Comparator Patents (Class 382/218)
-
Publication number: 20130334807Abstract: The present invention relates to the field of anti-counterfeit products. In particular, the invention is related to a method to produce anti-counterfeiting tags having unique nanofibre patterns. This unique nanofibres pattern is grown randomly at the edge of or underneath a masking means.Type: ApplicationFiled: February 29, 2012Publication date: December 19, 2013Applicant: NANORIG A/SInventors: Horst-Günter Rubahn, Stefan Johansen, Michal Radziwon
-
Publication number: 20130336590Abstract: An embodiment includes a method and an apparatus for the generation of a visual story board in real time in an image-capturing device including a photo sensor and a buffer, wherein the method includes the consecutively performed steps: starting the recording of a video, receiving information on an image frame of the video, comparing the information on the received image frame with information on at least one of a plurality of image frames wherein the information on the plurality of image frames has previously been stored in the buffer, storing the information on the received image frame in the buffer depending on the result of the comparison, and finishing the recording of the video.Type: ApplicationFiled: May 2, 2013Publication date: December 19, 2013Applicant: STMicroelectronics S.r.l.Inventors: Alexandro SENTINELLI, Luca CELETTO, Arcangelo Ranieri BRUNA, Giuseppe SPAMPINATO, Claudio Domenico MARCHISIO
-
Publication number: 20130336583Abstract: Apparatus for determining model parameters, the apparatus comprising an object model transformer, a region comparator, and a model parameter determiner. The object model transformer is configured to receive an object model of a known object and to transform the object model based on a set of model parameters from a first frame of reference to a second frame of reference, and is further configured to determine as result of this transformation a transformed object model comprising at least one region that is associated to an object region of the object. The region comparator is configured to receive the transformed object model and an image depicting the object, to determine for a selected region of the transformed object model a region-related similarity measure. The model parameter determiner is configured to determine an updated set of model parameters on the basis of the region-related similarity measure and an optimization scheme.Type: ApplicationFiled: August 20, 2013Publication date: December 19, 2013Applicant: Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V.Inventors: Andreas ERNST, Tobias RUF, Felix LAUTENSCHLAGER, Anton PAPST, Joern THIELECKE, Christian KUEBLBECK
-
Publication number: 20130339848Abstract: Systems and methods for image deduplication in a file are provided. A method includes identifying a plurality of similar images (e.g., similar intent images) in an electronic document. The method also includes designating one of the plurality of similar images as a master copy. The method also includes replacing each remaining one of the plurality of similar images, other than the master copy, with one of (i) a duplicate copy of the master copy and (ii) a soft link pointing to the master copy.Type: ApplicationFiled: June 14, 2012Publication date: December 19, 2013Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Sandeep R. PATIL, Sri RAMANATHAN, Riyazahamad M. SHIRAGUPPI, Prashant SODHIYA, Matthew B. TREVATHAN
-
Patent number: 8610963Abstract: An image processing system, apparatus and method are disclosed for corner enhancing a digital image for rendering on an image output device. According to one exemplary method, pixels associated with corner regions of the digital image are determined using a plurality of vector windows. Subsequently, one or more corner pixels are modified to sharpen the rendering of the digital image on the image output device.Type: GrantFiled: March 9, 2010Date of Patent: December 17, 2013Assignee: Xerox CorporationInventors: Robert P. Loce, Edgar A. Bernal
-
Patent number: 8611674Abstract: A computer-implemented method for invariant-based normal estimation. The method includes calculating a set of measured invariants for a point associated with a surface of an object, where the set of measured invariants is based on pixel information that includes lighting information, calculating one or more sets of estimated invariants for the point associated with the surface of the object, where each set of estimated invariants is based on a known lighting environment for the object and a different normal for the point associated with the surface of the object, and determining a first normal for the point associated with the surface of the object that results in the set of measured invariants corresponding to a first set of estimated invariants.Type: GrantFiled: January 18, 2010Date of Patent: December 17, 2013Assignee: Disney Enterprises, Inc.Inventors: Thabo Dominik Beeler, Bernd Bickel, Markus Gross, Robert Sumner
-
