公开(公告)号：US10068073B2

公开(公告)日：2018-09-04

申请号：US14415324

申请日：2013-07-03

Applicant: NEC Corporation

Inventor： Masato Ishii

IPC: G06F21/00 ,  G06F21/31 ,  G06K9/00

Abstract: Disclosed is a verification device and the like that suppress an erroneous determination upon determining a difference between input patterns based on a similarity to a reference pattern recorded under a specific condition. A verification device 100 includes a similarity calculation unit 6 calculating similarities S 7 between a set of input information x 110 and y 111 indicating features related to input patterns that are objects of verification and a plurality of types of reference information 112 indicating features related to a reference pattern to be a reference of the verification by using the set of input information x 110 and y 111 and the plurality of types of reference information 112. The calculated similarities S7 are presented to an external device or a user.

公开(公告)号：US09836662B2

公开(公告)日：2017-12-05

申请号：US14769532

申请日：2014-02-05

Applicant: NEC Corporation

Inventor： Masato Ishii

IPC: G06K9/00 ,  G05B19/00 ,  G06F21/00 ,  G06F21/32

CPC classification number: G06K9/00892 ,  G06F21/32

Abstract: The purpose of the present invention is to prevent a reduction in authentication accuracy caused by identity fraud. A score calculation unit compares each of a plurality of types of biological information, acquired as acquired biological information from a target person of identity verification, to the same type of registered biological information registered in advance. Based on the comparison, the score calculation unit calculates an authentication score that expresses the degree of similarity between the acquired biological information and the registered information, for each type of acquired biological information. For each type of the acquired biological information, a probability calculation unit calculates as an identity fraud probability using the calculated authentication score to. A determination unit determines whether the target person of identity verification is the registered person, and/or determines whether the target person of identity verification is fraudulently pretending to be the registered person.

公开(公告)号：US11386149B2

公开(公告)日：2022-07-12

申请号：US16129994

申请日：2018-09-13

Applicant: NEC Corporation

Inventor： Masato Ishii

IPC: G06F16/683 ,  G06F16/635 ,  G06K9/62 ,  G06F16/583

Abstract: Provided is a search system which is configured to search for a registered vector being similar to an input vector among a plurality of registered vectors, on the basis of a degree of similarity between an input vector and a registered vector. The search system includes a partial similarity calculation unit that calculates a degree of partial similarity which is the degree of similarity concerning some of one or more dimensions of the input vector and the registered vector, a limit calculation unit that calculates, on the basis of the degree of partial similarity, an upper limit of the degree of similarity that is expected when the degree of similarity is calculated, and a rejection decision unit that decides, on the basis of the upper limit of the degree of similarity, whether or not to reject the registered vector from a candidate for a search result.

公开(公告)号：US11556780B2

公开(公告)日：2023-01-17

申请号：US16477234

申请日：2018-01-17

Applicant: NEC Corporation

Inventor： Masato Ishii

IPC: G06N3/08 ,  G06N3/04

Abstract: A neural network learning device 20 is equipped with: a determination module 22 that determines the size of a local region in learning information 200 which is to be learned by a neural network 21 containing multiple layers, said determination being made for each layer, on the basis of the structure of the neural network 21; and a control module 25 that, on the basis of size of the local region as determined by the determination module 22, extracts the local region from the learning information 200, and performs control such that the learning of the learning information represented by the extracted local region by the neural network 200 is carried out repeatedly while changing the size of the extracted local region, and thus, a reduction in the generalization performance of the neural network can be avoided even when there is little learning data.

公开(公告)号：US11321387B2

公开(公告)日：2022-05-03

申请号：US16129933

申请日：2018-09-13

Applicant: NEC Corporation

Inventor： Masato Ishii

IPC: G06F16/683 ,  G06F16/635 ,  G06K9/62 ,  G06F16/583

Abstract: Provided is a search system which is configured to search for a registered vector being similar to an input vector among a plurality of registered vectors, on the basis of a degree of similarity between an input vector and a registered vector. The search system includes a partial similarity calculation unit that calculates a degree of partial similarity which is the degree of similarity concerning some of one or more dimensions of the input vector and the registered vector, a limit calculation unit that calculates, on the basis of the degree of partial similarity, an upper limit of the degree of similarity that is expected when the degree of similarity is calculated, and a rejection decision unit that decides, on the basis of the upper limit of the degree of similarity, whether or not to reject the registered vector from a candidate for a search result.

公开(公告)号：US11263511B2

公开(公告)日：2022-03-01

申请号：US16078121

申请日：2017-02-14

Applicant: NEC CORPORATION

Inventor： Masato Ishii

IPC: G06N3/02 ,  G06N3/04 ,  G06N3/08

Abstract: A neural network training device according to an exemplary aspect of the present invention includes: a memory that stores a set of instructions; and at least one central processing unit (CPU) configured to execute the set of instructions to: determine a regularization strength for each layer, based on an initialized network; and train a network, based on the initialized network and the determined regularization strength, wherein the at least one CPU is further configured to determine the regularization strength in such a way that a difference between magnitude of a parameter update amount calculated from a loss function and magnitude of a parameter update amount calculated from a regularization term falls within a predetermined range.

