专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08433922B2 System and method of biometric authentication using multiple kinds of templates 失效
标题翻译：使用多种模板的生物认证的系统和方法
公开(公告)号：US08433922B2
公开(公告)日：2013-04-30
申请号：US12873729
申请日：2010-09-01
申请人： Yosuke Kaga , Osamu Takata , Yoshiaki Isobe , Kenta Takahashi , Takao Murakami
发明人： Yosuke Kaga , Osamu Takata , Yoshiaki Isobe , Kenta Takahashi , Takao Murakami
IPC分类号： G06F21/00 , G06K9/00
CPC分类号： G06F21/32 , G06F2221/2117
摘要： In additional enrollment of a template in a biometric authentication system, the template is automatically enrolled on the basis of a plurality of authentication results to assure a user's convenience and security. A post-migration authentication server receives a first template and a second template from a post-migration authentication terminal, performs authentication on the basis of the comparison result between the received first template and the user's preliminarily first enrolled template, and provisionally enrolls the first template and the second template. It repeats the reception, authentication, and provisional enrollment and calculates a match probability from a plurality of comparison results of the provisionally first enrolled templates, determines whether or not to store a second enrolled template on the basis of the match probability, and automatically enrolls the second template in the post-migration authentication server.
摘要翻译：在生物认证系统中额外登记模板时，基于多个认证结果自动注册该模板，以确保用户的便利性和安全性。迁移后认证服务器从迁移后认证终端接收第一模板和第二模板，根据接收到的第一模板与用户的初始登录模板之间的比较结果进行认证，并临时登记第一模板和第二个模板。它重复接收，认证和临时注册，并根据临时第一登记模板的多个比较结果计算匹配概率，基于匹配概率确定是否存储第二登记模板，并自动注册后迁移认证服务器中的第二个模板。

2. 发明申请

US20100011423A1 User identification system and a method thereof 有权
标题翻译：用户识别系统及其方法
公开(公告)号：US20100011423A1
公开(公告)日：2010-01-14
申请号：US12379639
申请日：2009-02-26
申请人： Yoshiaki Isobe , Takao Murakami , Kenta Takahashi
发明人： Yoshiaki Isobe , Takao Murakami , Kenta Takahashi
IPC分类号： H04L9/32 , G06F21/00
CPC分类号： G06F21/32 , G06F21/31 , G07C9/00158
摘要： A service providing system using the biometrics identification without inputting the user ID poses the problem that the consideration of a service is erroneously claimed to the registered user not using the service due to the erroneous identification. According to this invention, the threshold of the value of the degree of similarity for user identification is set strictly for each registered biometrics information of the user in accordance with the declaration of the loss caused by the erroneous identification.
摘要翻译：在不输入用户ID的情况下使用生物特征识别的服务提供系统造成了由于错误识别而使服务错误地要求给注册用户不使用服务的问题。根据本发明，根据由错误识别引起的损失的声明，对用户的每个登记生物特征信息严格地设定用户识别度的相似度值的阈值。

3. 发明授权

US08332916B2 User identification system and a method thereof 有权
标题翻译：用户识别系统及其方法
公开(公告)号：US08332916B2
公开(公告)日：2012-12-11
申请号：US12379639
申请日：2009-02-26
申请人： Yoshiaki Isobe , Takao Murakami , Kenta Takahashi
发明人： Yoshiaki Isobe , Takao Murakami , Kenta Takahashi
IPC分类号： G06F7/04
CPC分类号： G06F21/32 , G06F21/31 , G07C9/00158
摘要： A service providing system using the biometrics identification without inputting the user ID poses the problem that the consideration of a service is erroneously claimed to the registered user not using the service due to the erroneous identification. According to this invention, the threshold of the value of the degree of similarity for user identification is set strictly for each registered biometrics information of the user in accordance with the declaration of the loss caused by the erroneous identification.
摘要翻译：在不输入用户ID的情况下使用生物特征识别的服务提供系统造成了由于错误识别而使服务错误地要求给注册用户不使用服务的问题。根据本发明，根据由错误识别引起的损失的声明，对用户的每个登记生物特征信息严格地设定用户识别度的相似度值的阈值。