Patent number: 8611587Abstract: A device, system and method for determining a compliance with an instruction to assemble a figure according to a depiction of the figure on an output device, by presenting image data of the figure, capturing an image of the assembled figure, and comparing the figure captured in the image to the figure depicted on the output device.Type: GrantFiled: February 28, 2011Date of Patent: December 17, 2013Assignee: Eyecue Vision Technologies Ltd.Inventor: Ronen Horovitz
-
Patent number: 8611621Abstract: A system and method for comparing captured sequences of in-vivo images with (e.g., template or model) sequences, for example, for computer-automated recognition of contractions. The size of the opening of an in-vivo lumen passageway represented in each frame in a subset of frames of an image stream captured in vivo may be measured. Frames in the subset of frames of the image stream having a local minimum size of the lumen passageway may be identified. The subset of frames may be divided into segments of sequential frames at frames having local maximum lumen sizes before and after the identified frame having a local minimum size of the lumen passageway to generate contraction sequences. A plurality of the contraction sequences may be compared to template sequences. A plurality of the contraction sequences may be displayed.Type: GrantFiled: September 8, 2011Date of Patent: December 17, 2013Assignee: Given Imaging Ltd.Inventors: Michal Drozdzal, Petia Radeva, Santiago Segui Mesquida, Laura Igual-Munoz, Carolina Malagelada, Fernando Azpiroz, Jordi Vitria
-
Patent number: 8611618Abstract: An apparatus for generating a representative fingerprint template is provided. The apparatus includes a calculation unit configured to calculate levels of similarity between N fingerprint templates; and a selection unit configured to select at least one fingerprint template from among the N fingerprint templates as a representative fingerprint template.Type: GrantFiled: August 3, 2011Date of Patent: December 17, 2013Assignee: Suprema Inc.Inventors: Dongjin Kwon, Bo Gun Park, Bong Seop Song, Jae Won Lee
-
Publication number: 20130328760Abstract: An apparatus and method for a mobile device to reduce computer vision (CV) processing, for example, when detecting features and key points, is disclosed. Embodiments herein reduce the search area of an image or the volume of image data that is searched to detect features and key points. Embodiments limit a search area of a full image to an actual area of interest to the user. This reduction decreases the search area, decreases search time, decreases power consumption, and limits detection to the area of interest to the user.Type: ApplicationFiled: June 8, 2012Publication date: December 12, 2013Applicant: QUALCOMM IncorporatedInventor: William Keith HONEA
-
Publication number: 20130329070Abstract: Systems, methods, and computer readable media to register images in real-time and that are capable of producing reliable registrations even when the number of high frequency image features is small. The disclosed techniques may also provide a quantitative measure of a registration's quality. The latter may be used to inform the user and/or to automatically determine when visual registration techniques may be less accurate than motion sensor-based approaches. When such a case is detected, an image capture device may be automatically switched from visual-based to sensor-based registration. Disclosed techniques quickly determine indicators of an image's overall composition (row and column projections) which may be used to determine the translation of a first image, relative to a second image. The translation so determined may be used to align/register the two images.Type: ApplicationFiled: June 6, 2012Publication date: December 12, 2013Applicant: Apple Inc.Inventors: Marco Zuliani, Kevin L. Hunter, Jianping Zhou, Todd Sachs, Frank Doepke
-
Patent number: 8605952Abstract: The present system and method provides a more precise way to record food and beverage intake than traditional methods. The present disclosure provides custom software for use in mobile computing devices that include a digital camera. Photos captured by mobile digital devices are analyzed with image processing and comparisons to certain databases to allow a user to discretely record foods eaten. Specifically, the user captures images of the meal or snack before and after eating. The foods pictured are identified. Image processing software may identify the food or provide choices for the user. Once a food is identified and volume of the food is estimated, nutrient databases are used for calculating final portion sizes and nutrient totals.Type: GrantFiled: December 27, 2012Date of Patent: December 10, 2013Assignee: Purdue Research Foundation, Inc.Inventors: Carol Boushey, Edward John Delp, David Scott Ebert, Kyle DelMar Lutes, Deborah Kerr
-
