Calculating Weighted Similarity Or Difference (e.g., Dont-care Areas) Patents (Class 382/220)
-
Patent number: 8774526Abstract: Techniques for intelligent image search results summarization and browsing scheme are described. Images having visual attributes are evaluated for similarities based in part on their visual attributes. At least one preference score indicating a probability of an image to be selected into a summary is calculated for each image. Images are selected based on the similarity of the selected images to the other images and the preference scores of the selected images. A summary of the plurality of images is generated including the selected one individual image.Type: GrantFiled: February 8, 2010Date of Patent: July 8, 2014Assignee: Microsoft CorporationInventors: Jingdong Wang, Xian-Sheng Hua
-
Publication number: 20140177970Abstract: Aspects of a device, system, and method for subset determination and processing are described. In certain aspects, a process for subset determination includes determining a reference for correlation with at least one image and identifying a set of images for comparison with the reference. The reference for correlation may be specified by a user based on a desire to determine a subset of certain images from a larger group. The process further includes determining a subset of the set of images based on a correlation between the reference and the set of images. According to various features, a subset of images that not only includes certain images but also excludes certain images may be determined quickly.Type: ApplicationFiled: January 17, 2013Publication date: June 26, 2014Applicant: Broadcom CorporationInventor: Murat Mese
-
Publication number: 20140169687Abstract: Image search systems and methods are provided. The image search system includes a storage unit, a display unit, and a processing unit. The storage unit includes a plurality of image, each having a characteristic value. The processing unit receives a specifying of a target image, analyzes at least one content feature of the target image, obtains at least one capturing feature of the target image, and calculates a characteristic value for the target image according to the at least one content feature and the at least one capturing feature of the target image. The processing unit compares the characteristic value of the target image with the characteristic value of the respective image in the storage unit, thus to generate a similarity score for the respective image in the storage unit. The processing unit displays the images in sequence via the display unit according to the corresponding similarity scores.Type: ApplicationFiled: December 13, 2012Publication date: June 19, 2014Applicant: HTC CORPORATIONInventors: Ying-Chung CHEN, Tai-Ling LU, Wei-Chi CHANG
-
Publication number: 20140161361Abstract: The present disclosure provides a method for determining an applicability of a specific processing device having a specific processing pattern. The method includes the following steps: locating a similarity index between the specific processing pattern and a reference processing pattern of a reference processing device; and confirming the applicability of the specific processing device if the similarity index is no less than a threshold. Besides, a method for assessing an applicability of a new processing pattern for a specific processing device, and a method for determining an applicability of an alternative processing path for a reference processing path are also provided.Type: ApplicationFiled: December 7, 2012Publication date: June 12, 2014Applicant: Taiwan Semiconductor Manufacturing Company, Ltd.Inventors: Ching-Hsi NAN, Hann-Ru Chen, Yu-Hsiu Fu, Wen-Pin Liu
-
Patent number: 8750621Abstract: A method for authenticating security markers includes capturing an image of a region of interest on a product with a camera; storing image data in a two-dimensional array on a microprocessor; counting a number of pixels at or above a predetermined brightness level in the image data with the microprocessor to determine a first score; establishing an area within the image; counting a number of pixels within the area to determine a second score; calculating a ratio of the second score to the first score; and if the ratio is above a predetermined threshold the security marker is authenticated.Type: GrantFiled: April 27, 2011Date of Patent: June 10, 2014Assignee: Eastman Kodak CompanyInventors: Thomas J. Widzinski, Erwin L. Allmann, Thomas D. Pawlik, Judith A. Bose, Gary M. Spinelli, Myra T. Olm
-
Patent number: 8744193Abstract: The image signature extraction device includes an extraction unit and a generation unit. The extraction unit extracts region features from respective sub-regions in an image in accordance with a plurality of pairs of sub-regions in the image, the pairs of sub-regions including at least one pair of sub-regions in which both a combination of shapes of two sub-regions of the pair and relative position between the two sub-regions of the pair differ from those of at least one of other pairs of sub-regions. The generation unit generates an image signature to be used for identifying the image based on the extracted region features of the respective sub-regions, using, for at least one pair of sub-regions, a method different from that used for another pair of sub-regions.Type: GrantFiled: March 12, 2010Date of Patent: June 3, 2014Assignee: NEC CorporationInventors: Kota Iwamoto, Ryoma Oami
-
