patent: December 18, 2007Assignees: Ume Tech Yugen Kaisha, Kabushiki Kaisha DDSInventors: Taizo Umezaki, Kenji Miyoshino, Tatsuhiko Sugimoto, Toshio Ishizaka
-
Patent number: 7305122Abstract: The present invention recites a method and computer program product for identifying and correcting systematic noise in a pattern recognition classifier. A plurality of input patterns that have been determined not to be associated with any of a set of at least one represented output class are rejected by the pattern recognition classifier. A subset of pattern samples is selected from the rejected input patterns based upon the similarity of each pattern to one of the represented output classes. The selected pattern samples are subjected to an independent review to determine if they were correctly rejected. The classifier is retrained based upon this independent review of the selected pattern samples.Type: GrantFiled: August 13, 2002Date of Patent: December 4, 2007Assignee: Lockheed Martin CorporationInventors: David L. Ii, Elliott D. Reitz, II, Dennis A. Tillotson
-
Patent number: 7302101Abstract: Detecting video phenomena, such as fire in an aircraft cargo bay, includes receiving a plurality of video images from a plurality of sources, compensating the images to provide enhanced images, extracting features from the enhanced images, and combining the features from the plurality of sources to detect the video phenomena. The plurality of sources may include cameras having a sensitivity of between 400 nm and 1000 nm and/or may include cameras having a sensitivity of between 7 and 14 micrometers. Extracting features may include determining an energy indicator for each of a subset of the plurality of frames. Detecting video phenomena may also include comparing energy indicators for each of the subset of the plurality of frames to a reference frame.Type: GrantFiled: August 21, 2002Date of Patent: November 27, 2007Assignee: Simmonds Precision Products, Inc.Inventors: Radoslaw Romuald Zakrzewski, Mokhtar Sadok
-
Patent number: 7302087Abstract: The Present invention relates to a method of recognizing the human iris corresponding to a field of a biometric technology, and more particularly to a method of recognizing human iris using Daubechies wavelet transform, wherein the dimensions of characteristic vectors are reduced by extracting iris features from inputted iris image signals through the Daubechies wavelet transform, binary characteristic vectors are generated by applying quantiztion functions to the extracted characteristic values so that utility of human iris recognition can be improved since storage capacity arid processing time thereof can be improved since storage capacity characteristic vectors, and a measurement process suitable for the low capacity characteristic vectors is employed when measuring vectors and previously registered characteristic vectors.Type: GrantFiled: September 5, 2003Date of Patent: November 27, 2007Assignee: Senga Advisors, LLCInventor: Seong-Won Cho
-
Patent number: 7298887Abstract: A system for and a method of analyzing the surface condition of a PCB using RGB colors are disclosed. The analyzing method includes the steps of feeding a target PCB, to be measured, to an image pick-up position where a pick-up unit is disposed, by a feeding unit, picking up an image of a metal surface of the fed target PCB, extracting pixel data from the picked-up image for the target PCB, performing a mapping operation for RGB signals of the extracted pixel data in accordance with a mapping program, thereby determining relative RGB values, producing cumulative distribution data of the relative RGB values for the target PCB in accordance with an RGB-mapping process, and quantitatively determining the oxidation degree of the target PCB metal surface exhibited with the lapse of time, based on the cumulative distribution data.Type: GrantFiled: September 24, 2003Date of Patent: November 20, 2007Assignee: Samsung Electro-Mechanics Co., LtdInventors: Hyo-Soo Lee, Young-Hwan Shin, Chong-Ho Kim
-
Patent number: 7298874Abstract: The present invention relates to an iris recognition method which is one of biometric technologies. According to a non-contact-type human iris recognition method by correction of a rotated iris image of the present invention, the iris image is acquired by image acquisition equipment using an infrared illuminator. Inner and outer boundaries of the iris are detected by analyzing differences in pixels of a Canny edge detector and the image for the inputted iris image, so as to allow the boundaries of the iris to be more accurately detected from the eye image of a user. Thus, the iris image with a variety of deformation can be processed into a correct iris image, so that there is an advantage in that a false acceptance rate and a false rejection rate can be markedly reduce.Type: GrantFiled: September 5, 2003Date of Patent: November 20, 2007Assignee: Senga Advisors, LLCInventor: Seong-Won Cho