Patent number: 8606019Abstract: A 2-dimensional pattern matching method contains a process of extracting a query feature data by projecting a vector representation of either of a query 2-dimensional pattern and a transformed query 2-dimensional pattern which is generated by transforming the query 2-dimensional pattern, to a feature space. An enrollment feature data as previously enrolled and a query feature data are inversely projected to the 2-dimensional pattern representation space which has the dimension of the vector representation and the similarity is calculated. The data size of a feature amount is small and a matching technique robust to the positional displacement and the image distortion is provided.Type: GrantFiled: April 21, 2008Date of Patent: December 10, 2013Assignee: NEC CorporationInventor: Toshio Kamei
-
Patent number: 8606020Abstract: According to one embodiment, a search skip region setting function generation method includes estimating. The estimating includes estimating a relative position between a object and a template based on a distribution of surrounding search point similarities, and generates a function required to set a search skip region which allows to skip the object search on each model reduced-scale image based on the estimated relative position.Type: GrantFiled: February 16, 2012Date of Patent: December 10, 2013Assignee: Kabushiki Kaisha ToshibaInventors: Miki Yamada, Yoshihiro Ohmori, Kaoru Matsuoka
-
Patent number: 8605989Abstract: Information of different scans of physical objects may require comparison, for example to determine if the scans are of the same object or if an object has changed, or better information for a three dimensional model may be desired. Different scans of physical objects may be compared by determining lines or planes tangent to a surface at a discrete number of points, registering three dimensional information provided by the scans using the tangent lines or planes, and determining a measure of discrepancy between the surfaces. Three dimensional information of different scans of the same object may also be merged after determining lines or planes tangent to a surface at a discrete number of points and performing registration and merging.Type: GrantFiled: February 13, 2009Date of Patent: December 10, 2013Assignee: Cognitech, Inc.Inventors: Leonid I. Rudin, Jose L. Lisani, Jean-Michel Morel
-
Publication number: 20130322762Abstract: A system and method of processing an image is disclosed. A particular method of determining whether a particular pixel of an image is a feature includes receiving data corresponding to a plurality of pixels (from the image) surrounding the particular pixel. The method further includes determining a set of comparison results, each corresponding to one of the plurality of pixels and indicating a result of comparing an attribute value corresponding to one of the plurality of pixels to a comparison value (based on a particular attribute value of the particular pixel and a threshold value). The method further includes performing a processor-executable instruction that, when executed by a processor, causes the processor to identify a subset of the set of comparison results that indicate the particular pixel is the feature. The identified subset may be a consecutive order of pixels of the plurality of pixels.Type: ApplicationFiled: September 4, 2012Publication date: December 5, 2013Applicant: QUALCOMM INCORPORATEDInventors: Mao Zeng, Erich James Plondke, Lucian Codrescu
-
Patent number: 8600172Abstract: An analytical device is disclosed that analyzes whether a first image is similar to (or the same as) as a second image. The analytical device analyzes the first image by combining at least a part (or all) of the first image with at least a part (or all) of the second image, and by analyzing at least a part (or all) of the combined image. Part or all of the combination may be analyzed with respect to the abstraction of the first image and/or the abstraction of the second image. The abstraction may be based on a Bag of Features (BoF) description, based on a histogram of intensity values, or based on other types of abstraction methodologies. The analysis may involve comparing one or more aspects of the combination (such as the entropy or randomness of the combination) with the one or more aspects of the abstracted first image and/or abstracted second image. Based on the comparison, the analytical device may determine whether the first image is similar to or the same as the second image.Type: GrantFiled: March 16, 2011Date of Patent: December 3, 2013Assignee: Sensormatic Electronics, LLCInventors: Kuntal Sengupta, Ian Westmacott, Serdar Ince
-
Patent number: 8600101Abstract: A portrait illustration creation system includes a basic face photo data storage unit for storing a plurality of pieces of face photo data of basic faces, a basic portrait illustration data storage unit for storing a plurality of basic portrait illustrations, and an associating information storage unit for storing information which associates the basic face photo data with the basic portrait illustration data. The system also includes an approximate basic face photo extraction unit for recognizing, from face-photo-data-to-be-illustrated which is a photo of a face-to-be-illustrated of which a portrait illustration is desired to be created, the face-to-be-illustrated; performing matching between the face-to-be-illustrated and the basic faces represented by the plurality of pieces of basic face photo data stored on the basic face photo data storage unit; and extracting the basic face photo data having a high approximation degree.Type: GrantFiled: February 4, 2010Date of Patent: December 3, 2013Inventor: Kazuo Sairyo
