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

US5274714A Method and apparatus for determining and organizing feature vectors for neural network recognition 失效
标题翻译：用于确定和组织用于神经网络识别的特征向量的方法和装置
公开(公告)号：US5274714A
公开(公告)日：1993-12-28
申请号：US920188
申请日：1992-07-23
申请人： Timothy L. Hutcheson , Wilson Or , Venkatesh Narayanan , Subramaniam Mohan , Peter G. Wohlmut , Ramanujam Srinivasan , Bobby R. Hunt , Thomas W. Ryan
发明人： Timothy L. Hutcheson , Wilson Or , Venkatesh Narayanan , Subramaniam Mohan , Peter G. Wohlmut , Ramanujam Srinivasan , Bobby R. Hunt , Thomas W. Ryan
IPC分类号： G06K9/00 , G06K9/52 , G06K9/62 , G06K9/66 , G07C9/00 , G06K9/36 , G06K9/46 , G06K9/68
CPC分类号： G06K9/66 , G06K9/00221 , G06K9/00268 , G06K9/522 , G06K9/6217 , G07C9/00071
摘要： A pattern recognition method and apparatus utilizes a neural network to recognize input images which are sufficiently similar to a database of previously stored images. Images are first processed and subjected to a Fourier transform which yields a power spectrum. An in-class to out-of-class study is performed on a typical collection of images in order to determine the most discriminatory regions of the Fourier transform. A feature vector consisting of the (most discriminatory) information from the power spectrum of the Fourier transform of the image is formed. Feature vectors are input to a neural network having preferably two hidden layers, input dimensionality of the number of elements in the feature vector and output dimensionality of the number of data elements stored in the database. Unique identifier numbers are preferably stored along with the feature vector. Application of a query feature vector to the neural network results in an output vector. The output vector is subjected to statistical analysis to determine if a sufficiently high confidence level exists to indicate a successful identification whereupon a unique identifier number may be displayed.
摘要翻译：模式识别方法和装置利用神经网络来识别与先前存储的图像的数据库足够相似的输入图像。首先对图像进行处理，并进行傅里叶变换，从而产生功率谱。为了确定傅里叶变换的最具歧视性的区域，对图像的典型集合执行类外的课外研究。形成由图像的傅立叶变换的功率谱的（最具辨别）信息构成的特征矢量。特征向量被输入到具有优选地两个隐藏层的神经网络，特征向量中的元素数量的输入维数和存储在数据库中的数据元素的数量的输出维数。唯一标识符号优选与特征向量一起存储。将查询特征向量应用于神经网络，得到输出向量。对输出向量进行统计分析以确定是否存在足够高的置信水平以指示成功的标识，从而可以显示唯一的标识符号。

2. 发明授权

US5465308A Pattern recognition system 失效
标题翻译：模式识别系统
公开(公告)号：US5465308A
公开(公告)日：1995-11-07
申请号：US111616
申请日：1993-08-25
申请人： Timothy L. Hutcheson , Wilson Or , Venkatesh Narayanan , Subramaniam Mohan , Peter G. Wohlmut , Ramanujam Srinivasan , Bobby R. Hunt , Thomas W. Ryan
发明人： Timothy L. Hutcheson , Wilson Or , Venkatesh Narayanan , Subramaniam Mohan , Peter G. Wohlmut , Ramanujam Srinivasan , Bobby R. Hunt , Thomas W. Ryan
IPC分类号： G06K9/00 , G06K9/52 , G06K9/62 , G06K9/66 , G07C9/00
CPC分类号： G06K9/66 , G06K9/00221 , G06K9/00268 , G06K9/522 , G06K9/6217 , G07C9/00071
摘要： A method and apparatus under software control for pattern recognition utilizes a neural network implementation to recognize two dimensional input images which are sufficiently similar to a database of previously stored two dimensional images. Images are first image processed and subjected to a Fourier transform which yields a power spectrum. An in-class to out-of-class study is performed on a typical collection of images in order to determine the most discriminatory regions of the Fourier transform. A feature vector consisting of the highest order (most discriminatory) magnitude information from the power spectrum of the Fourier transform of the image is formed. Feature vectors are input to a neural network having preferably two hidden layers, input dimensionality of the number of elements in the feature vector and output dimensionality of the number of data elements stored in the database. Unique identifier numbers are preferably stored along with the feature vector. Application of a query feature vector to the neural network will result in an output vector. The output vector is subjected to statistical analysis to determine if a sufficiently high confidence level exists to indicate that a successful identification has been made. Where a successful identification has occurred, the unique identifier number may be displayed.
摘要翻译：用于模式识别的软件控制下的方法和装置利用神经网络实现来识别与先前存储的二维图像的数据库足够相似的二维输入图像。首先对图像进行图像处理，并进行傅立叶变换，从而产生功率谱。为了确定傅里叶变换的最具歧视性的区域，对图像的典型集合执行类外的课外研究。形成由图像的傅里叶变换的功率谱的最高阶（最具辨别）的幅度信息构成的特征矢量。特征向量被输入到具有优选地两个隐藏层的神经网络，特征向量中的元素数量的输入维数和存储在数据库中的数据元素的数量的输出维数。唯一标识符号优选与特征向量一起存储。将查询特征向量应用于神经网络将导致输出向量。对输出向量进行统计分析以确定是否存在足够高的置信水平以指示已经进行了成功的识别。在发生成功识别的情况下，可以显示唯一标识符号。