4. 发明申请

US20110185176A1 BIOMETRIC AUTHENTICATION METHOD AND SYSTEM 有权
标题翻译：生物识别方法与系统
公开(公告)号：US20110185176A1
公开(公告)日：2011-07-28
申请号：US13057468
申请日：2009-08-21
申请人： Kenta Takahashi , Shinji Hirata , Yoshiaki Isobe
发明人： Kenta Takahashi , Shinji Hirata , Yoshiaki Isobe
IPC分类号： H04L9/32
CPC分类号： H04L63/0861 , G06F21/32 , G06F21/83 , G06F2221/2153 , G06K2009/00953 , G07C9/00158 , G07C9/00166 , G07C2209/12 , H04L9/3231 , H04L2209/043
摘要： At a registration time, a feature data array for registration is generated from biometric information acquired by a client, and a position correction template and a comparison template obtained by converting the feature data array for registration are registered in a server.At an authentication time, a feature data array for authentication is generated from biometric information acquired by the client, and converted feature data for position correction obtained by converting the feature data array for authentication is transmitted to the server. The server detects a position correction amount of the feature data array for authentication relative to the feature data array for registration using the position correction template and the converted feature data for position correction, and transmits the position correction amount to the client. The client corrects the feature data array for authentication using the position correction amount and transmits the converted feature data array for comparison to the server. The server calculates a distance between the comparison template and the converted feature data array for comparison and determines success or failure of the authentication on the basis of the distance.
摘要翻译：在注册时，由客户机获取的生物特征信息生成用于注册的特征数据阵列，并且通过转换用于注册的特征数据阵列获得的位置校正模板和比较模板被登记在服务器中。在认证时刻，由客户端获取的生物特征信息生成用于认证的特征数据阵列，并且将用于认证的特征数据阵列转换获得的用于位置校正的转换特征数据发送到服务器。服务器使用位置校正模板和转换后的位置校正特征数据检测相对于用于登记的特征数据阵列进行认证的特征数据阵列的位置校正量，并将位置校正量发送给客户端。客户端使用位置校正量来校正特征数据阵列进行认证，并将转换的特征数据数组发送到服务器进行比较。服务器计算比较模板和转换的特征数据阵列之间的距离进行比较，并根据距离确定认证的成功或失败。

5. 发明授权

US08412940B2 Biometric authentication method and system 有权
标题翻译：生物识别方法和系统
公开(公告)号：US08412940B2
公开(公告)日：2013-04-02
申请号：US13057468
申请日：2009-08-21
申请人： Kenta Takahashi , Shinji Hirata , Yoshiaki Isobe
发明人： Kenta Takahashi , Shinji Hirata , Yoshiaki Isobe
IPC分类号： H04L29/06
CPC分类号： H04L63/0861 , G06F21/32 , G06F21/83 , G06F2221/2153 , G06K2009/00953 , G07C9/00158 , G07C9/00166 , G07C2209/12 , H04L9/3231 , H04L2209/043
摘要： At registration time, feature data array for registration is generated from biometric information, and position correction template and comparison template. At authentication time, feature data array for authentication is generated from biometric information acquired by the client, and converted feature data for position correction obtained by converting the feature data array for authentication is transmitted to the server. The server detects position correction amount of the feature data array for authentication relative to the feature data array for registration using the position correction template and the converted feature data, and transmits the position correction amount to client. Client corrects the feature data array for authentication and transmits the converted feature data array for comparison to the server. Server calculates a distance between the comparison template and the converted feature data array for comparison and determines success or failure of the authentication on the basis of the distance.
摘要翻译：在注册时，从生物特征信息和位置校正模板和比较模板生成用于注册的特征数据阵列。在验证时，由客户端获取的生物特征信息生成用于认证的特征数据阵列，并将用于认证的特征数据阵列转换获得的用于位置校正的转换特征数据发送到服务器。服务器使用位置校正模板和转换的特征数据来检测用于认证的特征数据阵列的位置校正量，并且将位置校正量发送给客户端。客户端更正特征数据阵列进行认证，并将转换的特征数据数组发送到服务器进行比较。服务器计算比较模板和转换的特征数据数组之间的距离进行比较，并根据距离确定认证的成功或失败。