-
Patent number: 8600150Abstract: A wafer aligning apparatus includes a laser sensor that generates a trigger signal, a CCD camera imaging a wafer in response to the trigger signal, a signal processing unit that calculates a center alignment correction value for the wafer, and a robot controller that receives the center alignment correction value to control movement of a transfer robot. The laser sensor generates the trigger signal in accordance with a change in reflected light detected by the laser sensor, the change in the amount of reflected light being detected by the laser sensor when a boundary between a blade of the transfer robot and a coupler of the transfer robot passes under the laser sensor.Type: GrantFiled: October 8, 2010Date of Patent: December 3, 2013Assignee: Samsung Electronics Co., Ltd.Inventors: Heok-Jae Lee, Sang-Ho Kim, Hyu-Rim Park, Do-In Bae, Kee-Weone Seo, Chang-Woo Woo
-
Patent number: 8594398Abstract: A method for recognizing heart diseases in a cardiac echo video of a heart with an unknown disease using a spatio-temporal disease model derived from a training echo video, comprising the steps of: generating a plurality of training models for heart diseases, wherein the cardiac echo videos are each derived from a known viewpoint and the disease of the heart is known; analyzing the video of the heart with the unknown disease by fitting a model of shape and motion for each frame and combining the results across the frames; and, reporting the disease using a classification method for choosing among the diseases of interest.Type: GrantFiled: June 26, 2009Date of Patent: November 26, 2013Assignee: International Business Machines CorporationInventors: David James Beymer, Fei Wang, Tanveer Fathima Mahmood
-
Patent number: 8594437Abstract: It is an object of this invention to detect a similar picture at high speed with high accuracy from a large-scale picture archive. Previously, a frame is extracted from each picture in a picture archive at fixed time intervals, an image feature quantity is extracted from each extracted frame, and the extracted image feature quantities are clustered, thereby constructing a clustered feature quantity database. A frames search section performs a similar frame search not only for a leading frame of a query picture but also for a subsequent frame, by using the database. A search result integration section checks whether there is a sequence across a plurality of search results and outputs, as a picture similar to the query picture, a segment which is confirmed to be continuous for a certain length or more.Type: GrantFiled: March 1, 2011Date of Patent: November 26, 2013Assignee: Hitachi, Ltd.Inventors: Yuki Watanabe, Tsuneya Kurihara, Naoto Akira
-
Patent number: 8588481Abstract: A facial recognition method for eliminating the effect of noise blur and environmental variations is provided, applicable to a data processing apparatus, to determine whether a current-face-image matches a reference-face-image or not. According to the method, Gaussian Noise blur Reduction or another noise blur reduction method is performed on the current-face-image and the reference-face-image. Furthermore, the current-face-image and the reference-face-image are respectively divided into a plurality of blocks, so as to derive feature-vector sets representing the current-face-image and the reference-face-image. Finally a dynamic threshold value is determined according to environmental variations to be compared with the difference of the feature-vector sets, so as to determine whether a current-face-image matches a reference-face-image.Type: GrantFiled: January 11, 2011Date of Patent: November 19, 2013Assignee: MSI Computer (Shenzhen) Co., LtdInventor: Wei Ting Lee
-
Patent number: 8588528Abstract: Disclosed are techniques and systems to provide a scanned image in which a portion of the image is overlaid with OCR generated text corresponding to the text of the original scanned document.Type: GrantFiled: June 22, 2010Date of Patent: November 19, 2013Assignee: K-NFB Reading Technology, Inc.Inventors: Peter Chapman, Paul Albrecht
-
Publication number: 20130301934Abstract: A method of making an image-based product includes providing an image collection having a plurality of digital images, each digital image having an image type; providing one or more image-type distributions, each image-type distribution corresponding to a theme and including a distribution of image types related to the theme; using a processor to automatically compare the image types of the digital images in the image collection to the image types in the image-type distribution; using the processor to automatically determine a match between the image types in the image collection and the image types in the image-type distribution; and selecting a group of digital images from the image collection having a distribution of image types specified by the determined matching image-type distribution. The method further includes assembling the digital images in the selected group of images into an image-based product and causing the construction of the image-based product.Type: ApplicationFiled: May 11, 2012Publication date: November 14, 2013Inventor: Ronald Steven Cok
