Patents by Inventor Toshikazu TAKI
Toshikazu TAKI 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: 11915498Abstract: According to one embodiment, a reading system includes an extractor, a determiner, and a reader. The extractor extracts a candidate image from an input image. The candidate image is of a portion of the input image in which a segment display is imaged. The determiner calculates an angle with respect to a reference line of each of a plurality of straight lines detected from the candidate image, and determines whether or not the candidate image is an image of a segment display based on a distribution indicating a relationship between the angle and a number of the straight lines. The reader reads a numerical value displayed in a segment display from the candidate image determined to be an image of a segment display.Type: GrantFiled: March 7, 2022Date of Patent: February 27, 2024Assignee: KABUSHIKI KAISHA TOSHIBAInventor: Toshikazu Taki
-
Patent number: 11900664Abstract: According to one embodiment, a reading system includes an extractor, a determiner, and a reader. The extractor extracts a candidate image from an input image. The candidate image is a candidate of a portion of the input image in which a segment display is imaged. The determiner uses the candidate image and a mask to calculate a match ratio indicating a certainty of a segment display being included in the candidate image, and determines that the candidate image is an image of a segment display when the match ratio is not less than a threshold. The mask and the threshold are preset. The reader reads a numerical value displayed in a segment display from the candidate image determined to be an image of a segment display.Type: GrantFiled: August 23, 2022Date of Patent: February 13, 2024Assignee: Kabushiki Kaisha ToshibaInventor: Toshikazu Taki
-
Publication number: 20230290161Abstract: According to an embodiment, a reading system includes a reader and a calculator. The reader reads, from a character image, a character that is displayed by a segment display. The calculator performs one of first, second, third, or fourth processing. In the first processing, the calculator calculates a first score based on a state of pixels of the character. In the second processing, the calculator calculates a second score based on a match ratio between the pixels and the extracted pixels. In the third processing, the calculator calculates a third score based on a ratio of a length of the character image in first and second direction. In the fourth processing, the calculator calculates a fourth score based on a comparison result between the detected result and preset patterns. The calculator calculates a certainty of the reading by using one of the first, second, third, or fourth score.Type: ApplicationFiled: May 22, 2023Publication date: September 14, 2023Applicants: KABUSHIKI KAISHA TOSHIBA, TOSHIBA DIGITAL SOLUTIONS CORPORATIONInventors: Toshikazu TAKI, Tsubasa KUSAKA
-
Patent number: 11694451Abstract: According to an embodiment, a reading system includes a reader and a calculator. The reader reads, from a character image, a character that is displayed by a segment display. The calculator performs one of first, second, third, or fourth processing. In the first processing, the calculator calculates a first score based on a state of pixels of the character. In the second processing, the calculator calculates a second score based on a match ratio between the pixels and the extracted pixels. In the third processing, the calculator calculates a third score based on a ratio of a length of the character image in first and second direction. In the fourth processing, the calculator calculates a fourth score based on a comparison result between the detected result and preset patterns. The calculator calculates a certainty of the reading by using one of the first, second, third, or fourth score.Type: GrantFiled: May 21, 2020Date of Patent: July 4, 2023Assignees: KABUSHIKI KAISHA TOSHIBA, TOSHIBA DIGITAL SOLUTIONS CORPORATIONInventors: Toshikazu Taki, Tsubasa Kusaka
-
Publication number: 20230075911Abstract: According to one embodiment, a hand includes a first holding unit, and a second holding unit. The first holding unit includes a plurality of first holding portions capable of holding an article. A plurality of the first holding units is provided in a second direction and is movable independently of each other in a first direction crossing the second direction. The second holding unit is movable in a third direction crossing a plane parallel to the first direction and the second direction. The second holding unit includes a plurality of second holding portions capable of holding the article.Type: ApplicationFiled: September 7, 2022Publication date: March 9, 2023Applicants: KABUSHIKI KAISHA TOSHIBA, TOSHIBA INFRASTRUCTURE SYSTEMS & SOLUTIONS CORPORATIONInventors: Motojiro SHIBATA, Yukihiro IKEYA, Toshikazu TAKI, Chiayu LIN, Takeshi TOYOSHIMA, Hiroaki FUJIHARA, Yusuke MITSUYA