Patent number: 8718350Abstract: A computerized method for immunohistochemistry analysis of tissue utilizes digital images of multiple adjacent tissue sections aligned within a computerized software and processed with an algorithm to quantify a two-dimensional IHC signature score for each respective slide image. In various embodiments, the IHC score is performed over several adjacent sections and further processed to produce a three-dimensional IHC quantification referred to as an IHC signature map.Type: GrantFiled: April 9, 2012Date of Patent: May 6, 2014Assignee: Regents of the University of MinnesotaInventors: Gregory Metzger, Stephen C. Schmechel, Stephen Dankbar, Jonathan Henriksen
-
Patent number: 8687910Abstract: An image filtering method and apparatus that filter a block of a plane area by using a pseudo-random filter are provided, whereby artifacts generated in image encoding and decoding procedures are removed, the method including: determining a similarity between pixel values of a the first block; and generating a second block by selectively applying a pseudo-random filter on the first block according to a result of based on the determining the determined similarity.Type: GrantFiled: June 18, 2010Date of Patent: April 1, 2014Assignee: Samsung Electronics Co., Ltd.Inventors: Hak-Sup Song, Sun-Mi Park, Woo-Jin Han
-
Publication number: 20140086496Abstract: An image processing device includes an evaluation unit which acquires a search pattern which is an appearance pattern of a person in a scene of a video content containing the scene, where a similar scene is to be searched, and a search target pattern which is an appearance pattern of a person in a video content which is to be a search target of the similar scene, calculates a degree of similarity between the search pattern and the search target pattern, and determines the similar scene on a basis of the calculated degree of similarity.Type: ApplicationFiled: September 23, 2013Publication date: March 27, 2014Applicant: Sony CorporationInventors: Kyosuke Yoshida, Kenji Tanaka, Yukihiro Nakamura, Yoshihiro Takahashi, Kentaro Fukazawa, Kazumasa Tanaka
-
Publication number: 20140079323Abstract: A classification apparatus includes: a spectrogram generation unit that generates a spectrogram of a time variation signal of a classification object by processing the time variation signal of the classification object obtained by a sensor; a two-dimensional Fourier transform calculation unit that calculates a two-dimensional Fourier transform of the generated spectrogram; a similarity calculation unit that calculates a similarity between an template image and an image of the obtained two-dimensional Fourier transform, for each template image corresponding to each phenomenon stored in the template image memorizing unit; and a determination unit that determines whether the time variation signal of the classification object conforms to any of one or more phenomena, on the basis of the calculated similarity.Type: ApplicationFiled: March 8, 2013Publication date: March 20, 2014Applicant: FUJI XEROX CO., LTD.Inventors: Roshan THAPLIYA, Tohru FUSE
-
Patent number: 8648912Abstract: Bicycles present before a vehicle are identified. A picked-up image having intensity values that are in accordance with the temperatures of objects is acquired to extract image regions having intensity values representative of higher temperatures than a background. An object, which includes a pair of first object portions (legs) and a second object portion (a tire), would be identified as a bicycle if the pair of first object portions, which have greater dimensions in length in the vertical direction than in width in the horizontal direction and the distance between which is less than a predetermined value in the horizontal direction, are detected from the extracted image regions and further if the second object portion, which has a different intensity value from any one of the first object portions and also has a length greater than a predetermined value in the vertical direction, is existent between the pair of first object portions.Type: GrantFiled: October 8, 2009Date of Patent: February 11, 2014Assignee: Honda Motor Co., Ltd.Inventors: Kodai Matsuda, Makoto Aimura, Izumi Takatsudo
-
Patent number: 8639037Abstract: A method and system for calculating oblong-shape rotation angles from image data of arbitrary size using running sums is described without the need of eigenvector routines and storage of the image data. The oblong shape may be of arbitrary size and location and need not be precisely elliptical. A few running sums are calculated and stored throughout each scan, and the results are obtained in closed form by simple post-scan computation. An algorithmic embodiment can execute on one or more hardware processors with limited or otherwise constrained computation power, available instruction cycles, available memory, etc. Hardware processors may CPUs found in desktops, laptops, tablets, or handheld computing devices. The resulting arrangement may be used for touch or optical user interfaces, real-time image recognition, real-time machine vision, and other purposes.Type: GrantFiled: March 18, 2013Date of Patent: January 28, 2014Inventor: Lester F. Ludwig
-
Patent number: 8630461Abstract: A system stores reference data generated by associating image feature point data with an image-capturing position and a recorded vehicle event. The system generates data for matching by extracting image feature points from an actually-captured image. The system generates information on an actual vehicle event, extracts first reference data whose image-capturing position is located in a vicinity of an estimated position of the vehicle, and extracts second reference data that includes a recorded vehicle event that matches the actual vehicle event. The system performs matching between at least one of the first reference data and the second reference data, and the data for matching, and determines a position of the vehicle based on the matching.Type: GrantFiled: January 25, 2011Date of Patent: January 14, 2014Assignee: Aisin AW Co., Ltd.Inventors: Takayuki Miyajima, Yuusuke Morita
