Document registration
    2.
    发明授权
    Document registration 有权
    文件注册

    公开(公告)号:US08965134B2

    公开(公告)日:2015-02-24

    申请号:US14110130

    申请日:2011-04-05

    IPC分类号: G06K9/74 G06K9/00 G06K9/62

    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。

    Associating auxiliary data with digital ink
    3.
    发明授权
    Associating auxiliary data with digital ink 有权
    将辅助数据与数字墨水相关联

    公开(公告)号:US08681129B2

    公开(公告)日:2014-03-25

    申请号:US12200942

    申请日:2008-08-29

    IPC分类号: G06F3/033

    摘要: A method of associating auxiliary data with a digital ink stream comprises capturing a sequence of samples representing a digital ink stream and modifying the sample information, or inserting a plurality of new samples into the sample sequence, the modified or new samples representing auxiliary data. New samples are inserted in between existing samples and are essentially imperceptible to a person viewing the digital ink image, while an authorised recipient can extract the auxiliary data.

    摘要翻译: 将辅助数据与数字墨流相关联的方法包括捕获表示数字墨流的样本序列,并修改样本信息,或者将多个新样本插入到样本序列中,所述修改的或新的样本表示辅助数据。 新样本插入到现有样本之间,并且对于观看数字墨水图像的人来说基本上是不可察觉的,而授权的接收者可以提取辅助数据。

    Associating Auxilliary Data With Digital Ink
    4.
    发明申请
    Associating Auxilliary Data With Digital Ink 有权
    将辅助数据与数字墨水相关联

    公开(公告)号:US20090120694A1

    公开(公告)日:2009-05-14

    申请号:US12200942

    申请日:2008-08-29

    IPC分类号: G06F3/041

    摘要: A method of associating auxiliary data with a digital ink stream comprises capturing a sequence of samples representing a digital ink stream and modifying the sample information, or inserting a plurality of new samples into the sample sequence, the modified or new samples representing auxiliary data. New samples are inserted in between existing samples and are essentially imperceptible to a person viewing the digital ink image, while an authorised recipient can extract the auxiliary data.

    摘要翻译: 将辅助数据与数字墨流相关联的方法包括捕获表示数字墨流的样本序列,并修改样本信息,或者将多个新样本插入到样本序列中,所述修改的或新的样本表示辅助数据。 新样本插入到现有样本之间,并且对于观看数字墨水图像的人来说基本上是不可察觉的,而授权的接收者可以提取辅助数据。

    Searching document images
    8.
    发明授权
    Searching document images 有权
    搜索文档图像

    公开(公告)号:US08340429B2

    公开(公告)日:2012-12-25

    申请号:US12953460

    申请日:2010-11-24

    IPC分类号: G06K9/00 G06K9/54

    CPC分类号: G06K9/00852

    摘要: Disclosed is a method of searching a digital image of a document for a predetermined keyword. The method identifies a word in the digital image, the word comprising one or more shapes. A test matrix comprising a difference vector for each character of the word is generated, and a template matrix comprising a difference vector for each shape of the keyword is also generated, wherein a difference vector represents the differences between the visual features of a respective shape and the visual features of a collection of reference shapes. A measure of similarity between the word and the keyword is generated by comparing the test matrix and the template matrix.

    摘要翻译: 公开了一种在预定关键字上搜索文档的数字图像的方法。 该方法识别数字图像中的单词,该单词包括一个或多个形状。 生成包含该单词的每个字符的差分向量的测试矩阵,并且还生成包括关键字的每个形状的差向量的模板矩阵,其中差矢量表示各形状的视觉特征与 参考形状集合的视觉特征。 通过比较测试矩阵和模板矩阵来生成单词和关键字之间的相似度度量。

    Document Registration
    10.
    发明申请
    Document Registration 有权
    文件注册

    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

    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。