Abstract: Provided are a monitoring system and an operating method thereof, and more particularly, an image processing method and apparatus for removing a motion blur of a wide dynamic range (WDR) image by using a machine learning algorithm. The image processing method includes: generating an overlap image by overlapping a first image having a predetermined exposure time and a second image having an exposure time different from that of the first image; detecting a region of interest (ROI) in which a motion blur occurs in the overlap image; and performing a motion blur removing operation of changing an image in the ROI to any one of the first image and the second image by applying a first machine learning algorithm.
Abstract: A medical image processing apparatus may include an image data generator to generate image data corresponding to at least two different energy bands by using an X-ray, an ROI processor to highlight a tissue of interest classified based on a predetermined characteristic to be distinguished from a normal tissue, in the generated image data, and a display to alternately display first image data in which the tissue of interest is not highlighted, and second image data in which the tissue of interest is highlighted to be distinguished from the normal tissue.
Type:
Grant
Filed:
July 31, 2013
Date of Patent:
May 3, 2016
Assignee:
SAMSUNG ELECTRONICS CO., LTD.
Inventors:
Jae Hyun Kwon, Sung Su Kim, Young Hun Sung, Hyun Hwa Oh, Myung Jin Chung
Abstract: A system and method for identifying and locating instances of a shape under large variations in linear degrees of freedom is provided. The invention extracts boundary segments from an image and generates potential match candidates for boundary models based on the extracted boundary segments. The invention also extracts skeletal segments from the obtained image. Potential match candidates are then generated for skeletal models based on the extracted skeletal segments. Once the match candidates for the boundary models and skeletal models have been generated, the present invention then corresponds the various boundary segments and outputs a best correspondence. The output from the present invention may be utilized by a user to signify acceptance of the various correspondences located by the present invention. These correspondences may then be utilized to train a machine vision system.
Abstract: Provided us a visual cortical circuit apparatus comprising: a current mirror unit which uses a transistor as a current source to generate a current having the same size as that of a reaction; a transconductance unit which takes, as an input, the current generated by the current mirror unit and outputs a voltage using a transconductance; and a buffer unit for converting the voltage output from the transconductance unit into a current and buffering the current.
Type:
Grant
Filed:
January 24, 2013
Date of Patent:
March 15, 2016
Assignee:
KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY
Abstract: An authentication device may include a housing and a finger sensor carried by the housing and including first processing circuitry and a finger sensing area coupled thereto. The first processing circuitry may be configured to generate finger image data based upon a finger positioned adjacent the finger sensing area, and generate and store a first template based upon the finger image data. The authentication device may include second processing circuitry carried by the housing and configured to obtain the finger image data from the first processing circuitry. The second processing circuitry may be configured to generate a second template based upon the finger image data. The first processing circuitry may further be configured to obtain the second template from second processing circuitry, and validate the second template against the first template.
Abstract: Methods and apparatus to count people in images are disclosed. An example method includes generating a first fluctuation factor for a first frame by averaging fluctuation values of a random set of pixels of the first frame; generating a second fluctuation factor for a person indication area of the first frame by averaging fluctuation values of pixels of the person indication area; and marking the person indication area as a false positive when the second fluctuation factor is less than or equal to the first fluctuation factor.
Abstract: An authentication apparatus performs identity authentication by comparing and matching image information of a palm captured by a sensor unit with a preliminarily registered template. A surface information correcting unit corrects concavity/convexity of a palm surface for surface information that allows the concavity/convexity thereof to be evaluated. The surface information is extracted by a surface information extraction unit from the image information obtained by capturing the palm. When the surface information is not corrected by the surface information correcting unit or not used for authentication by an authentication unit even after correction, the authentication apparatus newly obtains image information of the palm. Correction by the surface information correcting unit reduces opportunities for the authentication apparatus to perform notification to guide the palm to a proper posture.
Abstract: A parallel object detection method for heterogeneous microarchitectures. The method is designed for increasing the throughput of object detection in a computer system that is equipped with an array of cores including a shared memory, a constant memory, and functional units. Latency reduction is achieved through a multilevel parallelization method that exploits fine-grain data-level parallelism using multithreaded SIMD computations, and coarse-grain parallelism by relying on concurrent kernel execution.
