Patents by Inventor Kentaro Yokoi
Kentaro Yokoi has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 8447114Abstract: A feature extracting apparatus includes a pixel feature calculator that calculates a pixel feature for each pixel of image data; an area setting unit configured to set a plurality of areas in the image data; a coordinate mapping unit configured to map a first coordinate in one of the plurality of areas onto a second coordinate in at least one of the other plurality of areas; and a co-occurrence matrix calculator configured to calculate a co-occurrence matrix for each of the plurality of areas, the co-occurrence matrix being frequency of combinations of the pixel features at the first coordinate and the pixel feature at the second coordinates.Type: GrantFiled: August 6, 2009Date of Patent: May 21, 2013Assignee: Kabushiki Kaisha ToshibaInventors: Tomoki Watanabe, Satoshi Ito, Kentaro Yokoi
-
Patent number: 7844921Abstract: An apparatus for a user to interface with a control object apparatus by a posture or a motion of the user's physical part. An image input unit inputs an image including the user's physical part. A gesture recognition unit recognizes the posture or the motion of the user's physical part from the image. A control unit controls the control object apparatus based on an indication corresponding to the posture or the motion. A gesture information display unit displays an exemplary image of the posture or the motion recognized for the user's reference to indicate the control object apparatus.Type: GrantFiled: June 1, 2007Date of Patent: November 30, 2010Assignee: Kabushiki Kaisha ToshibaInventors: Tsukasa Ike, Yasuhiro Taniguchi, Ryuzo Okada, Nobuhisa Kishikawa, Kentaro Yokoi, Mayumi Yuasa, Bjorn Stenger
-
Patent number: 7756295Abstract: A device includes a first change detection unit which detects a change region distribution based on the texture information; a second change detection unit which detects a change region distribution based on a background differential method; a texture detection unit, a change-detection-unit weighting storage unit, and a change detection result integration unit, wherein while applying a firm texture differential method to the illumination change as much as possible, a detection unit based on a background differential method is applied to a region to which the texture differential method is not favorably applicable.Type: GrantFiled: November 27, 2006Date of Patent: July 13, 2010Assignee: Kabushiki Kaisha ToshibaInventor: Kentaro Yokoi
-
Publication number: 20100034465Abstract: A feature extracting apparatus includes a pixel feature calculator that calculates a pixel feature for each pixel of image data; an area setting unit configured to set a plurality of areas in the image data; a coordinate mapping unit configured to map a first coordinate in one of the plurality of areas onto a second coordinate in at least one of the other plurality of areas; and a co-occurrence matrix calculator configured to calculate a co-occurrence matrix for each of the plurality of areas, the co-occurrence matrix being frequency of combinations of the pixel features at the first coordinate and the pixel feature at the second coordinates.Type: ApplicationFiled: August 6, 2009Publication date: February 11, 2010Applicant: KABUSHIKI KAISHA TOSHIBAInventors: Tomoki Watanabe, Satoshi Ito, Kentaro Yokoi
-
Publication number: 20100034459Abstract: A feature extraction apparatus includes a pixel feature calculator configured to calculate a plurality of pixel features for each of pixels included in a plurality of pieces of image data; a co-occurrence frequency calculator configured to calculate co-occurrence frequencies of the pixel features by comparing the pixel features among corresponding pixels in the pieces of image data; and a co-occurrence frequency output unit configured to output the co-occurrence frequencies.Type: ApplicationFiled: August 6, 2009Publication date: February 11, 2010Applicant: KABUSHIKI KAISHA TOSHIBAInventors: Satoshi Ito, Tomoki Watanabe, Kentaro Yokoi
-
Publication number: 20090080711Abstract: A storage unit stores therein features and reliabilities of respective first segment regions divided from a first region. An object extracting unit extracts a second region including an object from input image data. A reliability calculating unit calculates reliabilities of respective second segment regions divided from the second region. A feature calculating unit calculates features of the respective second segment regions. A similarity calculating unit calculates an object similarity by performing multiplication of: segment similarities between the features of the first segment regions divided from the first region and the features of the second segment regions; and reliabilities of the respective segment regions, and then by summing up obtained values from the multiplication. A determining unit determines that an object included in the first region matches an object included in the second region when the object similarity is greater than a threshold.Type: ApplicationFiled: September 15, 2008Publication date: March 26, 2009Inventor: Kentaro YOKOI