公开(公告)号：US20140301634A1

公开(公告)日：2014-10-09

申请号：US14364467

申请日：2012-12-12

Applicant: Masato ISHII ,  Naoki SHIMOSAKA ,  NEC CORPORATION

Inventor： Masato Ishii

IPC: G06K9/62

CPC classification number: G06K9/6215 ,  G06K9/03 ,  G06K9/6255 ,  G10L15/20

Abstract: Provided is a technology which enables further improvement of the accuracy of the determination in the pattern matching processing.A dictionary learning device 1 includes a score calculation unit (score calculation means) 2 and a learning unit (learning means) 3. The score calculation unit 2 calculates a matching score representing a similarity-degree between a sample pattern, which is a sample of a pattern which is likely to be subjected to a pattern matching processing, and a degradation pattern resulting from a degrading processing on the sample pattern. The learning unit 3 learns a quality dictionary based on the calculated matching score and the degradation pattern. The quality dictionary is a dictionary which is used in a processing to evaluate a degradation degree (quality) of a matching target pattern of being pattern of an object on which the pattern matching processing is carried out. Through evaluating the degradation degree (quality) of the matching target pattern by using the generated quality dictionary by the dictionary learning device 1, the result of the evaluation of the matching target pattern becomes a result in view of the pattern matching processing.

Abstract translation: 提供了能够进一步提高模式匹配处理中的确定的精度的技术。 字典学习装置1包括乐谱计算单元（乐谱计算装置）2和学习单元（学习装置）3。乐谱计算单元2计算表示作为样本的样本之间的相似程度的匹配分数 可能进行图案匹配处理的图案，以及由对样本图案的劣化处理而产生的劣化图案。 学习单元3基于计算的匹配分数和退化模式来学习质量词典。 质量字典是用于评价作为进行图案匹配处理的对象的图案的匹配对象图案的劣化度（质量）的处理中使用的字典。 通过使用字典学习装置1的生成的质量词典来评价匹配对象图案的劣化程度（质量），从而考虑了图案匹配处理的结果。

公开(公告)号：US11281686B2

公开(公告)日：2022-03-22

申请号：US15734442

申请日：2018-06-04

Applicant: NEC Corporation

Inventor： Devendra Dhaka ,  Masato Ishii ,  Atsushi Sato

IPC: G06F16/00 ,  G06F16/25 ,  G06F16/2455 ,  G06F16/28 ,  G06F16/21

Abstract: The information processing apparatus (2000) of the example embodiment 1 includes an acquisition unit (2020), a clustering unit (2040), a transformation unit (2060) and modeling unit (2080). Until a predetermined termination condition is determined, the clustering unit (2040) repeatedly preforms: 1) optimizing the posterior parameters for clustering assignment for each data streams; 2) optimizes the posterior parameters for each determined cluster and for each time frame; 3) optimizes the posterior parameters for individual responses for each data stream; 4) optimizes the posterior parameters for latent states, via approximating the observation model through non-conjugate inference. The transformation unit (2060) transforms the latent states into parameters of the observation model, through a transformation function. The modeling unit (2060) generates the model data, which including all the optimized parameters of all the model latent variables, optimized inside the clustering unit (2040).

公开(公告)号：US11003954B2

公开(公告)日：2021-05-11

申请号：US16067702

申请日：2017-01-17

Applicant: NEC CORPORATION

Inventor： Masato Ishii

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04

Abstract: A neural network capturing a minute pattern variation useful for recognition while maintaining robustness against a pattern variation unrelated to recognition is learned. A preprocessing unit performs, on a set of patterns being to be learned and including a specific pattern variation, a plurality of preprocesses causing different degrees of the specific pattern variation. A network structure determination unit determines, for each of the plurality of preprocesses, a network structure of a neural network having robustness according to a degree of the specific pattern variation after the preprocess. A network learning unit learns, for each of the plurality of preprocesses, the neural network with the network structure associated with the preprocess using the set of patterns after the preprocess.

公开(公告)号：US10303717B2

公开(公告)日：2019-05-28

申请号：US15114930

申请日：2015-02-09

Applicant: NEC Corporation

Inventor： Masato Ishii

IPC: G06F17/00 ,  G06F16/683 ,  G06F16/635 ,  G06F17/30 ,  G06K9/62 ,  G06F16/583

Abstract: Provided is a search system which is configured to search for a registered vector being similar to an input vector among a plurality of registered vectors, on the basis of a degree of similarity between an input vector and a registered vector. The search system includes a partial similarity calculation unit that calculates a degree of partial similarity which is the degree of similarity concerning some of one or more dimensions of the input vector and the registered vector, a limit calculation unit that calculates, on the basis of the degree of partial similarity, an upper limit of the degree of similarity that is expected when the degree of similarity is calculated, and a rejection decision unit that decides, on the basis of the upper limit of the degree of similarity, whether or not to reject the registered vector from a candidate for a search result.