-
Publication number: 20220398824Abstract: According to one embodiment, a reading system includes an extractor, a determiner, and a reader. The extractor extracts a candidate image from an input image. The candidate image is a candidate of a portion of the input image in which a segment display is imaged. The determiner uses the candidate image and a mask to calculate a match ratio indicating a certainty of a segment display being included in the candidate image, and determines that the candidate image is an image of a segment display when the match ratio is not less than a threshold. The mask and the threshold are preset. The reader reads a numerical value displayed in a segment display from the candidate image determined to be an image of a segment display.Type: ApplicationFiled: August 23, 2022Publication date: December 15, 2022Applicant: Kabushiki Kaisha ToshibaInventor: Toshikazu TAKI
-
Publication number: 20220309611Abstract: According to one embodiment, a training device is configured to use a first image to generate a second image. A meter is visible in the first image. The meter includes a pointer and a plurality of graduations. The pointer is relatively rotated with respect to the plurality of graduations in the second image. The training device is further configured to use the second image to train a first model that processes a meter image.Type: ApplicationFiled: March 9, 2022Publication date: September 29, 2022Applicant: KABUSHIKI KAISHA TOSHIBAInventor: Toshikazu TAKI
-
Patent number: 11455787Abstract: According to one embodiment, a reading system includes an extractor, a determiner, and a reader. The extractor extracts a candidate image from an input image. The candidate image is a candidate of a portion of the input image in which a segment display is imaged. The determiner uses the candidate image and a mask to calculate a match ratio indicating a certainty of a segment display being included in the candidate image, and determines that the candidate image is an image of a segment display when the match ratio is not less than a threshold. The mask and the threshold are preset. The reader reads a numerical value displayed in a segment display from the candidate image determined to be an image of a segment display.Type: GrantFiled: July 10, 2020Date of Patent: September 27, 2022Assignee: KABUSHIKI KAISHA TOSHIBAInventor: Toshikazu Taki
-
Publication number: 20220219337Abstract: According to one embodiment, a holding device includes a first holder configured to hold an upper surface of an article, and a second holder configured to hold a side surface of the article. The holding device performs at least a first operation of the first and second holders holding the article, and a second operation of only the first holder holding the article.Type: ApplicationFiled: January 13, 2022Publication date: July 14, 2022Applicants: KABUSHIKI KAISHA TOSHIBA, TOSHIBA INFRASTRUCTURE SYSTEMS & SOLUTIONS CORPORATIONInventors: Motojiro SHIBATA, Yukihiro IKEYA, Takeshi TOYOSHIMA, Toshikazu TAKI, Hiroaki FUJIHARA, Yusuke MITSUYA
-
Publication number: 20220189182Abstract: According to one embodiment, a reading system includes an extractor, a determiner, and a reader. The extractor extracts a candidate image from an input image. The candidate image is of a portion of the input image in which a segment display is imaged. The determiner calculates an angle with respect to a reference line of each of a plurality of straight lines detected from the candidate image, and determines whether or not the candidate image is an image of a segment display based on a distribution indicating a relationship between the angle and a number of the straight lines. The reader reads a numerical value displayed in a segment display from the candidate image determined to be an image of a segment display.Type: ApplicationFiled: March 7, 2022Publication date: June 16, 2022Applicant: KABUSHIKI KAISHA TOSHIBAInventor: Toshikazu TAKI
-
Patent number: 11301709Abstract: According to one embodiment, a reading system includes an extractor, a determiner, and a reader. The extractor extracts a candidate image from an input image. The candidate image is of a portion of the input image in which a segment display is imaged. The determiner calculates an angle with respect to a reference line of each of a plurality of straight lines detected from the candidate image, and determines whether or not the candidate image is an image of a segment display based on a distribution indicating a relationship between the angle and a number of the straight lines. The reader reads a numerical value displayed in a segment display from the candidate image determined to be an image of a segment display.Type: GrantFiled: July 7, 2020Date of Patent: April 12, 2022Assignee: KABUSHIKI KAISHA TOSHIBAInventor: Toshikazu Taki
-
