Abstract: Methods and systems for managing digital photos are disclosed. In one implementation, a method for organizing digital photos includes receiving a set of digital photos, analyzing the set of digital photos to create tags that identify content information in the set of digital photos, tagging the set of digital photos in accordance with their corresponding content information, categorizing the set of digital photos in accordance with their corresponding tags, and displaying the digital photos and their corresponding tags with a display device.
Abstract: Disclosed is an image processor generating a three-dimensional image easily three-dimensionally viewed by, and hardly causing fatigue of, an observer, and easily adjusting a three-dimensional effect of an arbitrary portion in the three-dimensional image. The disparity correction portion 101 corrects a disparity of the input disparity image within a predetermined range and outputs a disparity image storing the corrected disparity to the disparity conversion portion 103. The disparity conversion portion 103 converts the disparity of the disparity image such that a disparity corresponding to the image of the main object determined by the main object determination portion 102 reaches a predetermined value, and outputs the disparity image obtained after the conversion to an image generation portion 104. The image generation portion 104 generates an image for the left eye and an image for the right eye based on the input disparity image and the input captured image, and outputs the images to a display apparatus.
Abstract: A method for analyzing a character string, the method including: analyzing a character string to determine one of more characters of the character string; determining from a dictionary source, an alternative character string to the analyzed character string; comparing the analyzed character string with the alternative character string to determine a weighting factor for each of the characters of the analyzed character string relative to the positional arrangement of the characters in the alternative character string; and for each determined weighting factor, generating for each of the characters in the analyzed character string a corresponding character of a particular size as determined by the weighting factor.
Type:
Grant
Filed:
September 27, 2011
Date of Patent:
August 12, 2014
Assignee:
International Business Machines Corporation
Abstract: A computer-implemented method for moving information between computing devices includes capturing a digital image of a display of a first computing device using a camera of a second computing device, transmitting, to the first computing device, data that corresponds to the digital image; analyzing the transmitted data on the first computing device to determine whether the digital image matches a current display of the first computing device, and using the analysis to cause one of the first or second computing devices to invoke an application and match a state of an application that is executing on the other of the first or second computing devices.
Abstract: A sectional image recognition method and a zonal recognition device are applied in a zonal fingerprint recognition device with small storage capacity.
Abstract: An authenticity determination support device includes an acquiring unit and a compressing unit. The acquiring unit photographs, in a solid having a unique random feature in a surface thereof, a predetermined area in the surface such that continuity of the feature is generated in a predetermined direction, and thereby acquires feature information representing the feature included in the area. The compressing unit compresses the feature information in a direction in which continuity of the feature information acquired by the acquiring unit is high.
Abstract: A system and method for performing automated defect detection by utilizing data from prior inspections is disclosed. The system and method may include providing a image capture device for capturing and transmitting at least one current image of an object and providing a database for storing at least one prior image from prior inspections. The system and method may further include registering the at least one current image with the at least one prior image, comparing the registered at least one current image with the at least one prior image to determine a transformation therebetween and updating the database with the at least one current image.
Type:
Grant
Filed:
November 3, 2011
Date of Patent:
July 29, 2014
Assignee:
United Technologies Corporation
Inventors:
Paul Raymond Scheid, Richard C. Grant, Alan Matthew Finn, Hongcheng Wang, Ziyou Xiong
Abstract: An object recognition system performs a number of rounds of dimensionality reduction and consistency learning on visual content items such as videos and still images, resulting in a set of feature vectors that accurately predict the presence of a visual object represented by a given object name within an visual content item. The feature vectors are stored in association with the object name which they represent and with an indication of the number of rounds of dimensionality reduction and consistency learning that produced them. The feature vectors and the indication can be used for various purposes, such as quickly determining a visual content item containing a visual representation of a given object name.
Abstract: Techniques are described to employ image recognition techniques to content. In an implementation, one or more images are identified in content using a signature derived from the one or more images. Metadata associated with the content is then supplemented based on the identified one or more images.
Abstract: Methods are disclosed for finding images from a large corpus of images that at least partially match a query image. The present method makes use of feature detectors to bundle features into local groups or bundles. These bundled features are repeatable and much more discriminative than an individual SIFT feature. Equally importantly, the bundled features provide a flexible representation that allows simple and robust geometric constraints to be efficiently enforced when querying the index.
Type:
Grant
Filed:
August 27, 2012
Date of Patent:
July 22, 2014
Assignee:
Microsoft Corporation
Inventors:
Michael Isard, Qifa Ke, Jian Sun, Zhong Wu
Abstract: A system, method, and apparatus includes a computed tomography (CT) system having a rotatable gantry, an x-ray source, a generator, a detector having pixels and positioned to receive x-rays, and a computer. The computer is programmed to acquire CT data representative of an object, determine a first subset of the CT data, determine a second subset of the CT data, and determine a difference between the first and second subsets of the CT data to identify a motion region in the object. The computer is also programmed to update image data reconstructed from a first portion of the first subset of the CT data and corresponding to the region and reconstruct an image based on the updated image data and non-updated image data. The non-updated image data is reconstructed from a second portion the first subset of the CT data.
Type:
Grant
Filed:
August 23, 2012
Date of Patent:
July 1, 2014
Assignee:
General Electric Company
Inventors:
Jiang Hsieh, Roy-Arnulf Helge Nilsen, Peter Michael Edic, Bruno Kristiaan Bernard De Man, Jean-Baptiste Thibault, Baojun Li, John Lawrence Seamans
Abstract: An image processing apparatus includes: face detection means for detecting a subject face contained in each of images continuously captured by capturing means and extracting attribute information on each detected face; score determination means for determining a score for each of the continuously captured images on the basis of the attribute information on the detected face extracted by the face detection means; and representative image selection means for selecting a representative image from the continuously captured images on the basis of the score determined by the score determination means.