-
Patent number: 7454041Abstract: When authentication data of a person O to be authenticated is registered as dictionary data, this authentication data of the person to be authenticated is acquired and collated with the registered dictionary data. In accordance with the collation result, the dictionary data is updated.Type: GrantFiled: September 6, 2006Date of Patent: November 18, 2008Assignee: Kabushiki Kaisha ToshibaInventors: Hiroshi Sukegawa, Kentaro Yokoi, Jun Ogata, Toshio Sato, Akio Okazaki
-
Publication number: 20080052643Abstract: An apparatus for a user to interface with a control object apparatus by a posture or a motion of the user's physical part. An image input unit inputs an image including the user's physical part. A gesture recognition unit recognizes the posture or the motion of the user's physical part from the image. A control unit controls the control object apparatus based on an indication corresponding to the posture or the motion. A gesture information display unit displays an exemplary image of the posture or the motion recognized for the user's reference to indicate the control object apparatus.Type: ApplicationFiled: June 1, 2007Publication date: February 28, 2008Applicant: KABUSHIKI KAISHA TOSHIBAInventors: Tsukasa IKE, Yasuhiro Taniguchi, Ryuzo Okada, Nobuhisa Kishikawa, Kentaro Yokoi, Mayumi Yuasa, Bjorn Stenger
-
Publication number: 20070206869Abstract: A first variation detecting unit, a second variation detecting unit and a varied area integrating unit that integrates results of variation detection of these units are provided. The first variation detecting unit judges a variation in an input image using brightness difference code of the brightness difference between respective pixels in a learned image and peripheral pixels thereof and brightness difference code of the input image, and the second variation detecting unit detects the variation of the brightness difference between the target pixel and the reference pixels in the input image on the basis of the stored positions of the reference pixels on the basis of the reference pixels having a predetermined brightness difference with respect to the respective pixels located in a plurality of directions from the respective pixels in the learned image.Type: ApplicationFiled: March 2, 2007Publication date: September 6, 2007Inventor: Kentaro Yokoi
-
Publication number: 20070127817Abstract: A device includes a first change detection unit which detects a change region distribution based on the texture information; a second change detection unit which detects a change region distribution based on a background differential method; a texture detection unit, a change-detection-unit weighting storage unit, and a change detection result integration unit, wherein while applying a firm texture differential method to the illumination change as much as possible, a detection unit based on a background differential method is applied to a region to which the texture differential method is not favorably applicable.Type: ApplicationFiled: November 27, 2006Publication date: June 7, 2007Inventor: Kentaro Yokoi
-
Publication number: 20070031010Abstract: When authentication data of a person O to be authenticated is registered as dictionary data, this authentication data of the person to be authenticated is acquired and collated with the registered dictionary data. In accordance with the collation result, the dictionary data is updated.Type: ApplicationFiled: September 6, 2006Publication date: February 8, 2007Applicant: KABUSHIKI KAISHA TOSHIBAInventors: Hiroshi Sukegawa, Kentaro Yokoi, Jun Ogata, Toshio Sato, Akio Okazaki
-
Patent number: 7120278Abstract: When authentication data of a person O to be authenticated is registered as dictionary data, this authentication data of the person to be authenticated is acquired and collated with the registered dictionary data. In accordance with the collation result, the dictionary data is updated.Type: GrantFiled: August 23, 2002Date of Patent: October 10, 2006Assignee: Kabushiki Kaisha ToshibaInventors: Hiroshi Sukegawa, Kentaro Yokoi, Hironori Dobashi, Jun Ogata, Toshio Sato, Akio Okazaki
-
Publication number: 20060100872Abstract: A feature amount extracting unit extracts feature amount vectors of an inputted image. A probability distribution calculator calculates a probability distribution of feature amount vectors in a calculation space range which is set by a calculation space range setting unit. A probability distribution storage stores the probability distribution in association with identifiers of learning objects. A posterior probability calculator calculates a posterior probability, which is a probability that a recognition object corresponds to each of the learning objects, using feature amount vectors calculated from an image of the recognition object and the probability distribution of the learning objects stored in the probability distribution storage. A posterior probability comparing unit compares posterior probabilities calculated and outputs a result of recognition of the recognition object.Type: ApplicationFiled: November 8, 2005Publication date: May 11, 2006Applicant: Kabushiki Kaisha ToshibaInventor: Kentaro Yokoi
