公开(公告)号：US20230360440A1

公开(公告)日：2023-11-09

申请号：US17636074

申请日：2021-03-18

Applicant: NEC Corporation ,  The University of Electro-Communications

Inventor： Masatsugu ICHINO ,  Daisuke UENOYAMA ,  Tsubasa BOURA ,  Takahiro TOIZUMI ,  Masato TSUKADA ,  Yuka OGINO

IPC: G06T3/40 ,  G06V10/77 ,  G06V40/18 ,  G06V10/774 ,  G06V10/776

CPC classification number: G06V40/193 ,  G06T3/40 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/776

Abstract: A feature conversion learning device is configured to acquire a first image, reduce the first image to a second image having lower resolution than the first image, enlarge the second image to a third image having the same resolution as the first image, extract a first feature that is a feature of the first image and a second feature, convert the second feature into a third feature, and learn a feature conversion method based on a result of comparing the first feature with the third feature.

公开(公告)号：US20230351729A1

公开(公告)日：2023-11-02

申请号：US17638900

申请日：2021-03-29

Applicant: NEC Corporation

Inventor： Masato TSUKADA ,  Takahiro TOIZUMI ,  Ryuichi AKASHI

IPC: G06V10/774 ,  G06F21/32 ,  G06V40/18 ,  G06V10/776

CPC classification number: G06V10/774 ,  G06F21/32 ,  G06V40/193 ,  G06V40/197 ,  G06V10/776

Abstract: A learning system (10) comprises: a selection unit (110) that selects from images corresponding to a plurality of frames shot at a first frame rate, part of the images, the part including an image taken outside a focus range; an extraction unit (120) that extracts a feature amount from the part of the images; and a learning unit (130) that performs learning for the extraction unit based on the feature amount extracted and correct answer information indicating a correct answer with respect to the feature amount. According to such a learning system, it is possible to execute machine learning assumed that moving images are shot at a low frame rate.

公开(公告)号：US20230156348A1

公开(公告)日：2023-05-18

申请号：US17640520

申请日：2021-01-21

Applicant: NEC Corporation

Inventor： Takahiro TOIZUMI ,  Chisato FUNAYAMA ,  Masato TSUKADA

IPC: H04N23/82 ,  G06T7/00

CPC classification number: H04N23/82 ,  G06T7/0002 ,  G06T2207/10152 ,  G06T2207/30168

Abstract: A parameter optimization system (10) includes: an image sensor (110) having at least one sensing parameter; a parameter setting unit (120) configured to be able to change the sensing parameter; a score calculation unit (130) configured to calculate a score from an image acquired by the image sensor; and a parameter determination unit (140) configured to determine a right parameter value that is a value of the sensing parameter at which the score is relatively high, based on a value of the sensing parameter and the score corresponding to the value of the sensing parameter. According to such a parameter optimization system, the sensing parameter of the image sensor can be set to an appropriate value.

公开(公告)号：US20220358953A1

公开(公告)日：2022-11-10

申请号：US17623316

申请日：2019-07-04

Applicant: NEC Corporation

Inventor： Sakiko MISHIMA ,  Yu KIYOKAWA ,  Takahiro TOIZUMI ,  Kazutoshi SAGI

IPC: G10L25/78 ,  G10L15/06

Abstract: Provided are a sound model generation device and the like that make it possible to more easily generate a sound model capable of distinguishing sound events using a plurality of features. A concatenating unit concatenates a plurality of features of sound signals that are learning data and generates a concatenated feature. A learning unit learns the generated concatenated feature for generating a sound model for distinguishing a sound event from a sound signal.

公开(公告)号：US20220139069A1

公开(公告)日：2022-05-05

申请号：US17435512

申请日：2020-02-10

Applicant: NEC Corporation

Inventor： Takahiro TOIZUMI

IPC: G06V10/771 ,  G06V10/74 ,  G06V10/774 ,  G06N20/00

Abstract: The information processing system according to the present invention includes: a first selection unit for selecting two or more images from a first data set that includes learning data including an image, a label associated with the image, and auxiliary information; a second selection unit for selecting an image from a second data set including learning data different from the learning data included in the first data set, based on positions in a feature space of the two or more images selected by the first selection unit; and a learning unit for learning a model for estimating a label based on the auxiliary information using the learning data included in the first data set and the learning data corresponding to the image selected by the second selection unit.