-
Patent number: 8620093Abstract: A system and method for detecting changes by comparing images which cover the same physical area but are collected at different times, the system comprising: at least one input for inputting an image of a target area; the image of the target area having signatures representing outstanding features; at least one processor operating to divide the image of a target area into a plurality of target subimages; at least one memory comprising reference data comprising reference subimages taken at or near the target area at various times, the at least one processor operating to determine a sparse image representation from the reference data; the sparse image representation of the target data being a linear combination of reference data from corresponding reference subimages stored in the at least one memory; the at least one processor operating to compare the target image to the sparse image representation and to match signatures from the target image to the sparse image representation to register the images and perfoType: GrantFiled: October 19, 2010Date of Patent: December 31, 2013Assignee: The United States of America as represented by the Secretary of the ArmyInventors: Lam Huy Nguyen, Trac D Tran
-
Patent number: 8611673Abstract: A web-based application provides more accurate and clearer methods of searching, sorting, and displaying a set of images stored in a database. A first aspect of the present invention is the method by which image data is stored. Typical content-based systems use color information, whereas the present invention uses an image-location tagging method. A second aspect of the present invention is the method by which the set of images are sorted in relevancy. Tag data of the images allows for a new and fast method of searching through an entire set. A third aspect of the present invention is the method by which the sorted images are displayed to the user. Instead of the common method of just displaying the images in a rectangular array, where each image is the same size, the web-based application positions and sizes each image based on how relevant it is.Type: GrantFiled: September 14, 2006Date of Patent: December 17, 2013Inventors: Parham Aarabi, Ron Appel
-
Patent number: 8600120Abstract: Systems and methods are provided for control of a personal computing device based on user face detection and recognition techniques.Type: GrantFiled: March 6, 2008Date of Patent: December 3, 2013Assignee: Apple Inc.Inventors: Jeff Gonion, Duncan Robert Kerr
-
Patent number: 8577094Abstract: A method of identifying images as matching comprises comparing two image templates using a master mask to select corresponding codes from the templates. The master mask excludes blocks from the matching process and/or weights blocks according to their known or expected reliability.Type: GrantFiled: April 9, 2010Date of Patent: November 5, 2013Inventor: Donald Martin Monro
-
Patent number: 8571356Abstract: The present invention relates to generation of an appropriate high-resolution image with respect to a plurality of input images. An image processing apparatus including a unit for acquiring a relative movement amount for each first image between a reference image selected from a plurality of first images and the first images; a unit for generating a fourth image having a first resolution for each first image in accordance with a third image having a second resolution, the relative movement amounts, and image capture characteristics of an image capture device; a unit for acquiring, for each fourth image, an evaluation value indicating a difference between the fourth image and the first image corresponding to the fourth image; and a unit for generating a second image having the second resolution by updating the third image using an update value that is determined using the fourth images in accordance with the evaluation values.Type: GrantFiled: August 20, 2010Date of Patent: October 29, 2013Assignee: Canon Kabushiki KaishaInventor: Yuichi Nakada
-
Patent number: 8559731Abstract: Personalized tag ranking of images, including identifying within a reference image collection any images that are similar to an input image, identifying within a source image collection any images that have associated tags that are similar to a set of input tags associated with the input image, identifying among the images identified in the reference image collection any images that are similar to the images identified in the source image collection, and calculating a weight for each of a plurality of tag pairs, where each of the tags in each of the tag pairs is associated with a different subset of the images in the reference image collection identified as being similar to the images identified in the source image collection, and ranking the input tags of the input image in accordance with a predefined ranking function as applied to the tag pair weights.Type: GrantFiled: January 18, 2010Date of Patent: October 15, 2013Assignee: International Business Machines CorporationInventors: Yosi Mass, Michal Shmueli-Scheuer
-
Patent number: 8553968Abstract: A serial number detector is disclosed for detecting an encoded serial number written on a wafer. A scanner scans the wafer to generate a raster image representing the encoded serial number, and an optical character recognition (OCR) system detects a detected serial number comprising a plurality of detected data characters and a plurality of detected redundancy characters. A character-to-binary converter converts the detected data characters and the detected redundancy characters into codeword symbols. A syndrome generator generates a plurality of error syndromes in response to the codeword symbols, and an error corrector, responsive to the error syndromes, detects and corrects errors in the codeword symbols.Type: GrantFiled: February 18, 2005Date of Patent: October 8, 2013Assignee: Western Digital Technologies, Inc.Inventors: Patrick J. Lee, Robert E. Caddy, Jr., Mark D. Thomas