-
Publication number: 20130301936Abstract: A technique for use in automatic validation of a media item involves accessing a template that comprises multiple one-class classifiers, each corresponding to one of multiple classes to which the media item might belong, and then applying each of the one-class classifiers to an image of the media item to generate a result set for each of the multiple classes. The result set for each media class is then analyzed to assess whether the media item belongs to that class.Type: ApplicationFiled: July 19, 2013Publication date: November 14, 2013Applicant: NCR CORPORATIONInventors: Chao He, Gary Ross
-
Publication number: 20130301935Abstract: A user may submit an image and request from a server one or more images that are similar to the submitted image. The server may generate an image signature based on the content of the submitted image. The server may conduct a Hash operation to the image signature to generate one or more Hash values. These Hash values may be used to identify one or more candidate images similar to the image in a Hash table. These candidate images may be sorted and outputted to the user based on similarity. The similarity between each of the candidate images and the image may be determined using at least one of Hamming distance or Euclidean distance.Type: ApplicationFiled: January 18, 2012Publication date: November 14, 2013Applicant: Alibaba Group Holding LimitedInventor: Hui Xue
-
Publication number: 20130301937Abstract: A method, a data network arrangement and a computer program product by which a comparator can be implemented in a data network. The user of the comparator stores his evaluation of the properties included in the targets to be evaluated in a database in the server in the data network using a graphic one- or two-dimensional evaluation frame. In the comparator the comparator user's evaluations are compared to property evaluations given by a reference user. When calculating the total accuracy percentage of the comparison the evaluations given by the comparator user are weighted with a weighting coefficient, which is obtained by normalising first the importance evaluations of all the properties given by the reference user and by using the normalised importance evaluation of a certain property as the weighting coefficient for this property.Type: ApplicationFiled: November 30, 2011Publication date: November 14, 2013Applicant: ZEF Solutions OyInventors: Markku Alasaarela, Jaakko Alasaarela, Esko Alasaarela
-
Patent number: 8582892Abstract: Provided are a method and an apparatus for processing digital images, and more particularly, a method and an apparatus for face determination, wherein it is determined if a subject is a true subject based on distance information regarding a distance to the subject and face detection information. In an embodiment, the face detecting apparatus is a digital image processing apparatus and includes a digital signal processor for determining if a subject is a true subject based on distance information regarding a distance to the subject and face length information.Type: GrantFiled: September 13, 2010Date of Patent: November 12, 2013Assignee: Samsung Electronics Co., Ltd.Inventors: Isaac Lee, Seung-yun Lee, Byoung-kwon Lee
-
Patent number: 8582818Abstract: A method of automatically detecting objects in front of a motor vehicle comprises the steps of pre-storing template objects representing possible objects in front of the motor vehicle, detecting images from a region in front of the vehicle by a vehicle mounted imaging means, generating a processed image containing disparity or vehicle-to-scene distance information from the detected images, comparing the pre-stored template objects with corresponding regions-of-interest of the processed image, and generating a match result relating to the match between the processed image and the template objects. Each of the pre-stored template objects is a flat two-dimensional multi-pixel area of predetermined shape.Type: GrantFiled: February 4, 2010Date of Patent: November 12, 2013Assignee: Autoliv Development ABInventors: Per Jonas Hammarström, Ognjan Hedberg
-
Publication number: 20130294703Abstract: Method and system for determining a measure of quality for images by using multi-level decomposition are presented. Multi-level decomposition of images is performed in the wavelet domain producing subbands at each level of decomposition. Aggregation of subbands is performed across multiple levels to produce an accurate measure of image quality. By aggregating only selected subbands the computational complexity of the method is greatly reduced.Type: ApplicationFiled: July 9, 2013Publication date: November 7, 2013Inventors: Soroosh REZAZADEH, Stephane COULOMBE
-
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
-