6. 发明申请

US20130088327A1 TEMPLATE DELIVERY TYPE CANCELABLE BIOMETRIC AUTHENTICATION SYSTEM AND METHOD THEREFOR 审中-公开
标题翻译：模板输送类型可取消生物识别系统及其方法
公开(公告)号：US20130088327A1
公开(公告)日：2013-04-11
申请号：US13587212
申请日：2012-08-16
申请人： Kenta Takahashi , Yoshiaki Isobe
发明人： Kenta Takahashi , Yoshiaki Isobe
IPC分类号： G05B19/00
CPC分类号： G07C9/00158 , G06F21/32 , H04L9/3228 , H04L9/3231
摘要： In a biometric authentication system, a delivery server includes a parameter conversion unit which generates, by converting the parameter, a parameter for delivery, a template conversion unit which generates, by converting the template, a template for delivery, and a delivery unit which delivers the template for delivery and the parameter for delivery to one of the client terminal and an authentication device; the authentication device includes a sensor which obtains biometric information on a registered user, a feature quantity obtaining unit which obtains a feature quantity from the biometric information, and a feature quantity conversion unit which generates, by converting the feature quantity using the parameter for delivery, a converted feature quantity; and the client terminal includes a match determination unit which determines, by comparing the converted feature quantity with the template for delivery, whether or not the converted feature quantity and the template for delivery match.
摘要翻译：在生物体认证系统中，传送服务器包括参数转换单元，该参数转换单元通过转换参数来生成用于传送的参数，模板转换单元，其通过转换模板来生成用于传递的模板，以及递送单元用于传送的模板和用于传送到客户端终端和认证设备之一的参数; 所述认证装置包括获取对登录用户的生物体信息的传感器，从所述生物体信息获取特征量的特征量获取单元，以及特征量变换单元，其通过使用所述传送用参数转换所述特征量，转换的特征量; 并且客户终端包括匹配确定单元，其通过将转换的特征量与用于传递的模板进行比较来确定转换的特征量和用于传送的模板是否匹配。

7. 发明申请

US20120221574A1 HIGH-ACCURACY SIMILARITY SEARCH SYSTEM 审中-公开
标题翻译：高精度相似搜索系统
公开(公告)号：US20120221574A1
公开(公告)日：2012-08-30
申请号：US13369634
申请日：2012-02-09
申请人： Takao Murakami , Kenta Takahashi
发明人： Takao Murakami , Kenta Takahashi
IPC分类号： G06F17/30 , G06F15/18
CPC分类号： G06F16/901 , G06K9/6271
摘要： A pivot is determined from enrolled data by a pivot determination unit, raw data is acquired, features are extracted from the raw data, a score is calculated as one of a distance and a degree of similarity between the features, an index vector is generated by using the score for the pivot, a Δ score is calculated as one of a distance and a degree of similarity between the index vectors, a parameter of each non-pivot including a regression coefficient is trained by using training data, order to select the non-pivots is, by using the Δ score between search data and the non-pivot as well as the regression coefficient, determined in descending order of posterior probability through logistic regression, and a search result is outputted based on the score between the search data and the enrolled data.
摘要翻译：通过枢轴确定单元从注册数据确定枢轴，获取原始数据，从原始数据中提取特征，将得分计算为特征之间的距离和相似度之一，索引向量由使用分数为枢轴，＆Dgr; 计算得分是索引向量之间的距离和相似程度之一，通过使用训练数据训练包括回归系数的每个非关键点的参数，通过使用＆Dgr来选择非枢轴的顺序; 通过逻辑回归以后验概率的降序确定搜索数据与不确定性之间的分数以及回归系数，并且基于搜索数据和登记数据之间的得分输出搜索结果。

8. 发明申请

US20090289760A1 Biometric authentication system, authentication client terminal, and biometric authentication method 有权
标题翻译：生物认证系统，认证客户端，生物认证方法
公开(公告)号：US20090289760A1
公开(公告)日：2009-11-26
申请号：US12379715
申请日：2009-02-27
申请人： Takao Murakami , Kenta Takahashi
发明人： Takao Murakami , Kenta Takahashi
IPC分类号： G05B19/00
CPC分类号： G06K9/6277 , G06K9/00885
摘要： A biometric authentication system, authentication client terminal, and biometric authentication method are provided to reduce an expected value of the number of inputs of biometric data for authentication, while effectively preventing forgery. In a biometric authentication system, prior probabilities of enrolled users un and non-enrolled user u0 are previously set. 1:N matching is performed between feature data of a claimant v and matching feature data. The matching score is calculated for each enrolled user un. A ratio of the likelihood v=un to the likelihood v≠un is calculated for each enrolled user un using the calculated matching scores. Posterior probabilities of the enrolled users un and non-enrolled user u0 are calculated, using the likelihood ratios, and the prior probabilities of both the enrolled users un and the non-enrolled user u0. Then, determination is made by comparing each posterior probability with a first threshold.
摘要翻译：提供生物认证系统，认证客户终端和生物认证方法，以减少用于认证的生物特征数据的输入数量的期望值，同时有效地防止伪造。在生物认证系统中，预先设定了注册用户un和未注册用户u0的先验概率。 1：在索赔人v的特征数据和匹配特征数据之间执行N匹配。为每个注册用户un计算匹配分数。对于每个登记的用户，使用计算出的匹配分数来计算似然率v = un与似然度的比率。使用可能性比率和注册用户un和未注册用户u0的先验概率来计算登记用户un和未注册用户u0的后验概率。然后，通过将每个后验概率与第一阈值进行比较来进行确定。

