Patents by Inventor Masafumi Takimoto
Masafumi Takimoto 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: 11521099Abstract: Embodiments of the present invention are directed to learning of an appropriate dictionary which has a high expression ability of minority data while preventing reduction of an expression ability of majority data. A dictionary generation apparatus which generates a dictionary used for discriminating whether data to be discriminated belongs to a specific category includes a generation unit configured to generate a first dictionary based on learning data belonging to the specific category and a selection unit configured to estimate a degree of matching of the learning data at each portion with the first dictionary using the generated first dictionary and select a portion of the learning data based on the estimated degree of matching, wherein the generation unit generates a second dictionary based on the selected portion of the learning data.Type: GrantFiled: January 12, 2018Date of Patent: December 6, 2022Assignee: Canon Kabushiki KaishaInventors: Zhuolin Liang, Yusuke Mitarai, Masafumi Takimoto, Masakazu Matsugu
-
Patent number: 11455489Abstract: An image processing device includes: a determination unit configured to determine, based on a feature amount of input image data, a category of the input image data and a score representing confidence of the category, with a classification model; a display unit configured to display an image representing the input image data and the determined category of the input image data; an acceptance unit configured to accept a correction of the displayed category from a user; and an updating unit configured to update the classification model, based on the correction of the category.Type: GrantFiled: June 7, 2019Date of Patent: September 27, 2022Assignee: Canon Kabushiki KaishaInventors: Tomotaka Fujimori, Yusuke Mitarai, Masafumi Takimoto
-
Publication number: 20220129675Abstract: An information processing apparatus comprises a first selection unit configured to select, as at least one candidate learning model, at least one learning model from a plurality of learning models learned under learning environments different from each other based on information concerning image capturing of an object, a second selection unit configured to select at least one candidate learning model from the at least one candidate learning model based on a result of object detection processing by the at least one candidate learning model selected by the first selection unit, and a detection unit configured to perform the object detection processing for a captured image of the object using at least one candidate learning model of the at least one candidate learning model selected by the second selection unit.Type: ApplicationFiled: October 25, 2021Publication date: April 28, 2022Inventors: Masafumi Takimoto, Tatsuya Yamamoto, Eita Ono, Satoru Mamiya, Shigeki Hirooka
-
Patent number: 11182423Abstract: An information presentation apparatus obtains monitoring information that indicates a state of a monitoring target, accumulates it in a storage unit, and detects, based on the monitoring information accumulated in the storage unit, the occurrence of an information presentation trigger event. The information presentation apparatus generates, based on the monitoring information accumulated in the storage unit, search data for searching for relevant information related to the detected event, uses the generated the search data to search for the relevant information, and generates presentation information for present the relevant information found by the searching.Type: GrantFiled: November 21, 2016Date of Patent: November 23, 2021Assignee: Canon Kabushiki KaishaInventors: Yusuke Mitarai, Masakazu Matsugu, Atsushi Nogami, Masafumi Takimoto, Tomotaka Fujimori
-
Patent number: 10891508Abstract: This invention makes it possible to properly detect a detection object region in an image. For this purpose, an image processing apparatus according to this invention includes an image input unit configured to input an object image and a reference image different in pixel value component type from the object image, a detection unit configured to detect a detection object candidate region from the object image, an extraction unit configured to extract at least one feature amount from the detection object candidate region by using at least the reference image, and a selection unit configured to select the detection object candidate region based on the feature amount.Type: GrantFiled: September 24, 2018Date of Patent: January 12, 2021Assignee: CANON KABUSHIKI KAISHAInventors: Tomotaka Fujimori, Yusuke Mitarai, Masafumi Takimoto, Hiroshi Okuda
-
Patent number: 10657281Abstract: An information processing apparatus includes level setting unit configured to set a disclosure level of learning data used when a discriminator is generated, first specifying unit configured to specify, in accordance with the disclosure level, disclosure data to be disclosed to administrators other than a first administrator who manages the learning data in the learning data and association data which is associated with the learning data, second specifying unit configured to specify, in accordance with the disclosure level, reference data which is referred to by the first administrator in the learning data and the association data of the other administrators which are registered in a common storage apparatus, obtaining unit configured to obtain the reference data specified by the second specifying unit from the common storage apparatus, and generating unit configured to generate a discriminator using data obtained by the obtaining unit.Type: GrantFiled: August 9, 2018Date of Patent: May 19, 2020Assignee: Canon Kabushiki KaishaInventor: Masafumi Takimoto
-