Publication number: 20130286238Abstract: Determining a location. An initial image is captured at an image capturing device. The initial image is compared with images in a database of images which have associated locations to determine the location of the image capturing device. A user receives a notification if a location cannot be determined.Type: ApplicationFiled: April 30, 2012Publication date: October 31, 2013Inventors: Wai-Tian Tan, John Apostolopoulos
-
Publication number: 20130287306Abstract: Provided are techniques for assessing object relevance. One or more user usage patterns are retrieved. Object properties of one or more objects are retrieved. The one or more user usage patterns are compared against the object properties of the one or more objects to compute one or more interaction scores that represent a value of how an object interacts with a user based on a current context of the user. Object importance is assigned to each of the one or more objects based on the one or more interaction scores.Type: ApplicationFiled: May 4, 2012Publication date: October 31, 2013Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: James P. Galvin, JR., Andrew L. SCHIRMER
-
Publication number: 20130287305Abstract: Methods, systems, and apparatus for testing content rendering are described. A method includes receiving input specifying a change to a parameter relating to display of content in a webpage, in response to receiving the input, generating a test image of the webpage including the content, comparing a target image of the content with the generated test image to determine whether the generated test image includes the target image of the content, and selectively providing a failure notification based upon a result of the comparison.Type: ApplicationFiled: April 26, 2012Publication date: October 31, 2013Applicant: GOOGLE INC.Inventors: Sanjeev Dhanda, Yi Zhang
-
Publication number: 20130287307Abstract: Methods and apparatuses are disclosed. Previously stored images of one or more geographic areas may be viewed by online users. A new low-resolution image may be acquired and aspects of the new low-resolution image may be compared with a corresponding one of the previously stored images to determine an amount of change. A determination may be made regarding whether to acquire a new high-resolution image based on the determined amount of change and a freshness score associated with the one of the previously stored images. In another embodiment, a new image may be captured and corresponding location data may be obtained. A corresponding previously stored image may be obtained and compared with the new image to determine an amount of change. The new image may be uploaded to a remote computing device based on the determined amount of change and a freshness score of the previously stored image.Type: ApplicationFiled: June 28, 2013Publication date: October 31, 2013Inventors: Ido Omer, Eyal Ofek
-
Patent number: 8571350Abstract: A method of operation of an image processing system includes: identifying a feature point on a first image; determining a matching point on a second image with the matching point corresponding to the feature point; calculating an offset component between the feature point and the matching point with the offset component having a vertical offset; identifying a correction field for updating the first image and the second image, with the correction field having a vertical adjustment, a zoom adjustment, a rotational adjustment, and a keystone adjustment; and updating the first image and the second image using the correction field for minimizing the offset component for displaying an aligned image on a device.Type: GrantFiled: February 17, 2011Date of Patent: October 29, 2013Assignee: Sony CorporationInventors: Dennis Adams, Dale Emmons
-
Patent number: 8571328Abstract: Determining correspondence between image regions can include: selecting first and second regions of visual content including pixels in a computer system, the first region comprising a first patch to be mapped to the second region; selecting at least two heuristics for use in mapping the first patch to the second region, the heuristics selected from the group consisting of: (i) nearby-pixel mapping evaluation; (ii) random-perturbation mapping evaluation; (iii) evaluation of multiple mapping candidates identified in an iterative search process; and (iv) enrichment to increase a collection of mapping candidates; and identifying, using the selected heuristics, at least one patch in the second region for the first patch.Type: GrantFiled: August 16, 2010Date of Patent: October 29, 2013Assignee: Adobe Systems IncorporatedInventors: Elya Shechtman, Dan Goldman, Connelly Barnes, Adam Finkelstein
-
Patent number: 8571329Abstract: A method and system for automatically analyzing and searching a database of digital content items includes a process for analyzing digital content items to identify portions capable of receiving text. In one implementation user input is received, where the user input helps construct a set of ordered values representing digital content item features desired by the user. The constructed set of ordered values is compared to sets of ordered values corresponding to digital content items in the database of digital content items, and digital content items are retrieved with sets of ordered values corresponding to the constructed set of ordered values.Type: GrantFiled: March 22, 2012Date of Patent: October 29, 2013Assignee: Getty Images, Inc.Inventor: Kelly Thompson