-
Patent number: 8548247Abstract: The present invention relates to an image processing apparatus and method, and a program that make it possible to more accurately specify a photographic subject in an image. A photographic subject map generating unit 21 generates, based on an input image, a photographic subject map indicating the likeliness of each region of the input image being a region of a photographic subject. A gradient map generating unit 22 generates a gradient map indicating the degree of change of the likeliness of the photographic subject map being a photographic subject. A threshold processing unit 23 and a threshold processing unit 24 binarize the gradient map using a high threshold THh and a low threshold TH1, and obtain threshold maps.Type: GrantFiled: May 6, 2010Date of Patent: October 1, 2013Assignee: Sony CorporationInventors: Kazuki Aisaka, Masaya Kinoshita, Takashi Kameya, Jun Murayama, Masatoshi Yokokawa
-
Patent number: 8548259Abstract: Techniques and methods are disclosed herein for combining and weighting of values from and associated with classifiers. Classifiers are used to recognize characters as part of an optical character recognition (OCR) system. Various methods of normalization facilitate combining of results of classifiers. For example, weight values may be entered into a weight table having two columns, one that includes weights from comparing patterns with images of correct characters, the other column includes weights from comparing patterns with images of incorrect characters.Type: GrantFiled: October 24, 2012Date of Patent: October 1, 2013Assignee: ABBYY Development LLCInventor: Diar Tuganbaev
-
Patent number: 8542950Abstract: Iconic images for a given object or object category may be identified in a set of candidate images by using a learned probabilistic composition model to divide each candidate image into a most probable rectangular object region and a background region, ranking the candidate images according to the maximal composition score of each image, removing non-discriminative images from the candidate images, clustering highest-ranked candidate images to form clusters, wherein each cluster includes images having similar object regions according to a feature match score, selecting a representative image from each cluster as an iconic image of the object category, and causing display of the iconic image. The composition model may be a Naïve Bayes model that computes composition scores based on appearance cues such as hue, saturation, focus, and texture. Iconic images depict an object or category as a relatively large object centered on a clean or uncluttered contrasting background.Type: GrantFiled: June 2, 2009Date of Patent: September 24, 2013Assignee: Yahoo! Inc.Inventors: Tamara L. Berg, Alexander Berg
-
Patent number: 8509542Abstract: A method and system for calculating oblong-shape rotation angles from binary images of arbitrary size using running sums is described without the need of eigenvector routines and storage of the image data. The oblong shape may be of arbitrary size and location and need not be precisely elliptical. A few running sums are calculated and stored throughout each scan, and the results are obtained in closed form by simple post-scan computation. An algorithmic embodiment can execute on one or more hardware processors with limited or otherwise constrained computation power, available instruction cycles, available memory, etc. Hardware processors may CPUs found in desktops, laptops, tablets, or handheld computing devices. The resulting arrangement may be used for touch or optical user interfaces, real-time image recognition, real-time machine vision, and other purposes.Type: GrantFiled: April 7, 2012Date of Patent: August 13, 2013Inventor: Lester F. Ludwig
-
Patent number: 8499046Abstract: Techniques for capturing images of business cards, uploading the images to a designated computing device for processing and recognition are disclosed. A mechanism is provided to update extracted data from the images when there are any changes. Depending on implementation, there are a number of ways to capture images of business cards (e.g., via a phone camera, a PC camera, or a scanning device). A transmission means is provided to transport the images to the designated computing device for centralized management of integrated contact information for individual users. As a result, a user may access his/her updatable integrated contact information database anywhere anytime from a chosen device.Type: GrantFiled: May 6, 2009Date of Patent: July 30, 2013Inventor: Joe Zheng
-
Publication number: 20130163886Abstract: An information processing apparatus and method for processing an input image by comparing a stored background image with the input image to obtain a difference, collating a change in the difference and time of the change with conditions for the occurrence of a periodic event and information as to the time of occurrence of the periodic event, which are previously stored in a storage unit, to determine whether the change in state of the input image is the periodic or a non-periodic movement of an object, and selecting, according to a result of the determination, any one of operations according to the periodic or the non-periodic movement of an object.Type: ApplicationFiled: February 22, 2013Publication date: June 27, 2013Applicant: CANON KABUSHIKI KAISHAInventor: CANON KABUSHIKI KAISHA
-