Publication number: 20210192255Abstract: According to one embodiment, a reading system includes a processing device. The processing device includes an extractor, a line thinner, a setter, and an identifier. The extractor extracts a partial image from an input image. A character of a segment display is imaged in the partial image. The segment display includes a plurality of segments. The line thinner thins a cluster of pixels representing a character in the partial image. The setter sets, in the partial image, a plurality of determination regions corresponding respectively to the plurality of segments. The identifier detects a number of pixels included in the thinned cluster for each of the plurality of determination regions, and identifies the character based on a detection result.Type: ApplicationFiled: March 10, 2021Publication date: June 24, 2021Applicant: KABUSHIKI KAISHA TOSHIBAInventors: Toshikazu TAKI, Tsubasa KUSAKA
-
Publication number: 20200380296Abstract: According to an embodiment, a reading system includes a reader and a calculator. The reader reads, from a character image, a character that is displayed by a segment display. The calculator performs one of first, second, third, or fourth processing. In the first processing, the calculator calculates a first score based on a state of pixels of the character. In the second processing, the calculator calculates a second score based on a match ratio between the pixels and the extracted pixels. In the third processing, the calculator calculates a third score based on a ratio of a length of the character image in first and second direction. In the fourth processing, the calculator calculates a fourth score based on a comparison result between the detected result and preset patterns. The calculator calculates a certainty of the reading by using one of the first, second, third, or fourth score.Type: ApplicationFiled: May 21, 2020Publication date: December 3, 2020Applicants: KABUSHIKI KAISHA TOSHIBA, TOSHIBA DIGITAL SOLUTIONS CORPORATIONInventors: Toshikazu TAKI, Tsubasa KUSAKA
-
Publication number: 20200342251Abstract: According to one embodiment, a reading system includes an extractor, a determiner, and a reader. The extractor extracts a candidate image from an input image. The candidate image is a candidate of a portion of the input image in which a segment display is imaged. The determiner uses the candidate image and a mask to calculate a match ratio indicating a certainty of a segment display being included in the candidate image, and determines that the candidate image is an image of a segment display when the match ratio is not less than a threshold. The mask and the threshold are preset. The reader reads a numerical value displayed in a segment display from the candidate image determined to be an image of a segment display.Type: ApplicationFiled: July 10, 2020Publication date: October 29, 2020Applicant: KABUSHIKI KAISHA TOSHIBAInventor: Toshikazu TAKI
-
Publication number: 20200334483Abstract: According to one embodiment, a reading system includes an extractor, a determiner, and a reader. The extractor extracts a candidate image from an input image. The candidate image is of a portion of the input image in which a segment display is imaged. The determiner calculates an angle with respect to a reference line of each of a plurality of straight lines detected from the candidate image, and determines whether or not the candidate image is an image of a segment display based on a distribution indicating a relationship between the angle and a number of the straight lines. The reader reads a numerical value displayed in a segment display from the candidate image determined to be an image of a segment display.Type: ApplicationFiled: July 7, 2020Publication date: October 22, 2020Applicant: KABUSHIKI KAISHA TOSHIBAInventor: Toshikazu TAKI
-
Publication number: 20140259635Abstract: According to one embodiment, an assembly machine of a rotating electrical machine includes: a coil alignment portion that aligns coils, when aligning coils in a ring shape, such that one side of a circumferential direction in the ring is made to lay over a top surface side of an adjacent coil, and the other side of the circumferential direction of the coils is made to lay under a bottom surface side of an adjacent coil so as to form mutually overlapping regions in a thickness direction between the adjacent coils; an insertion part having columnar parts inserted into the interior of the mutually overlapping regions; and a pressing part which inserts the insertion part in an axial direction thereof, mutually overlapping in the thickness direction between the adjacent coils, from the insertion part into the interior of a slot in the core of the rotating electrical machine.Type: ApplicationFiled: September 13, 2013Publication date: September 18, 2014Applicant: Kabushiki Kaisha ToshibaInventors: Toshikazu TAKI, Tomohiro Kita, Yukihiro Ikeya, Mitsuhiro Fujii, Mineaki Iida