CitationDownload as .RIS
Emerald Group Publishing Limited
Copyright © 2011, Emerald Group Publishing Limited
Article Type: Patent abstracts From: Sensor Review, Volume 31, Issue 2
Title: Pattern recognition apparatus and method therefore, configured to recognize object and another lower-order object
Applicant: Canon KK (JP); Yano Kotaro (JP)
Patent number: WO2010131435 (A1)
Publication date: November 18, 2010
In a pattern recognition apparatus, a characteristic amount calculation unit calculates a characteristic amount for recognizing a desired object from a partial image clipped from an input pattern, a likelihood calculation unit calculates a likelihood of an object as a recognition target from the characteristic amount calculated by the characteristic amount calculation unit by referring to an object dictionary, and an object determination unit determines whether the partial image is the object as the recognition target based on the likelihood of the object calculated by the likelihood calculation unit. The likelihood calculation unit calculates the likelihood of the object as the recognition target from the characteristic amount calculated by the characteristic amount calculation unit by referring to a specific object dictionary. The object determination unit determines whether the partial image is a specific object as the recognition target from the likelihood of the object `calculated by the likelihood calculation unit.
Title: Image processing apparatus, image processing method and storage medium
Applicant: Sony Corp (JP)
Patent number: EP2249264 (A1)
Publication date: November 10, 2010
An image processing apparatus including: an image acquiring element for acquiring a target image; an identification information recognizing element for recognizing identification information corresponding to a specific image pattern from the target image acquired by the image acquiring element; and an activating element for activating selectively from among a plurality of previously stored processes a specific process corresponding to the identification information recognized by the identification information recognizing element so as to start execution of the specific process.
Title: Predicate logic based image grammars for complex visual pattern recognition
Applicant: Siemens Corp. (US)
Patent number: US2010278420 (A1)
Publication date: November 4, 2010
First-order predicate logics are provided, extended with a bilattice-based uncertainty handling formalism, as a means of formally encoding pattern grammars, to parse a set of image features, and detect the presence of different patterns of interest implemented on a processor. Information from different sources and uncertainties from detections, are integrated within the bilattice framework. Automated logical rule weight learning in the computer vision domain applies a rule weight optimization method which casts the instantiated inference tree as a knowledge-based neural network, to converge upon a set of rule weights that give optimal performance within the bilattice framework. Applications are in:
detecting the presence of humans under partial occlusions;
detecting large complex man made structures in satellite imagery;
detection of spatio-temporal human and vehicular activities in video; and
parsing of graphical user interfaces.
Title: Pattern recognition apparatus, pattern recognition method, image processing apparatus, and image processing method
Applicant: Panasonic Corp
Patent number: US2010172580 (A1)
Publication date: July 8, 2010
A task of the present invention is that even when a plurality of images exists in which the positions or sizes of character patterns indicating the identical object are different from each other, they can be treated as character patterns indicating the identical object. An image and supplementary information of the image, such as a photographing point and time, are input by an image input section and are stored in an image data storage section. Character recognition in the image is performed by a character recognition section, and the recognition result is stored in a character recognition result storage section. An analysis section extracts object character information relevant to an object from the image, the supplementary information, and the character recognition result on the basis of the analysis conditions input in a designation section to thereby analyze an object, and the analysis result is output to a result output section. Accordingly, a change in the object can be analyzed by analyzing a change in character patterns indicating the identical object.
Title: Large-capacity pattern recognition method
Applicant: East China Jiaotong University
Patent number: CN101739565 (A)
Publication date: June 16, 2010
The invention provides a large-capacity pattern recognition method, belonging to the technical field of image processing. In the method, weight value matrix elements and the pattern recognition stored on the basis of probability distribution are utilized. The method comprises the steps of: calculating a weight value matrix W according to a provided pattern or an image; designing the matrix elements wi and j of the W to be a random variable or a random numerical value, and forming 2N different Wis according to the number of the elements wi and j to be processed; and finally determining the input pattern to be recognized after training or the image to be the different Wis obtained by measuring and collapsing to achieve the purpose of large-capacity pattern recognition. The method in the invention stores the matrix elements by probability distribution, the recognized pattern or image can reach 2N times of a processing unit, and the storage capacity or the memory capacity is increased by exponential order. The method of the invention is of great significance to the promotion of the researches, such as the pattern recognition, the image processing, human brain consciousness, high-level intelligent robots and the like. The invention is suitable for the recognition of large-capacity pattern or image.
Title: Pattern recognition device, and method and program thereof
Applicant: NEC Corp
Patent number: JP2010079513 (A)
Publication date: April 8, 2010
Problem to be solved: to recognize the normal position of the recognition object of an input image even when an input image includes a pattern which is partially different from that of a reference image.
Solution: A sub-template creation means segments a reference image, and creates a sub-reference image, and a matching processing means six outputs recognition position candidate coordinates by template matching processing for calculating the inter-correlation coordinate value of a contrast value between the reference image and an input image, and a sub-matching processing means outputs sub-recognition position candidate coordinates by the template matching processing for calculating the inter-correlation value of the contrast value between a sub-reference image and the input image by limiting to the sub-region including the recognition position coordinate candidates, and a recognition position output means compares the results of the matching processing means and the sub-matching processing means, and measures the position coordinates to maximize the inter-correlation value, and outputs the position coordinates.
Title: Vision sensors, systems, and methods
Applicant: Cognex Corp. (US)
Patent number: EP2235662 (A1)
Publication date: October 6, 2010
A single chip vision sensor of an embodiment includes a pixel array and one or more circuits. The one or more circuits are configured to search an image for one or more features using a model of the one or more features. A method of an embodiment in a single chip vision sensor includes obtaining an image based at least partially on sensed light, and searching the image for one or more features using a model of the one or more features. A system of an embodiment includes the single chip vision sensor and a device. The device is configured to receive one or more signals from the single chip vision sensor and to control an operation based at least partially on the one or more signals.