Publication number: 20130114862Abstract: An image processing unit includes a memory unit in which continuously captured images including a reference image and a comparative image are stored, an image dividing unit to divide the reference image and the comparative image into image blocks of a predetermined size, a mean value calculator unit to calculate a mean value of pixel outputs in each image block of each of the reference and comparative images, a threshold determining unit to determine a threshold according to a mean value of pixel outputs of an image block of the reference image, and a determiner unit to compare the threshold with a difference value of the mean values of the pixel outputs in the image blocks of the reference and comparative images to be synthesized and determine whether the image blocks of the reference and comparative images are suitable for image synthesis based on a result of the comparison.Type: ApplicationFiled: June 6, 2011Publication date: May 9, 2013Inventor: Daisuke Hohjoh
-
Patent number: 8391560Abstract: The present invention provides a method and a system for image identification and identification result output, which determines a location coordinate with respect to an image and a rotating angle based on at least one direction of the image according to features of the image. The image is compared to a plurality of sample images stored in a database according to the rotating angle so as to obtain at least one identification result. By means of the method and the system of the present invention, identification can be achieved with respect to various rotating angles and distances so as to improve the identification rate.Type: GrantFiled: July 30, 2009Date of Patent: March 5, 2013Assignee: Industrial Technology Research InstituteInventors: Ya-Hui Tsai, Yu-Ting Lin, Kuo-Tang Huang, Chun-Lung Chang, Tung-Chuan Wu
-
Patent number: 8391559Abstract: The present invention provides a method and system for image identification and identification result output, wherein a feature image under identification acquired from an image is compared with a plurality of sample images respectively stored in a database so as to obtain a plurality of similarity indexes associated with the plurality of sample images respectively. Each similarity index represents similarity between the feature image and the corresponding sample image. Thereafter, the plurality of similarity indexes are sorted and then a least one of comparison results is output. The present invention is further capable of being used for identifying identification marks with respect to a carrier. By sorting the similarity index with respect to each feature forming the identification marks, it is capable of outputting many sets of combinations corresponding to the identification marks so as to improve speed for targeting suspected carrier and enhance the identification efficiency.Type: GrantFiled: July 30, 2009Date of Patent: March 5, 2013Assignee: Industrial Technology Research InstituteInventors: Ya-Hui Tsai, Kuo-Tang Huang, Yu-Ting Lin, Chun-Lung Chang, Tung-Chuan Wu
-
Patent number: 8379941Abstract: One embodiment of the present invention envisions providing requester with a computer program for a remote computer equipped with a digital photo camera. The computer program controls the camera and prevents alterations to an image taken with the camera. The unaltered image of a portrait photograph of the requester is transmitted from the remote computer to the verifier's server computer. The image of the portrait photograph of the requester may further be used to verify the requester by comparing the image to the photographs from other sources.Type: GrantFiled: February 1, 2011Date of Patent: February 19, 2013Assignee: Go Daddy Operating Company, LLCInventors: James M. Bladel, Yong Lee, Noah D. Plumb, Wayne Thayer
-
Patent number: 8363959Abstract: Method and apparatus for inferring irregularities in query data relative to referential data includes attempting to compose the query data, like a puzzle, from large chunks of the referential data, and inferring irregularities in the query data based on at least the size of the matching chunks. The larger the size of a matching chunk, the more likely it is that its corresponding region in the query data is valid and not irregular. Regions in the query data which cannot be composed from the referential data, or can only be composed using small fragmented pieces and not large chunks of the referential data, are considered irregular. The method and apparatus is applicable to all types of signals, including images, video data, medical data, one-dimensional signals and multi-dimensional signals, and can be used to identify, inter alia, suspicious behaviors, suspicious objects, irregular patterns and defects in goods.Type: GrantFiled: March 21, 2006Date of Patent: January 29, 2013Assignee: Yeda Research & Development Co. Ltd.Inventors: Oren Boiman, Michal Irani
-
Patent number: 8358871Abstract: A skewed image data detecting and correcting device includes a skew angle detecting module, and an image rotating correction module. A skewed image data detecting and correcting method includes the following steps. Firstly, a binary digitizing operation is performed to obtain a binary image data. The binary image data is rotated by multiple different rotating angles, thereby obtaining multiple rotated binary image data. The pixel numbers of all horizontal rows of the rotated binary image data are totalized, thereby obtaining multiple horizontal pixel number distribution curves. A high-pass filtering procedure is performed to filter off low-frequency noise, thereby obtaining multiple high-frequency signal curves. The square sums of respective high-frequency signal curves are calculated, thereby obtaining multiple index values.Type: GrantFiled: May 28, 2009Date of Patent: January 22, 2013Assignee: AVerMedia Information, Inc.Inventors: Chien-Hui Tu, Cheng-Yueh Lo, De-Wei Huang, Yung-Hsi Wu