Type:
Grant
Filed:
March 15, 2012
Date of Patent:
January 12, 2016
Assignee:
HERTA SECURITY, S.L.
Inventors:
David Oro García, Carles Fernández Tena, Javier Rodríguez Saeta
Abstract: Systems and methods for implementing a hierarchical image recognition framework for classifying digital images are provided. The provided hierarchical image recognition framework utilizes a multi-layer approach to model training and image classification tasks. A first layer of the hierarchical image recognition framework generates first layer confidence scores, which are utilized by the second layer to produce a final recognition score. The provided hierarchical image recognition framework permits model training and image classification tasks to be performed more accurately and in a less resource intensive fashion than conventional single-layer image recognition frameworks. In some embodiments real-time operator guidance is provided for an image classification task.
Type:
Grant
Filed:
August 6, 2010
Date of Patent:
December 8, 2015
Assignee:
Sony Corporation
Inventors:
Shengyang Dai, Su Wang, Akira Nakamura, Takeshi Ohashi, Jun Yokono
Abstract: Systems and methods are provided for determining whether given business listings are spam or are closed businesses. In one example, a system receives a business listing from a user. The business listing contains a geolocation and the name of a business. The system also receives one or more street level images related to a geographic object that is at or near the same geolocation as the business listing. The system determines if the business listing is spam or is closed based on the received street level images by determining if the geographic object is the business or by analyzing whether the business associated with the listing is shown in any of the street level images.
Type:
Grant
Filed:
February 24, 2011
Date of Patent:
November 24, 2015
Assignee:
Google Inc.
Inventors:
Andrea Frome, Howard Wellington Trickey, Melanie Clements, Ethan G. Russell, Paul Eastlund, Diego Ariel Gertzenstein, Douglas Richard Grundman, Baris Yuksel
Abstract: Systems and methods to select and launch a restricted computing environment on an information handing system in an automated manner based on detected facial age and/or gender of a current user of the information handling system.
Abstract: An inspection apparatus and method are provided, wherein even when an image that cannot be processed by a current image processing algorithm is input to an image processing unit while a working line is in operation, the inspection can be continued by newly generating an image processing algorithm optimized in keeping with a particular image. The apparatus includes an erroneous recognition detector, a teacher data generator and a switching unit for switching the current image processing algorithm to a new image processing algorithm generated based on an updated teacher data group. As a result, the inspection can be continued without extremely decreasing the accuracy even when an unexpected image is input to the working line.
Abstract: A biometric authentication system includes: an image acquisition unit for acquiring an image of a living body; a light source with a predetermined wavelength band; an authentication information storage unit for, if light is emitted by the light source, setting a predetermined distance for a first distance to a first image acquired by the image acquisition unit in a depth direction so that quality of the first image is improved, extracting a first feature to be used to perform biometric authentication from the first image whose quality has been improved, and storing authentication information regarding the first feature; a feature extraction unit for, if light is emitted by the light source when performing authentication, setting the predetermined distance for a second distance to a second image acquired by the image acquisition unit in the depth direction so that quality of the second image is improved, and extracting a second feature for biometric authentication from the second image whose quality has been i
Abstract: A server system receives a visual query from a client system. The visual query is an image containing text such as a picture of a document. At the receiving server or another server, optical character recognition (OCR) is performed on the visual query to produce text recognition data representing textual characters. Each character in a contiguous region of the visual query is individually scored according to its quality. The quality score of a respective character is influenced by the quality scores of neighboring or nearby characters. Using the scores, one or more high quality strings of characters are identified. Each high quality string has a plurality of high quality characters. A canonical document containing the one or more high quality textual strings is retrieved. At least a portion of the canonical document is sent to the client system.
Type:
Grant
Filed:
August 6, 2010
Date of Patent:
November 10, 2015
Assignee:
Google Inc.
