-
公开(公告)号:US08965134B2
公开(公告)日:2015-02-24
申请号:US14110130
申请日:2011-04-05
CPC分类号: G06K9/00456 , G06K9/00483 , G06K9/6211
摘要: A method of registering a document comprises, with a processor (150), defining (block 505) a plurality of clusters in an image of a template document (300) by assigning each of a number of feature points of an image of a template document to a cluster with the closest mean, with the processor (150), refining (block 510) a correspondence set of the feature points between the image of the template document (300) and the image of the target document (400) using a histogram of Euclidian distances, and with the processor (150), eliminating (block 515) outliers within a correspondence set of the feature points between the image of the template document (300) and an image of a target document (400) by generating a hypothesis and evaluating the hypothesis a number of iterations, in which the image of the target document (400) is captured by an imaging device (110) from a physical document.
摘要翻译: 一种注册文档的方法包括通过分配模板文档的图像的多个特征点中的每一个来定义(框505)模板文档(300)的图像中的多个聚类的处理器(150) 使用处理器(150),使用直方图来精简(框510)模板文档(300)的图像与目标文档(400)的图像之间的特征点的对应集合 以及处理器(150),通过生成假设来消除模板文档(300)的图像与目标文档(400)的图像之间的特征点的对应集合内的异常值(框515) 以及评估所述假设,其中所述目标文档(400)的图像由物理文档由成像设备(110)捕获的迭代次数。
-
公开(公告)号:US20140029857A1
公开(公告)日:2014-01-30
申请号:US14110130
申请日:2011-04-05
IPC分类号: G06K9/00
CPC分类号: G06K9/00456 , G06K9/00483 , G06K9/6211
摘要: A method of registering a document comprises, with a processor (150), defining (block 505) a plurality of clusters in an image of a template document (300) by assigning each of a number of feature points of an image of a template document to a cluster with the closest mean, with the processor (150), refining (block 510) a correspondence set of the feature points between the image of the template document (300) and the image of the target document (400) using a histogram of Euclidian distances, and with the processor (150), eliminating (block 515) outliers within a correspondence set of the feature points between the image of the template document (300) and an image of a target document (400) by generating a hypothesis and evaluating the hypothesis a number of iterations, in which the image of the target document (400) is captured by an imaging device (110) from a physical document.
摘要翻译: 一种注册文档的方法包括通过分配模板文档的图像的多个特征点中的每一个来定义(框505)模板文档(300)的图像中的多个聚类的处理器(150) 使用处理器(150),使用直方图来精简(框510)模板文档(300)的图像与目标文档(400)的图像之间的特征点的对应集合 以及处理器(150),通过生成假设来消除模板文档(300)的图像与目标文档(400)的图像之间的特征点的对应集合内的异常值(框515) 以及评估所述假设,其中所述目标文档(400)的图像由物理文档由成像设备(110)捕获的迭代次数。
-