-
Patent number: 8355527Abstract: One embodiment of the present invention envisions providing requester with an application for a mobile device equipped with a built-in digital photo camera. The application controls the camera and prevents alterations to an image taken with the camera. The unaltered image of a photo ID is transmitted from the mobile device to the verifier's server computer. The image of the photo ID may further be used to verify the requester by comparing the image to the photographs from other sources.Type: GrantFiled: February 1, 2011Date of Patent: January 15, 2013Assignee: Go Daddy Operating Company, LLCInventors: James M. Bladel, Yong Lee, Noah D. Plumb, Wayne Thayer
-
Patent number: 8340368Abstract: The present invention relates to a face detection system for a vehicle. At least one first lighting unit is configured to radiate infrared light onto a left side of a driver's face. At least one second lighting unit is configured to radiate infrared light onto a right side of the driver's face. An image capturing unit separately captures the driver's face onto which the infrared light is radiated from the first and second lighting units. A control unit acquires left and right images of the face from the image capturing unit, and obtains a difference image between the acquired left and right images, thus determining whether the driver is inattentive in looking ahead. The system stably performs the face detection function with no or less effect by external optical environments as well as reduced computational load.Type: GrantFiled: December 29, 2008Date of Patent: December 25, 2012Assignees: Hyundai Motor Company, Kia Motors CorporationInventors: Byoung Joon Lee, Eui Yoon Chung
-
Patent number: 8331693Abstract: An information retrieval apparatus includes an obtaining unit configured to obtain dynamic ranges or re-quantization codes of a target object to be retrieved and dynamic ranges or re-quantization codes of each of comparison objects to be compared with the target object, the dynamic ranges or re-quantization codes of the target object and the dynamic ranges or re-quantization codes of the comparison objects being obtained as a result of adaptive dynamic range coding; a distance computation unit configured to compute distances between the target object and the comparison objects using the obtained dynamic ranges or re-quantization codes of the target object and the obtained dynamic ranges or re-quantization codes of the comparison objects; and a comparison unit configured to compare the distances between the target object and the comparison objects to select one of the comparison objects having a minimum distance.Type: GrantFiled: September 17, 2008Date of Patent: December 11, 2012Assignee: Sony CorporationInventors: Seiichi Inomata, Hideo Nakaya, Takashi Horishi, Tsugihiko Haga, Ryosuke Araki, Takuro Kawai, Toshiyuki Hino, Tetsujiro Kondo
-
Patent number: 8331696Abstract: To provide an update region detection device capable of accurately detecting an update region from plot data on a computer screen. In an update region detection unit (125), a pixel comparison unit (601) compares a difference between values of pixels at the same position in each of a reference frame and a current frame, with a first threshold and a second threshold, the second threshold being a value greater than the first threshold. An update region extraction unit (602) extracts, an update region, a group including a pixel where a difference greater than the second threshold has been detected, from among a group of pixels where a difference greater than the first threshold has been detected.Type: GrantFiled: February 13, 2009Date of Patent: December 11, 2012Assignee: NEC CorporationInventor: Jun Takada
-
Patent number: 8326082Abstract: An image processing apparatus includes: a subject region detection unit detecting regions of subjects included in an input image; a cropped region setting unit setting a region including all of the regions of the detected subjects as a cropped region; an expansion region addition unit adding an expansion region to expand an end of the cropped region only by a predetermined width; a cutting unit cutting a cut image formed from a cut region including the cropped region and the expansion region from the input image; a subject adaptation size change unit changing a size of an image formed from the cut region by deleting a region where an influence on the subjects is small in the cut image; and an entire image size changing unit changing the size of the entire image changed in size by the subject adaptation size change unit at a predetermined ratio.Type: GrantFiled: February 7, 2011Date of Patent: December 4, 2012Assignee: Sony CorporationInventors: Nodoka Tokunaga, Kazuki Aisaka, Masatoshi Yokokawa, Jun Murayama
-
Patent number: 8311337Abstract: Systems and methods for incorporating restricted access to feature vectors are described. A method is described for storing and accessing feature vectors relating to individuals in digital images. One or more individuals are identified within photos, and feature vectors are generated for individuals in one or more photos. User profiles are downloaded from a database over a network. The feature vectors and downloaded user profiles are grouped. The face tagging system collects tags for the generated grouped feature vectors for generating enhanced user profiles for the individuals, and the enhanced user profiles are stored in a storage resource.Type: GrantFiled: June 15, 2010Date of Patent: November 13, 2012Assignee: Cyberlink Corp.Inventor: Hung-Te Chou
-