公开(公告)号：US20210278832A1

公开(公告)日：2021-09-09

申请号：US16314239

申请日：2017-06-28

Applicant: NEC CORPORATION

Inventor： Shigeru KOUMOTO ,  Rie IWASAKI ,  Eisuke SANEYOSHI ,  Akira SHOUJIGUCHI ,  Takahiro TOIZUMI ,  Ryota SUZUKI

IPC: G05B23/02 ,  G05B19/418

Abstract: A maintenance plan formulation device includes: a failure sign detection unit that acquires a state of at least an apparatus and detects an abnormality indicating a sign that appears before a failure of the apparatus occurs; a maintenance limit timing calculation unit that calculates a maintenance limit timing that indicates a limit of a maintenance timing of the apparatus with the abnormality thereof being detected; a maintenance timing calculation unit that calculates a maintenance timing of the apparatus based on the maintenance limit timing of the apparatus; and a maintenance timing output part that outputs the maintenance timing to a display apparatus.

公开(公告)号：US20210224600A1

公开(公告)日：2021-07-22

申请号：US16769135

申请日：2017-12-14

Applicant: NEC CORPORATION

Inventor： Takahiro TOIZUMI ,  Kazutoshi SAGI ,  Yuzo SENDA

IPC: G06K9/62 ,  G06T7/73

Abstract: An identification device according to one embodiment comprises: an acquisition unit that uses an encoder configured to derive, from data in which a single subject under different conditions has been recorded, feature values as a first feature value derived from data in which a subject to be identified has been recorded; a conversion unit that generates a second feature value by carrying out conversion using the conversion parameter on the first feature value; a discrete classification unit that carries out discrete classification on each of a plurality of third feature values including the second feature value and generates a plurality of discrete classification results indicating the results of the classification; a result derivation unit that derives, on the basis of the plurality of discrete classification results, identification result information; and an output unit that outputs the identification result information.

公开(公告)号：US20210073586A1

公开(公告)日：2021-03-11

申请号：US16772057

申请日：2017-12-14

Applicant: NEC Corporation

Inventor： Kazutoshi SAGI ,  Takahiro TOIZUMI ,  Yuzo SENDA

IPC: G06K9/62 ,  G01S13/90

Abstract: Provided is a learning device that can generate a feature deriving device capable of deriving, for an identical object, feature amounts which respectively express a feature of the object in different forms and which are mutually related. This learning device comprises: an acquisition unit that acquires first data and second data, with different forms of the object recorded therein; an encoder that derives a first feature amount from the first data; a conversion unit that converts the first feature amount to a second feature amount; a decoder that generates third data from the second feature amount; and a parameter updating unit that updates, on the basis of a comparison between the second data and the third data, the value of a parameter used in the derivation of the first feature amount, and the value of a parameter used in the generation of the third data.

公开(公告)号：US20210056343A1

公开(公告)日：2021-02-25

申请号：US16955605

申请日：2017-12-22

Applicant: NEC CORPORATION

Inventor： Takahiro TOIZUMI ,  Yuzo SENDA

IPC: G06K9/62 ,  G06K9/46

Abstract: A label feature extraction means 71 extracts, from reference information, a label feature that is a vector representing a feature of the reference information. A label feature dimension reduction means 72 performs dimension reduction of the label feature. An image feature extraction means 73 extracts an image feature from a target image that is an image in which an object to be recognized is captured. A feature transformation means 74 performs feature transformation on the image feature in such a manner that comparison with the label feature after the dimension reduction becomes possible. The class recognition means 75 recognizes a class of the object to be recognized by comparing the image feature after the feature transformation with the label feature after the dimension reduction.

公开(公告)号：US20200058081A1

公开(公告)日：2020-02-20

申请号：US16344881

申请日：2017-10-30

Applicant: NEC Corporation

Inventor： Eisuke SANEYOSHI ,  Shigeru KOUMOTO ,  Akira SHOUJIGUCHI ,  Rie IWASAKI ,  Takahiro TOIZUMI ,  Ryota SUZUKI

IPC: G06Q50/04 ,  G06Q10/00 ,  G06Q10/06 ,  G05B19/406

Abstract: There are provided a repair determination section that determines, based on failure information on the facility for manufacturing a product, a repair time required to repair the facility, and a recovery plan creation section that creates a recovery plan in accordance with a predetermined production evaluation indicator, based on the repair time and production information on a line with the failed facility, one or more other facilities, and on one or more other lines.