Inventors:
David Petrou, Ashok C. Popat, Matthew R. Casey
Abstract: An attribute of image data can accurately be discriminated. An image attribute discrimination apparatus includes a heterogeneous region extracting unit that specifies a heterogeneous region from image data. The heterogeneous region includes a heterogeneous matter whose attribute is different from that of a content originally produced by the image data. An image attribute discrimination apparatus further includes a scene discrimination unit that discriminates the attribute of the image data based on a feature quantity extracted from a pixel group except each pixel in the heterogeneous region in each pixel of the image data.
Abstract: An information processing apparatus is provided that includes an obtaining section and a selecting section. The obtaining section obtains information of first and second images that each have an overlapped region where the first image and the second image are overlapped and constitute a taken image including an image part of a subject by being connected with each other with the overlapped region as a reference. The selecting section determines pixels other than the image part of the subject based on information of a plurality of pixels that belong to the overlapped region of the first image where the first image is overlapped with the second image, the information of the plurality of pixels being included in the obtained information of the first image, and selects, out of the determined pixels, a connection pixel corresponding to a position where the first image and the second image are connected in the overlapped region.
Abstract: A server system receives a visual query from a client system distinct from the server system, performs optical character recognition (OCR) on the visual query to produce text recognition data representing textual characters, including a plurality of textual characters in a contiguous region of the visual query, and scores each textual character in the plurality of textual characters. The server system identifies, in accordance with the scoring, one or more high quality textual strings, each comprising a plurality of high quality textual characters from among the plurality of textual characters in the contiguous region of the visual query; retrieves a canonical document having the one or more high quality textual strings; generates a combination of the visual query and at least a portion of the canonical document; and sends the combination to the client system.
Type:
Grant
Filed:
December 1, 2011
Date of Patent:
November 3, 2015
Assignee:
Google Inc.
Inventors:
David Petrou, Ashok C. Popat, Matthew R. Casey
Abstract: The method of the invention comprises: obtaining a sequence of at least two images, with different levels of illumination; extracting the region containing the sign in the image; calculating the luminance values of the signs; and obtaining the difference in luminance of the sign corresponding to the two levels of illumination. The value obtained is the luminance of the sign (11) corresponding to an illumination equal to the difference between the illuminations, or additional illumination. This result is based on the additive property of luminance, according to which the luminance of a sign is the sum of the luminance produced by each source of illumination. A basic illumination device (5), an additional illumination device (7), at least one camera for taking images, and image recording, positioning and synchronism systems are required to implement the method.
Type:
Grant
Filed:
April 8, 2008
Date of Patent:
October 27, 2015
Assignee:
DBI/Cidaut Technologies, LLC
Inventors:
Francisco Javier Burgoa Roman, Jose Antonio Gutierrez Mendez, Alberto Mansilla Gallo, Diego Oritz de Lejarazu Machin, Alberto Senen Perales Garcia
Abstract: The method of the invention comprises: obtaining a sequence of at least two images, with different levels of illumination; extracting the region containing the sign in the image; calculating the luminance values of the signs; and obtaining the difference in luminance of the sign corresponding to the two levels of illumination. The value obtained is the luminance of the sign (11) corresponding to an illumination equal to the difference between the illuminations, or additional illumination. This result is based on the additive property of luminance, according to which the luminance of a sign is the sum of the luminance produced by each source of illumination. A basic illumination device (5), an additional illumination device (7), at least one camera for taking images, and image recording, positioning and synchronism systems are required to implement the method.
Type:
Grant
Filed:
April 30, 2014
Date of Patent:
October 27, 2015
Assignee:
DBI/Cidaut Technologies, LLC
Inventors:
Francisco Javier Burgoa Roman, Jose Antonio Gutierrez Mendez, Alberto Mansilla Gallo, Diego Ortiz de Lejarazu Machin, Alberto Senen Perales Garcia
Abstract: The present invention is a system and method for modeling faces from images captured from a single or a plurality of image capturing systems at different times. The method first determines the demographics of the person being imaged. This demographic classification is then used to select an approximate three dimensional face model from a set of models. Using this initial model and properties of camera projection, the model is adjusted leading to a more accurate face model.