-
公开(公告)号:US06591224B1
公开(公告)日:2003-07-08
申请号:US09585211
申请日:2000-06-01
申请人: Brian M. Sullivan , Shi-Ping Hsu
发明人: Brian M. Sullivan , Shi-Ping Hsu
IPC分类号: G06K980
CPC分类号: G06K9/6293 , G06K9/00 , G07C9/00158
摘要: Method and apparatus for providing a standardized measure of accuracy of each biometric device in a biometric identity authentication system having multiple users. A statistical database includes continually updated values of false acceptance rate and false rejection rate for each combination of user, biometric device and biometric device comparison score. False acceptance rate data are accumulated each time a user successfully accesses the system, by comparing the user's currently obtained biometric data with stored templates of all other users of the same device. Each user is treated as an “impostor” with respect to the other users, and the probability of an impostor's obtaining each possible comparison score is computed with accumulated data each time a successful access is made to the system. The statistical database also contains a false rejection rate, accumulated during a test phase, for each combination of user, biometric device and biometric device comparison score.
摘要翻译: 用于在具有多个用户的生物特征身份认证系统中提供每个生物测定装置的精确度的标准化测量的方法和装置。 统计数据库包括用户,生物识别设备和生物特征设备比较分数的每个组合的不断更新的错误接受率和错误拒绝率值。 通过将用户当前获得的生物统计数据与同一设备的所有其他用户的存储模板进行比较,每次用户成功访问系统时都会累积虚假接受率数据。 每个用户被视为相对于其他用户的“冒名顶替者”,并且每次成功访问系统时,利用累积数据计算冒名顶替者获得每个可能的比较分数的概率。 统计数据库还包含针对用户,生物识别装置和生物识别装置比较分数的每个组合在测试阶段期间累积的假拒绝率。
-
2.
公开(公告)号:US06504947B1
公开(公告)日:2003-01-07
申请号:US09291944
申请日:1999-04-15
申请人: Takeo Nozaki , Satoshi Nishii
发明人: Takeo Nozaki , Satoshi Nishii
IPC分类号: G06K980
CPC分类号: G06T7/001 , G06T2207/30148
摘要: A method and an apparatus are presented for correcting corner images of an integrated circuit pattern, for example, in an real image produced by optical scanning and deleting defects from the corner sections. Design data describing rectangular or trapezoidal patterns are expanded in a design data expansion section in multi-level gradations to produce a reference data for each pixel having resolution capability less than the inspection resolution capability. In a reference image forming section, based on the edge position of the real image, the reference data are processed to produce a reference image by rounding off the corner section and the line width while maintaining multi-level gradations. The boundary regions are blended using optical point spread functions obtained from the real image.
摘要翻译: 提出了一种用于校正集成电路图案的角部图像的方法和装置,例如,通过光学扫描产生的实际图像和从拐角部分删除缺陷。 描述矩形或梯形图案的设计数据在多级渐变的设计数据扩展部分中扩展,以产生具有小于检查分辨能力的分辨能力的每个像素的参考数据。 在参考图像形成部分中,基于实际图像的边缘位置,处理参考数据以通过在保持多级灰度的同时舍入角部和线宽来产生参考图像。 使用从真实图像获得的光点扩散函数来混合边界区域。
-
公开(公告)号:US06526167B1
公开(公告)日:2003-02-25
申请号:US09317227
申请日:1999-05-24
申请人: Chisato Numaoka
发明人: Chisato Numaoka
IPC分类号: G06K980
CPC分类号: G06K9/6251 , G06K9/4652 , G06T7/254 , G06T7/73
摘要: An image processing apparatus and method and a provision medium arranged to perform image learning and image recognition in a short time. An image difference detector computes a differential image between an image stored in a frame buffer and an image stored in another frame buffer, and also computes the centroid of the differential image. A information collector forms RGB histogram data and binary data of a peripheral area about the centroid obtained by the image difference detector. A category former formed by a Kohonen network forms a category based on the RGB histogram data and binary data. A category statistic processor performs statistical processing of the categories output from the category former, and outputs a processing result to a learner formed by a recurrent neural network.
摘要翻译: 一种图像处理装置和方法以及用于在短时间内执行图像学习和图像识别的配置介质。 图像差分检测器计算存储在帧缓冲器中的图像与存储在另一帧缓冲器中的图像之间的差分图像,并且还计算差分图像的质心。 信息收集器形成由图像差分检测器获得的关于质心的周边区域的RGB直方图数据和二进制数据。 由Kohonen网络形成的类别前者基于RGB直方图数据和二进制数据形成一个类别。 类别统计处理器执行从类别分类输出的类别的统计处理,并将处理结果输出到由循环神经网络形成的学习者。
-
公开(公告)号:US06249604B1
公开(公告)日:2001-06-19
申请号:US08196028
申请日:1994-02-14
IPC分类号: G06K980
CPC分类号: G06K9/00463
摘要: A method for determining the boundaries of a symbol or word string within an image, including the steps of determining page orientation, isolating symbol strings from adjacent symbol strings, establishing a set of boundaries or references with respect to which measurements about, or further processing of, the symbol string may be made.
摘要翻译: 一种用于确定图像内的符号或字串的边界的方法,包括以下步骤:确定页面取向,将符号串与相邻符号串隔开,建立一组边界或参考文献,关于哪些测量或进一步处理 可以制作符号串。
-
公开(公告)号:US06201886B1
公开(公告)日:2001-03-13
申请号:US08934970
申请日:1997-09-22
申请人: Akihito Nakayama
发明人: Akihito Nakayama
IPC分类号: G06K980
CPC分类号: G06K9/00006
摘要: The present invention provides an image collation device having a simple whole structure which is applied, for example, as a fingerprint collation device. Linear images cut from the one image is stored in a memory means, and the other image is collated with the stored liner images. Thereby the image data of the linear images can be recorded in a memory means having a small capacity.
摘要翻译: 本发明提供了一种具有简单整体结构的图像对比装置,其被应用于例如指纹核对装置。 从一个图像切割的线性图像被存储在存储装置中,并且另一个图像与存储的衬纸图像进行核对。 因此,线性图像的图像数据可以记录在具有小容量的存储装置中。
-
-
-
-