Abstract: A tomographic system includes a gantry having an opening for receiving an object to be scanned, a radiation source, a detector positioned to receive radiation from the source that passes through the object, and a computer. The computer is programmed to acquire a plurality of projection datasets of the object, define a temporal subset of projection datasets from the plurality of projection datasets, reconstruct a working image of the object using the plurality of projection datasets, identify a region of motion in the working image, and minimize motion artifacts in the region of motion in the working image using the temporal subset of projection datasets.
Type:
Grant
Filed:
May 6, 2010
Date of Patent:
June 24, 2014
Assignee:
General Electric Company
Inventors:
Jiang Hsieh, Brian Edward Nett, Debashish Pal, Basel Hasan Taha, Jean-Baptiste Thibault, Zhou Yu
Abstract: Methods and systems for egomotion estimation (e.g. of a vehicle) from visual inputs of a stereo pair of video cameras are described. 3D egomotion estimation is a six degrees of freedom problem in general. In embodiments of the present invention, this is simplified to four dimensions and further decomposed to two two-dimensional sub-solutions. The decomposition allows use of a voting strategy that identifies the most probable solution. An input is a set of image correspondences between two temporally consecutive stereo pairs, i.e. feature points do not need to be tracked over time. The experiments show that even if a trajectory is put together as a simple concatenation of frame-to-frame increments, the results are reliable and precise.
Type:
Grant
Filed:
May 31, 2011
Date of Patent:
June 3, 2014
Assignees:
Toyota Motor Europe NV/SA, Czech Technical University in Prague
Inventors:
Gabriel Othmezouri, Ichiro Sakata, Jiri Matas, {hacek over (S)}t{hacek over (e)}pán Obdr{hacek over (z)}álek
Abstract: An individual is identified in a photograph. A portion of the photograph is temporarily blurred to prevent the individual from being recognized. Once consent is received for the tag, the blur is removed. However, if consent is not received, the blur remains.
Abstract: An exemplary locomotion analysis method includes steps of: acquiring a depth map including an image of a measured object, filtering out a background image of the depth map according to a depth threshold, finding out the image of the measured object from the residual image of the depth map, calculating three-dimensional (3D) coordinates of the measured object according to the image of the measured object has been found out, recording the 3D coordinates to reconstruct a 3D moving track of the measured object and performing a locomotion analysis of the measured object according to the 3D moving track. Moreover, an exemplary locomotion analysis apparatus applied to the above method also is provided.
Type:
Grant
Filed:
September 28, 2011
Date of Patent:
May 27, 2014
Assignee:
National Taiwan University
Inventors:
Ta-Te Lin, Tai-Hsien Ou-Yang, Meng-Li Tsai, Chen-Tung Yen
Abstract: A system for generating virtual interest points in an image, according to detected interest points in that image is detected by an interest point detector. The system includes: an interest point density map producer and an interest point generator, the interest point density map producer receiving the image including the detected interest points, the interest point density map producer extracts a density map of the detected interest points within the image. The interest point generator is coupled with the interest point density map producer, the interest point generator receiving the image including the detected interest points and the interest point density map. The interest point generator determines image areas for generating virtual interest points, the interest point generator generating at least one virtual interest point at the determined areas according to at least the position of one of the detected interest points, the virtual interest point not being detected by the interest point detector.
Abstract: A video detection system and method compares a queried video segment to one or more stored video samples. Each of the queried video segments and stored video samples can be represented by respective digital image sets. A first and second comparison comprises comparing a set of low and high resolution temporal and spatial statistical moments in a COLOR9 space, and eliminating file digital image sets that do not match the queried digital image set. A third comparison generates a set of matching files by comparing a set of wavelet transform coefficients in a COLOR9 space. RGB bit-wise registration and comparison of one or more subframes of specific frames in the queried digital image set to a corresponding set of matching file subframes determines queried subframe changes. In the event of a change in a queried subframe, the changed subframe is added to the set of matching file subframes.
Abstract: A method for measuring the relative local position error of one of the sections of an object that is exposed section by section, in particular of a lithography mask or of a wafer, is provided, each exposed section having a plurality of measurement marks, wherein a) a region of the object which is larger than the one section is imaged in magnified fashion and is detected as an image, b) position errors of the measurement marks contained in the detected image are determined on the basis of the detected image, c) corrected position errors are derived by position error components which are caused by the magnified imaging and detection being extracted from the determined position errors of the measurement marks, d) the relative local position error of the one section is derived on the basis of the corrected position errors of the measurement marks.
Type:
Grant
Filed:
November 28, 2009
Date of Patent:
May 20, 2014
Assignee:
Carl Zeiss SMS GmbH
Inventors:
Michael Arnz, Dirk Beyer, Wolfgang Harnisch, Thomas Scheruebl
Abstract: Stereoscopic imaging devices may include stereoscopic imagers, stereoscopic displays, and processing circuitry. The processing circuitry may be used to collect auto white balance (AWB) statistics for each image captured by the stereoscopic imager. A stereoscopic imager may include two image modules that may be color calibrated relative to each other or relative to a standard calibrator. AWB statistics may be used by the processing circuitry to determine global, local and spatial offset gain adjustments to provide intensity matched stereoscopic images for display. AWB statistics may be combined by the processing circuitry with color correction offsets determined during color calibration to determine color-transformation matrices for displaying color matched stereoscopic images using the stereoscopic display.
Type:
Grant
Filed:
May 31, 2011
Date of Patent:
May 20, 2014
Assignee:
Aptina Imaging Corporation
Inventors:
Yingjun Bai, Honghong Peng, Miguel Flores, Elizabeth Martin, Andrew Hanvey