Patent number: 8285052Abstract: Described is a system for ordering images. The system receives a plurality of images. Image features are extracted from each image. A set of all possible image pairs are generated for all images. A similarity metric with weights is generated between the images in each image pair in the set, with a net similarity metric thereafter generated by combining the similarity metrics. The images are then ordered according to the net similarity metrics to generate a computer-ordered set of images. The computer-ordered set of images is then displayed to the user, which allows the user to re-order the images to generate a user-ordered set of images. The weights are then optimized to minimize the distance between the computer-ordered set of images and the user-ordered set of images. The similarity metrics are then re-weighted, with the images thereafter being re-ordered according to the new metrics.Type: GrantFiled: December 15, 2009Date of Patent: October 9, 2012Assignee: HRL Laboratories, LLCInventors: Rajan Bhattacharyya, Deepak Khosla, David J. Huber, Penn Tasinga
-
Patent number: 8279494Abstract: There is provided an image printer having a display unit, in which a predetermined image can be set as a background picture of the display unit. The image printer includes an image processing unit processing an image selected by a user in accordance with a predetermined image processing technique so as to set the selected image as a background picture of the display unit; and a setting unit setting the processed image as the background picture of the display unit, wherein the display unit displays the processed image.Type: GrantFiled: November 21, 2005Date of Patent: October 2, 2012Assignee: Samsung Electronics Co., Ltd.Inventor: Sang-hyun Park
-
Patent number: 8265398Abstract: There is provided an image analysis system which captures image data of an arbitrary pair of a first image RI and a second image LI among images obtained by color-photographing a single object from different positions into an analysis computer, wherein the computer includes corresponding point extraction means for assigning a weighing factor to a pixel information value based on the contrast size of the pixel information value in each of a first local area ROI1 set around an arbitrary reference point in RI and second local areas ROI2s at which scanning is performed on LI, calculating the similarity between ROI1 and ROI2s, and extracting a corresponding point which corresponds to the reference point from a ROI2 having the highest similarity, and depth information calculating means for calculating depth information of the object based on coordinates of the reference point and the corresponding point.Type: GrantFiled: March 10, 2008Date of Patent: September 11, 2012Assignee: Kowa Company, Ltd.Inventors: Hiroshi Fujita, Toshiaki Nakagawa, Yoshinori Hayashi
-
Patent number: 8254698Abstract: The present invention discloses methods for document-to-template matching for data-leak prevention (DLP), the methods including the steps of: providing a document as a stream of characters; splitting the stream into a plurality of serialized data lines; calculating a hash value for each serialized data line; checking for each hash value in a hash map of a template set; determining a similarity match to a particular template based on a predefined threshold of template hash values, of the template set, being found in the stream; and based on the similarity match, executing a DLP security policy for the document. Preferably, the template set is extracted from documents manually prepared by a security administrator. Preferably, each template in the template set is deduced automatically from a plurality of documents.Type: GrantFiled: April 2, 2009Date of Patent: August 28, 2012Assignee: Check Point Software Technologies LtdInventors: Alon Kantor, Liran Antebi, Yoav Kirsch, Uri Bialik
-
Patent number: 8243997Abstract: A method, system, and medium are provided for detecting change in a geographic area. One embodiment includes receiving a set of remotely sensed imagery that depicts the geographic area, automatically identifying changes in physical features of the geographic area by comparing, without user intervention, the set of remotely sensed imagery to a dataset of previously stored remotely sensed imagery that also depicts the geographic area, and deriving a change-quality measurement associated with the set of remotely sensed imagery, wherein the change-quality measurement quantifies a suitability of comparison of the set of remotely sensed imagery to the previously stored remotely sensed imagery.Type: GrantFiled: October 20, 2008Date of Patent: August 14, 2012Assignee: The Curators of the University of MissouriInventors: Curtis Herbert Davis, Brian Christopher Claywell, James Michael Keller, Matthew Nicholas Klaric, Grant Jason Scott, Chi-Ren Shyu
-
Patent number: 8229230Abstract: A method which uses digital image comparison for imaging software development is described. The software under development is used to generate a set of test digital images from print data. The images are stored. The software of a reference system is used to generate a set of reference digital images based on the same print data. The test and reference images are tiled, and image comparison is carried out on a tile-by-tile basis. A difference tile is generated for each test image tile and corresponding reference image tile, and the tiles are stored together in an image file to be displayed to the human user. The test images and reference images are compared using an image comparison program. The result of the comparison is presented to the human software developer for further comparison and evaluation.Type: GrantFiled: July 30, 2008Date of Patent: July 24, 2012Assignee: Konica Minolta Laboratory U.S.A., Inc.Inventor: Kenneth David Hayber
-
