公开(公告)号：US09349237B2

公开(公告)日：2016-05-24

申请号：US13730743

申请日：2012-12-28

Applicant: Yibin Tian ,  Wei Ming

Inventor： Yibin Tian ,  Wei Ming

IPC: G06K9/00 ,  G07D7/20 ,  G07D7/00 ,  H04N1/40

CPC classification number: G07D7/2058 ,  G07D7/00 ,  G07D7/206

Abstract: A method for authenticating a printed document which carries barcode that encode authentication data, including word bounding boxes for each word in the original document image and data for reconstructing the original image. The printed document is scanned to generate a target document image, which is then segmented into text words. The word bounding boxes of the original and target document images are used to align the target document image. Then, each word in the original document image is compared to corresponding words in the target document image using word difference map and Hausdorff distance between them. Symbols of the original document image are further compared to corresponding symbols in the target document image using feature comparison, symbol difference map and Hausdorff distance comparison, and point matching. These various comparison results can identify alterations in the target document with respect to the original document, which can be visualized.

Abstract translation: 一种用于验证携带条形码的打印文件的方法，该打印文件对原始文档图像中的每个单词和用于重建原始图像的数据进行编码的认证数据，包括字边界框。 扫描打印的文档以生成目标文档图像，然后将其分割成文本字。 使用原始和目标文档图像的边界框对齐目标文档图像。 然后，将原始文档图像中的每个单词与目标文档图像中的相应单词进行比较，使用单词差异图和它们之间的Hausdorff距离。 使用特征比较，符号差异图和Hausdorff距离比较以及点匹配，将原始文档图像的符号进一步与目标文档图像中的对应符号进行比较。 这些各种比较结果可以识别目标文档中关于原始文档的变化，这可以被可视化。

公开(公告)号：US09230383B2

公开(公告)日：2016-01-05

申请号：US13730757

申请日：2012-12-28

Applicant: Yibin Tian ,  Wei Ming

Inventor： Yibin Tian ,  Wei Ming

IPC: G06K9/64 ,  G07D7/20 ,  G07D7/00 ,  G06K9/00 ,  G06K9/34 ,  G06K9/62

CPC classification number: G06T7/11 ,  G06K9/00456 ,  G06K9/00577 ,  G06K9/18 ,  G06K9/342 ,  G06K9/6201 ,  G06K9/6202 ,  G06K9/6255 ,  G06K2209/01 ,  G06T2207/10004 ,  G06T2207/30176 ,  G07D7/004 ,  G07D7/0043 ,  G07D7/20 ,  G07D7/2033 ,  G07D7/2041 ,  G07D7/206 ,  G07D7/2083 ,  H04N1/40062

Abstract: A method for compressing a bi-level document image containing text is disclosed. The document image is segmented into symbol images each representing a letter, numeral, etc. in the document. The symbol images are classified into a plurality of classes, each class being associated with a template image and a class index. Classification is done by comparing each symbol to be classified with template of existing classes, using a number of image features including zoning profiles, side profiles, topology statistics, and low-order image moments. These image features are compared using a tolerance based method to determine whether the symbol matches the template. After classification, certain classes that have few symbols classified into them may be merged with other classes. In addition, the template images of the classes are down-sampled, where the final sizes of the template images are dependent on the likelihood of confusion of the template with other templates.

Abstract translation: 公开了一种用于压缩包含文本的双层文档图像的方法。 文档图像被分割成符号图像，每个表示文档中的字母，数字等。 符号图像被分类为多个类，每个类与模板图像和类索引相关联。 通过使用许多图像特征（包括分区轮廓，侧面轮廓，拓扑统计和低阶图像力矩）将每个要分类的符号与现有类别的模板进行比较来进行分类。 使用基于公差的方法比较这些图像特征以确定符号是否与模板匹配。 分类后，分类为其中几个符号的某些类可能会与其他类合并。 此外，类的模板图像被采样，其中模板图像的最终尺寸取决于模板与其他模板混淆的可能性。

公开(公告)号：US20140185933A1

公开(公告)日：2014-07-03

申请号：US13730757

申请日：2012-12-28

Applicant: Yibin Tian ,  Wei Ming

Inventor： Yibin Tian ,  Wei Ming

IPC: G06K9/62

CPC classification number: G06T7/11 ,  G06K9/00456 ,  G06K9/00577 ,  G06K9/18 ,  G06K9/342 ,  G06K9/6201 ,  G06K9/6202 ,  G06K9/6255 ,  G06K2209/01 ,  G06T2207/10004 ,  G06T2207/30176 ,  G07D7/004 ,  G07D7/0043 ,  G07D7/20 ,  G07D7/2033 ,  G07D7/2041 ,  G07D7/206 ,  G07D7/2083 ,  H04N1/40062