-
Patent number: 6934404Abstract: An image input section inputs an image of a letter P and stores the same into an image memory. A stamp detecting section detects a stamp by a luminance projection value based on the image of the letter stored in the image memory, determining that an area is not an external area of the stamp and determining the area as an internal area of the stamp if the length of the area is smaller than a stamp internal gap permissible threshold value used for determining a stamp internal gap even in a case where the area which is partly determined as an external area of the stamp is present in an area which is determined as the internal area of the stamp affixed to the letter P based on the thus derived projection value.Type: GrantFiled: September 19, 2001Date of Patent: August 23, 2005Assignee: Kabushiki Kaisha ToshibaInventor: Kentaro Yokoi
-
Patent number: 6807302Abstract: A recognition apparatus of this invention for recognizing sorting information as a character string written within a cellophane region of a paper-like material extracts edge components according to a differential image based on an image of light and shade of the paper-like material, determines a cellophane frame based on the edge components and recognizes the character string within the thus determined cellophane frame as an address. Thus, the cellophane region in which the address used as the sorting information is written can be correctly extracted and occurrence of erroneous recognition of the sorting information and erroneous sorting of the paper-like material can be prevented.Type: GrantFiled: March 14, 2001Date of Patent: October 19, 2004Assignee: Kabushiki Kaisha ToshibaInventor: Kentaro Yokoi
-
Publication number: 20040125991Abstract: An individual recognizing apparatus includes a data acquisition unit to acquire certifying data from a recognized person, a detection unit to detect feature points of the certifying data acquired by the data acquisition unit, a change calculation unit to calculate changes of detecting positions of the feature points detected by the detection unit, an aptitude judging unit to judge whether the certifying data acquired by the data acquisition unit is appropriate for the preparation of a certifying dictionary based on the changes of feature points calculated by the change calculation unit, a dictionary preparing unit to prepare a certifying dictionary based on the certifying data acquired by the data acquisition unit when the acquired certifying data is judged appropriate by the aptitude judging unit, a dictionary storing unit to store the certifying dictionary prepared by the dictionary preparing unit, and a certifying unit to certify that a recognized person is a proper person using the certifying data acquireType: ApplicationFiled: November 20, 2003Publication date: July 1, 2004Applicant: KABUSHIKI KAISHA TOSHIBAInventor: Kentaro Yokoi
-
Publication number: 20030039380Abstract: When authentication data of a person O to be authenticated is registered as dictionary data, this authentication data of the person to be authenticated is acquired and collated with the registered dictionary data. In accordance with the collation result, the dictionary data is updated.Type: ApplicationFiled: August 23, 2002Publication date: February 27, 2003Inventors: Hiroshi Sukegawa, Kentaro Yokoi, Hironori Dobashi, Jun Ogata, Toshio Sato, Akio Okazaki
-
Publication number: 20020046663Abstract: An image input section inputs an image of a letter P and stores the same into an image memory. A stamp detecting section detects a stamp by a luminance projection value based on the image of the letter stored in the image memory, determining that an area is not an external area of the stamp and determining the area as an internal area of the stamp if the length of the area is smaller than a stamp internal gap permissible threshold value used for determining a stamp internal gap even in a case where the area which is partly determined as an external area of the stamp is present in an area which is determined as the internal area of the stamp affixed to the letter P based on the thus derived projection value.Type: ApplicationFiled: September 19, 2001Publication date: April 25, 2002Inventor: Kentaro Yokoi
-
Publication number: 20010022854Abstract: A recognition apparatus of this invention for recognizing sorting information as a character string written within a cellophane region of a paper-like material extracts edge components according to a differential image based on an image of light and shade of the paper-like material, determines a cellophane frame based on the edge components and recognizes the character string within the thus determined cellophane frame as an address. Thus, the cellophane region in which the address used as the sorting information is written can be correctly extracted and occurrence of erroneous recognition of the sorting information and erroneous sorting of the paper-like material can be prevented.Type: ApplicationFiled: March 14, 2001Publication date: September 20, 2001Inventor: Kentaro Yokoi