Patent number: 8199971Abstract: In a system for detecting a target object, a similarity determining unit sets a block in a picked-up image, and compares a part of the picked-up image contained in the block with a pattern image data while changes a location of the block in the picked-up image to determine a similarity of each part of the picked-up image contained in a corresponding one of the different-located blocks with respect to the pattern image data. A specifying unit extracts some different-located blocks from all of the different-located blocks. The determined similarity of the part of the picked-up image contained in each of some different-located blocks is equal to or greater than a predetermined threshold similarity. The specifying unit specifies, in the picked-up image, a target area based on a frequency distribution of some different-located blocks therein.Type: GrantFiled: January 21, 2009Date of Patent: June 12, 2012Assignee: Denso CorporationInventors: Akihiro Watanabe, Noriaki Shirai, Satoshi Osanai
-
Patent number: 8200021Abstract: An image signature to be used for matching is generated by the following generation method. First, region features are extracted from respective sub-regions of a plurality of pairs of sub-regions in an image, and for each of the pairs of sub-regions, a difference value between the region features of two sub-regions forming a pair is quantized. Then, a collection of elements which are quantization values calculated for the respective pairs of sub-regions is used as an image signature to be used for discriminating the image. The image signature matching device specifies, from an image signature of a first image and an image signature of a second image generated by the above generating method, a margin region of each of the images. The image signature matching device matches the image signature of the first image and the image signature of the second image in such a manner that a weight of an element, in which at least one of two sub-regions forming a pair is included in the specified margin region, is reduced.Type: GrantFiled: June 2, 2010Date of Patent: June 12, 2012Assignee: NEC CorporationInventors: Kota Iwamoto, Ryoma Oami
-
Patent number: 8194958Abstract: An image display device that includes: a region-of-interest setting section that sets regions-of-interest respectively for multiple medical images representing a photographed subject; a difference image creating section that creates a difference image representing a difference between images of the regions-of-interest set by the region-of-interest setting section; and an image displaying section that displays the difference image as well as the images arranged side by side.Type: GrantFiled: May 1, 2007Date of Patent: June 5, 2012Assignee: FUJIFILM CorporationInventor: Yoshiyuki Moriya
-
Publication number: 20120128242Abstract: A system and method that processes video to extract a keyframe-based adequate visual representation is disclosed. Certain embodiments utilize a hierarchical processing technique. A first stage in the hierarchy extracts a chromatic difference metric from a pair of video frames. An initial set of frames is chosen based on the chromatic metric and a threshold. A structural difference measurement is extracted from this initial set of frames. A second threshold is used to select key frames from the initial set. The first and second thresholds can be user selectable. The output of this process is the visual representation. The method is extensible to any number of metrics and any number of levels.Type: ApplicationFiled: January 30, 2012Publication date: May 24, 2012Applicant: Virage, Inc.Inventors: Arun Hampapur, Mojgan Monika Gorkani, Chiao-Fe Shu, Amarnath Gupta
-
Patent number: 8170346Abstract: A method for performing a high-performance closed-form single-scan calculation of oblong-shape rotation angles from binary images of arbitrary size on a processor using running sums is disclosed. Running sums are calculated and stored throughout each scan, and the results are obtained in closed form by simple post-scan computation. An algorithmic embodiment may execute on one or more hardware processors with limited or constrained computation power, available instruction cycles, available memory, etc. Exemplary hardware processors are found in one or more CPUs of a desktop, laptop, tablet, or handheld computing device, and may be an embedded processor or a signal processor chip. The resulting method may be used for touch or optical user interfaces, real-time image recognition, real-time machine vision, and other purposes.Type: GrantFiled: March 15, 2010Date of Patent: May 1, 2012Inventor: Lester F. Ludwig
-
Patent number: 8160370Abstract: An image processing apparatus includes: an image pyramid forming section configured to form an image pyramid by hierarchically creating layered image data including differently scaled images from inputted image data; a position calculating section configured to determine an in-image-pyramid position as a height position in the image pyramid to which template image data having an image portion of a target object at a fixed scale corresponds; an upper-layer-side likelihood calculating section configured to determine a likelihood for a target object by matching between upper-side layer image data directly above the in-image-pyramid position, and a state prediction; a lower-layer-side likelihood calculating section configured to determine a likelihood for a target object by matching between lower-side layer image data directly below the in-image-pyramid position, and a state prediction; and a true likelihood calculating section configured to determine a true likelihood from the likelihoods determined by the upperType: GrantFiled: November 6, 2009Date of Patent: April 17, 2012Assignee: Sony CorporationInventors: Yuyu Liu, Keisuke Yamaoka, Takayuki Yoshigahara, Xi Chen