Patent number: 10607121Abstract: Before dimension reduction is performed while local data distribution is stored as neighborhood data, a distance between data to be subjected to the dimension reduction is calculated, and a parameter (a neighborhood number of the k-nearest neighbor algorithm or a size of a hypersphere) which determines the neighborhood data is determined for each data to be subjected to the dimension reduction. Thereafter, the dimension reduction is performed on the target data based on the determined parameter.Type: GrantFiled: October 16, 2017Date of Patent: March 31, 2020Assignee: CANON KABUSHIKI KAISHAInventor: Masafumi Takimoto
-
Publication number: 20190385016Abstract: An image processing device includes: a determination unit configured to determine, based on a feature amount of input image data, a category of the input image data and a score representing confidence of the category, with a classification model; a display unit configured to display an image representing the input image data and the determined category of the input image data; an acceptance unit configured to accept a correction of the displayed category from a user; and an updating unit configured to update the classification model, based on the correction of the category.Type: ApplicationFiled: June 7, 2019Publication date: December 19, 2019Inventors: Tomotaka Fujimori, Yusuke Mitarai, Masafumi Takimoto
-
Patent number: 10311559Abstract: To present a determination result with respect to input data and also a reason of the determination result to a user, an extraction unit configured to extract a plurality of feature amounts from an image including an inspection target object, a determination unit configured to determine an anomaly degree of the inspection target object on the basis of the extracted feature amounts, and an image generation unit configured to generate a defect display image representing a defect included in the inspection target object on the basis of contribution degrees of the respective feature amounts with respect to the determined anomaly degree are provided.Type: GrantFiled: December 3, 2015Date of Patent: June 4, 2019Assignee: Canon Kabushiki KaishaInventors: Masafumi Takimoto, Yusuke Mitarai, Katsuhiko Mori, Tomotaka Fujimori
-
Patent number: 10262233Abstract: The presence of possibility of occurrence of an excessive adaptation due to use of only learned training data is detected during a learning stage. The user is urged to add data and other information, thereby avoiding the excessive adaptation. For this purpose, the invention has: an inputting unit for inputting a learning image; a generating unit for generating a discrimination model used to decide whether or not a target is normal on the basis of the learning image; a deciding unit for deciding whether or not the number of input learning images is insufficient when the discrimination model is generated; and a notifying unit for notifying a message for urging the user to add the learning image when it is decided that the number of input learning images is insufficient.Type: GrantFiled: January 12, 2016Date of Patent: April 16, 2019Assignee: CANON KABUSHIKI KAISHAInventor: Masafumi Takimoto
-
Publication number: 20190095742Abstract: This invention makes it possible to properly detect a detection object region in an image. For this purpose, an image processing apparatus according to this invention includes an image input unit configured to input an object image and a reference image different in pixel value component type from the object image, a detection unit configured to detect a detection object candidate region from the object image, an extraction unit configured to extract at least one feature amount from the detection object candidate region by using at least the reference image, and a selection unit configured to select the detection object candidate region based on the feature amount.Type: ApplicationFiled: September 24, 2018Publication date: March 28, 2019Inventors: Tomotaka Fujimori, Yusuke Mitarai, Masafumi Takimoto, Hiroshi Okuda
-
Publication number: 20180373738Abstract: An information presentation apparatus obtains monitoring information that indicates a state of a monitoring target, accumulates it in a storage unit, and detects, based on the monitoring information accumulated in the storage unit, the occurrence of an information presentation trigger event. The information presentation apparatus generates, based on the monitoring information accumulated in the storage unit, search data for searching for relevant information related to the detected event, uses the generated the search data to search for the relevant information, and generates presentation information for present the relevant information found by the searching.Type: ApplicationFiled: November 21, 2016Publication date: December 27, 2018Inventors: Yusuke Mitarai, Masakazu Matsugu, Atsushi Nogami, Masafumi Takimoto, Tomotaka Fujimori
-
Patent number: 10156471Abstract: A combination scale is provided that includes a combinatorial computation unit and two operation modes; a normal operation mode, and a corrective operation mode in which correction values are decided. The correction values are for use in correcting errors of measured weight values calculated from weight signals of weight sensors. In the normal operation mode, the combinatorial computation unit corrects the measured weight values using the correction values decided in the corrective operation mode. Then, the combinatorial computation unit executes combinatorial computations based on the corrected measured weight values.Type: GrantFiled: December 17, 2015Date of Patent: December 18, 2018Assignee: YAMATO SCALE Co., Ltd.Inventors: Takayuki Nagai, Masafumi Takimoto
-