3. 发明授权

US5161204A Apparatus for generating a feature matrix based on normalized out-class and in-class variation matrices 失效
标题翻译：用于基于归一化的外部类和类内变化矩阵来生成特征矩阵的装置
公开(公告)号：US5161204A
公开(公告)日：1992-11-03
申请号：US533113
申请日：1990-06-04
申请人： Timothy L. Hutcheson , Wilson Or , Venkatesh Narayanan , Subramaniam Mohan , Peter G. Wohlmut , Ramanujam Srinivasan , Bobby R. Hunt , Thomas W. Ryan
发明人： Timothy L. Hutcheson , Wilson Or , Venkatesh Narayanan , Subramaniam Mohan , Peter G. Wohlmut , Ramanujam Srinivasan , Bobby R. Hunt , Thomas W. Ryan
IPC分类号： G06K9/00 , G06K9/52 , G06K9/62 , G06K9/66 , G07C9/00
CPC分类号： G06K9/00268 , G06K9/00221 , G06K9/522 , G06K9/6217 , G06K9/66 , G07C9/00071
摘要： A method and apparatus under software control for pattern recognition utilizes a neural network implementation to recognize two dimensional input images which are sufficiently similar to a database of previously stored two dimensional images. Images are first image processed and subjected to a Fourier transform which yields a power spectrum. An in-class to out-of-class study is performed on a typical collection of images in order to determine the most discriminatory regions of the Fourier transform. A feature vector consisting of the highest order (most discriminatory) magnitude information from the power spectrum of the Fourier transform of the image is formed. Feature vectors are input to a neural network having preferably two hidden layers, input dimensionality of the number of elements in the feature vector and output dimensionality of the number of data elements stored in the database. Unique identifier numbers are preferably stored along with the feature vector. Application of a query feature vector to the neural network will result in an output vector. The output vector is subjected to statistical analysis to determine if a sufficiently high confidence level exists to indicate that a successful identification has been made. Where a successful identification has occurred, the unique identifier number may be displayed.
摘要翻译：用于模式识别的软件控制下的方法和装置利用神经网络实现来识别与先前存储的二维图像的数据库足够相似的二维输入图像。首先对图像进行图像处理，并进行傅立叶变换，从而产生功率谱。为了确定傅里叶变换的最具歧视性的区域，对图像的典型集合执行类外的课外研究。形成由图像的傅里叶变换的功率谱的最高阶（最具辨别）的幅度信息构成的特征矢量。特征向量被输入到具有优选地两个隐藏层的神经网络，特征向量中的元素数量的输入维数和存储在数据库中的数据元素的数量的输出维数。唯一标识符号优选与特征向量一起存储。将查询特征向量应用于神经网络将导致输出向量。对输出向量进行统计分析以确定是否存在足够高的置信水平以指示已经进行了成功的识别。在发生成功识别的情况下，可以显示唯一标识符号。

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