-
Patent number: 8571315Abstract: An information processing apparatus includes: a distinguishing unit which, by using an ensemble classifier, which includes a plurality of weak classifiers outputting weak hypotheses which indicates whether a predetermined subject is shown in an image in response to inputs of a plurality of features extracted from the image, and a plurality of features extracted from an input image, sequentially integrates the weak hypotheses output by the weak classifiers in regard to the plurality of features and distinguishes whether the predetermined subject is shown in the input image based on the integrated value. The weak classifier classifies each of the plurality of features to one of three or more sub-divisions based on threshold values, calculates sum divisions of the sub-divisions of the plurality of features as whole divisions into which the plurality of features is classified, and outputs, as the weak hypothesis, a reliability degree of the whole divisions.Type: GrantFiled: November 3, 2011Date of Patent: October 29, 2013Assignee: Sony CorporationInventors: Kohtaro Sabe, Kenichi Hidai, Kiyoto Ichikawa
-
Patent number: 8565509Abstract: The operation rate of a circuit pattern inspecting apparatus is prevented from deteriorating by measuring image noise of the circuit pattern inspecting apparatus and detecting the sign that the apparatus is to be in an abnormal state. Provided is the circuit pattern inspecting apparatus wherein circuit pattern abnormalities are detected by irradiating a substrate having a circuit pattern formed thereon with an electron beam and detecting generated secondary electrons or reflected electrons. The circuit pattern inspecting apparatus is provided with: an image processing section wherein an image is generated based on the signal intensities of the detected secondary electrons or those of the reflected electrons and the image is displayed for a display apparatus of the interface; and a control section which analyzes the frequency of noise included in the image.Type: GrantFiled: October 19, 2009Date of Patent: October 22, 2013Assignee: Hitachi High-Technologies CorporationInventors: Hiroyuki Takahashi, Yasuhiro Gunji, Hirokazu Ito
-
Patent number: 8559722Abstract: An image recognition apparatus detects a specific object image from an image to be processed, calculates a coincidence degree between an object recognizability state of the object image and that of an object in registered image information, and calculates a similarity between the image feature of the object image and the image feature in the registered image information. Based on the similarity and coincidence degree, the image recognition apparatus recognizes whether the object of the object image is that of the registered image information. When the similarity is lower than the first threshold and the coincidence degree is equal to or higher than the second threshold, the image recognition apparatus recognizes that the object of the object image is different from that of the registered image information.Type: GrantFiled: February 3, 2011Date of Patent: October 15, 2013Assignee: Canon Kabushiki KaishaInventor: Ryosuke Tsuji
-
Patent number: 8559724Abstract: An apparatus and method for generating additional information about moving picture content, including: comparing image feature information about each image frame in moving picture content with image feature information about each image frame in web information, searching for an image frame in the moving picture content, the image frame matching the image frame in the web information, determining location information about the found image frame in the moving picture content, and generating additional information by use of the determined location information and the web information.Type: GrantFiled: February 24, 2010Date of Patent: October 15, 2013Assignee: Samsung Electronics Co., Ltd.Inventors: Yoon-hee Choi, Il-hwan Choi, Hee-seon Park
-
Patent number: 8559706Abstract: In one embodiment, a method executed by at least one processor includes receiving an image associated with a user and analyzing, by the at least one processor, the image. The method also includes determining a set of colors of the image based on the analysis of the image and generating a representation of the image based on the determined set of colors. The method further includes comparing the representation of the image to one or more stored representations of a first set of images. The stored representations of the first set of images are based on sets of colors of the first set of images. The first set of images are associated with known users. The method also includes, in response to comparing the representation of the image to the one or more stored representations of the first set of images, determining that the user is a suspected fraudulent user.Type: GrantFiled: November 30, 2011Date of Patent: October 15, 2013Assignee: Match.com, LPInventors: Aaron J. de Zeeuw, Jason L. Alexander