Patent number: 10151624Abstract: A virtual weight value is set, and a dummy run mode is set and activated. Then, a zero point, reference value used to calculate the weight value of articles to be weighed in each weighing hopper, is corrected based on the virtual weight value. This enables a dummy run of a combination scale to be performed with the actually empty weighing hopper being assumed to contain the articles equivalent to the virtual weight value.Type: GrantFiled: December 9, 2015Date of Patent: December 11, 2018Assignee: Yamamoto Scale Co., Ltd.Inventors: Takayuki Nagai, Masafumi Takimoto
-
Publication number: 20180349633Abstract: An information processing apparatus includes level setting unit configured to set a disclosure level of learning data used when a discriminator is generated, first specifying unit configured to specify, in accordance with the disclosure level, disclosure data to be disclosed to administrators other than a first administrator who manages the learning data in the learning data and association data which is associated with the learning data, second specifying unit configured to specify, in accordance with the disclosure level, reference data which is referred to by the first administrator in the learning data and the association data of the other administrators which are registered in a common storage apparatus, obtaining unit configured to obtain the reference data specified by the second specifying unit from the common storage apparatus, and generating unit configured to generate a discriminator using data obtained by the obtaining unit.Type: ApplicationFiled: August 9, 2018Publication date: December 6, 2018Inventor: Masafumi Takimoto
-
Publication number: 20180274970Abstract: A combination scale is provided that includes a combinatorial computation unit and two operation modes; a normal operation mode, and a corrective operation mode in which correction values are decided. The correction values are for use in correcting errors of measured weight values calculated from weight signals of weight sensors. In the normal operation mode, the combinatorial computation unit corrects the measured weight values using the correction values decided in the corrective operation mode. Then, the combinatorial computation unit executes combinatorial computations based on the corrected measured weight values.Type: ApplicationFiled: December 15, 2015Publication date: September 27, 2018Inventors: Takayuki NAGAI, Masafumi TAKIMOTO
-
Publication number: 20180274969Abstract: A virtual weight value is set, and a dummy run mode is set and activated. Then, a zero point, reference value used to calculate the weight value of articles to be weighed in each weighing hopper, is corrected based on the virtual weight value. This enables a dummy run of a combination scale to be performed with the actually empty weighing hopper being assumed to contain the articles equivalent to the virtual weight value.Type: ApplicationFiled: December 9, 2015Publication date: September 27, 2018Inventors: Takayuki NAGAI, Masafumi TAKIMOTO
-
Patent number: 10071710Abstract: The swing member (63) to be subjected to swinging drive is integrally provided to the output shaft (56) outside the speed reducer case (52), the speed reducer case (52) is provided with a pair of swing regulating portions (61, 62) which prevents the swing member (63) from being moved beyond the wiping-allowable limit angle (b°) by contacting the swing member (63). As a result, the swing member (63) and the swing regulating portions (61, 62) can collectively form the regulating member (60). As a result, essential components (such as fixing plate) can be omitted from the conventional wiper apparatus. Therefore, the wiper apparatus can be improved in assembly workability, size and weight by reducing the number of components thereof, and provided with a regulating member (60) which prevents the wiper member being moved beyond the wiping-allowable limit angle (b°).Type: GrantFiled: December 25, 2014Date of Patent: September 11, 2018Assignee: Mitsuba CorporationInventors: Masafumi Takimoto, Shin Akimoto, Masaaki Kimura, Takeshi Kanai, Tomoya Nishikawa, Yukiyoshi Iso
-
Publication number: 20180246846Abstract: A technique for displaying information appropriate for causing a highly-precise classifier to learn through processing of causing a classifier to learn interactively with a user. An information processing apparatus includes a class determination unit configured to determine a class to which learning data belongs, based on feature amount of the learning data, a reliability determination unit configured to determine reliability with respect to the class determined by the class determination unit, and a display processing unit configured to display images indicating learning data on a display unit at positions corresponding to the class and the reliability.Type: ApplicationFiled: February 23, 2018Publication date: August 30, 2018Inventor: Masafumi Takimoto
-
Publication number: 20180204132Abstract: Embodiments of the present invention are directed to learning of an appropriate dictionary which has a high expression ability of minority data while preventing reduction of an expression ability of majority data. A dictionary generation apparatus which generates a dictionary used for discriminating whether data to be discriminated belongs to a specific category includes a generation unit configured to generate a first dictionary based on learning data belonging to the specific category and a selection unit configured to estimate a degree of matching of the learning data at each portion with the first dictionary using the generated first dictionary and select a portion of the learning data based on the estimated degree of matching, wherein the generation unit generates a second dictionary based on the selected portion of the learning data.Type: ApplicationFiled: January 12, 2018Publication date: July 19, 2018Inventors: Zhuolin Liang, Yusuke Mitarai, Masafumi Takimoto, Masakazu Matsugu