9. 发明授权

US08437511B2 Biometric authentication system 失效
标题翻译：生物识别系统
公开(公告)号：US08437511B2
公开(公告)日：2013-05-07
申请号：US12874647
申请日：2010-09-02
申请人： Takao Murakami , Kenta Takahashi
发明人： Takao Murakami , Kenta Takahashi
IPC分类号： G06K9/00
CPC分类号： G06K9/6278 , G06K9/00885 , G06K9/68
摘要： A 1:N identification system having high convenience and safety is to be provided. An authentication client includes at least one biometric information input sensor and a feature extraction function. A database includes an enrollee ID and registered templates of biometric information of at least one kind every enrollee and includes a score table. An authentication server includes a prior probability setting function, a 1:N fast matching function for successively matching the feature with the registered templates of the enrollees and discontinuing matching processing when the number of times of matching has exceeded a predetermined threshold, a delta score calculation function for calculating a delta score by using a score obtained by the 1:N fast matching and using the score table, a posterior probability calculation function for calculating posterior probabilities respectively of the enrollees on the basis of the score and the delta score, and an authentication object user identification function.
摘要翻译：提供具有高便利性和安全性的1：N识别系统。验证客户端包括至少一个生物特征信息输入传感器和特征提取功能。数据库包括登记者ID和每个登记者至少一种生物特征信息的登记模板，并且包括得分表。认证服务器包括先验概率设置功能，1：N快速匹配功能，用于在匹配次数超过预定阈值时连续匹配该特征与登记模板的注册模板，并停止匹配处理;增量分数计算用于通过使用通过1：N快速匹配获得的分数并使用分数表来计算增量分数的功能，用于基于分数和三角洲分数来计算登记者的后验概率的后验概率计算函数，以及认证对象用户识别功能。

10. 发明授权

US08340361B2 Biometric authentication system, authentication client terminal, and biometric authentication method 有权
标题翻译：生物认证系统，认证客户端，生物认证方法
公开(公告)号：US08340361B2
公开(公告)日：2012-12-25
申请号：US12379715
申请日：2009-02-27
申请人： Takao Murakami , Kenta Takahashi
发明人： Takao Murakami , Kenta Takahashi
IPC分类号： G06K9/00 , G05B19/00 , G05B13/02 , G06F7/00
CPC分类号： G06K9/6277 , G06K9/00885
摘要： A biometric authentication system, authentication client terminal, and biometric authentication method are provided to reduce an expected value of the number of inputs of biometric data for authentication, while effectively preventing forgery. In a biometric authentication system, prior probabilities of enrolled users un and non-enrolled user u0 are previously set. 1:N matching is performed between feature data of a claimant v and matching feature data. The matching score is calculated for each enrolled user un. A ratio of the likelihood v=un to the likelihood v≠un is calculated for each enrolled user un using the calculated matching scores. Posterior probabilities of the enrolled users un and non-enrolled user u0 are calculated, using the likelihood ratios, and the prior probabilities of both the enrolled users un and the non-enrolled user u0. Then, determination is made by comparing each posterior probability with a first threshold.
摘要翻译：提供生物认证系统，认证客户终端和生物认证方法，以减少用于认证的生物特征数据的输入数量的期望值，同时有效地防止伪造。在生物认证系统中，预先设定了注册用户un和未注册用户u0的先验概率。 1：在索赔人v的特征数据和匹配特征数据之间执行N匹配。为每个注册用户un计算匹配分数。使用计算的匹配分数，对于每个登记的用户un计算似然度v = un与似然v≠un的比率。使用可能性比率和注册用户un和未注册用户u0的先验概率来计算登记用户un和未注册用户u0的后验概率。然后，通过将每个后验概率与第一阈值进行比较来进行确定。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式