-
Publication number: 20130266215Abstract: Undated photos are organized by estimating the date of each photo. The date is estimated by building a model based on a set of reference photos having established dates, and comparing image characteristics of the undated photo to the image characteristics of the reference photos. The photo characteristics can include hues, saturation, intensity, contrast, sharpness and graininess as represented by image pixel data. Once the date of a photo is estimated, it can be tagged with identifying information, such as by using the estimated date to associate the photo with a node in a family tree.Type: ApplicationFiled: April 5, 2012Publication date: October 10, 2013Applicant: Ancestry.com Operations, Inc.Inventors: Chris Brookhart, Jack Reese
-
Publication number: 20130266229Abstract: A system for automatically selecting a template and a number of secondary images for display with a primary preselected image based on analyzing the primary image's attribute information and comparing the template's required image attributes and secondary image's attribute information. The attribute information is used to evaluate and arithmetically score a compatibility of the images and template so that a best compatibility fit can be obtained when displaying the image.Type: ApplicationFiled: March 14, 2013Publication date: October 10, 2013Inventors: Raymond W. Ptucha, Laura R. Whitby, William Bogart
-
Publication number: 20130266206Abstract: A user of an accessibility device is taught to properly use the device with a test image such that the accessibility device captures the entirety of or a large portion of a test image. In training the user, the device processes test image's information located within the device's field of view. Based on this processed information, the device indicates to the user if the device should be re-positioned such that a larger portion of the test image comes within the device's field of view.Type: ApplicationFiled: April 10, 2012Publication date: October 10, 2013Inventors: Paul Albrecht, Rafael Maya Zetune, Lucy Gibson, Raymond C. Kurzweil, Srivathsan Krishnamachari
-
Publication number: 20130266228Abstract: System, methods, and computer-readable media for automatic part identification and workflow generation. A method includes generating at least one image of a target part using a scanning device. The method includes analyzing the image to determine classification data based on physical characteristics of the target part. The physical characteristics including a size and shape of the target part. The method includes searching a parts database to identify a part that matches the classification data, and generating a workflow based on the identified matching part, including an identification of maintenance to be performed on the matching part.Type: ApplicationFiled: April 10, 2012Publication date: October 10, 2013Applicant: SIEMENS INDUSTRY, INC.Inventors: David Markson, Sabir Kader
-
Patent number: 8553988Abstract: To assess picture impairment due to the interpolation of output images from input images, for example in standards conversion, an output image detail measure is compared with an input image detail measure. One of the image detail measures is obtained by interpolation between image detail measures for at least two images.Type: GrantFiled: February 18, 2011Date of Patent: October 8, 2013Assignee: Snell LimitedInventor: Michael James Knee
-
Publication number: 20130259372Abstract: The present invention provides method and apparatus for object classifier generation, and method and apparatus for detecting object in image. The method for generating a two-cell structure feature descriptor of a two-cell structure composed of a center cell and a neighbor cell in an image region, wherein the neighbor cell is one of eight cells around and adjacent to the center cell, the method comprising: calculating step for calculating statistics of gradients in the center cell and the neighbor cell respectively; and comparing step for comparing the calculated statistics of gradients in the center cell and the neighbor cell, so as to obtain a two-cell structure feature descriptor for describing the feature of the two-cell structure, and wherein the two-cell structure feature descriptor is one bit binary value.Type: ApplicationFiled: March 26, 2013Publication date: October 3, 2013Inventors: LIFENG XU, Bo Wu
-
Publication number: 20130259389Abstract: The invention described herein is generally directed to methods for analyzing an image. In particular, crowded field images may be analyzed for unidentified, unobserved objects based on an iterative analysis of modified images including artificial objects or removed real objects. The results can provide an estimate of the completeness of analysis of the image, an estimate of the number of objects that are unobserved in the image, and an assessment of the quality of other similar images.Type: ApplicationFiled: May 24, 2013Publication date: October 3, 2013Applicant: Image Insight Inc.Inventors: Eric P. Rubenstein, Gordon A. Drukier