Abstract: A method for compressing a bi-level document image containing text is disclosed. The document image is segmented into symbol images each representing a letter, numeral, etc. in the document. The symbol images are classified into a plurality of classes, each class being associated with a template image and a class index. Classification is done by comparing each symbol to be classified with template of existing classes, using a number of image features including zoning profiles, side profiles, topology statistics, and low-order image moments. These image features are compared using a tolerance based method to determine whether the symbol matches the template. After classification, certain classes that have few symbols classified into them may be merged with other classes. In addition, the template images of the classes are down-sampled, where the final sizes of the template images are dependent on the likelihood of confusion of the template with other templates.

Abstract translation: 公开了一种用于压缩包含文本的双层文档图像的方法。 文档图像被分割成符号图像，每个表示文档中的字母，数字等。 符号图像被分类为多个类，每个类与模板图像和类索引相关联。 通过使用许多图像特征（包括分区轮廓，侧面轮廓，拓扑统计和低阶图像力矩）将每个要分类的符号与现有类别的模板进行比较来进行分类。 使用基于公差的方法比较这些图像特征以确定符号是否与模板匹配。 分类后，分类为其中几个符号的某些类可能会与其他类合并。 此外，类的模板图像被采样，其中模板图像的最终尺寸取决于模板与其他模板混淆的可能性。

公开(公告)号：US20140183854A1

公开(公告)日：2014-07-03

申请号：US13730743

申请日：2012-12-28

Applicant: Yibin Tian ,  Wei Ming

Inventor： Yibin Tian ,  Wei Ming

IPC: B42D15/00

CPC classification number: G07D7/2058 ,  G07D7/00 ,  G07D7/206

Abstract: A method for authenticating a printed document which carries barcode that encode authentication data, including word bounding boxes for each word in the original document image and data for reconstructing the original image. The printed document is scanned to generate a target document image, which is then segmented into text words. The word bounding boxes of the original and target document images are used to align the target document image. Then, each word in the original document image is compared to corresponding words in the target document image using word difference map and Hausdorff distance between them. Symbols of the original document image are further compared to corresponding symbols in the target document image using feature comparison, symbol difference map and Hausdorff distance comparison, and point matching. These various comparison results can identify alterations in the target document with respect to the original document, which can be visualized.

Abstract translation: 一种用于验证携带条形码的打印文件的方法，该打印文件对原始文档图像中的每个单词和用于重建原始图像的数据进行编码的认证数据，包括字边界框。 扫描打印的文档以生成目标文档图像，然后将其分割成文本字。 使用原始和目标文档图像的边界框对齐目标文档图像。 然后，将原始文档图像中的每个单词与目标文档图像中的相应单词进行比较，使用单词差异图和它们之间的Hausdorff距离。 使用特征比较，符号差异图和Hausdorff距离比较以及点匹配，将原始文档图像的符号进一步与目标文档图像中的对应符号进行比较。 这些各种比较结果可以识别目标文档中关于原始文档的变化，这可以被可视化。

公开(公告)号：US08595503B2

公开(公告)日：2013-11-26

申请号：US12165555

申请日：2008-06-30

Applicant: Wei Ming

Inventor： Wei Ming

IPC: G06F21/00

CPC classification number: H04N1/32144 ,  G06T1/0028 ,  G06T2201/0051 ,  G06T2201/0083 ,  H04N1/32283 ,  H04N2201/3235 ,  H04N2201/3236 ,  H04N2201/3269 ,  H04N2201/3283

Abstract: An improved document authentication method in which critical content, such as signatures, is preserved at a high-resolution in the authentication data carried on the self-authenticating document. When generating authentication data, signatures are compressed without down-sampling to preserve their resolution and quality. The compressed signature data (a bit string) is embedded in an image segment on the document. For example, each bit of the bit string is stored in the low bits of one or more image pixels. A hash code is calculated from the bit string and stored in a barcode printed on the document. To authenticate a scanned-back document, the bit string is recovered from the image segment. A hash code is calculated from the recovered bit string and compared to the hash code extracted from the barcode. The signatures re-generated from the recovered bit string are compared to the signatures in the scanned document.

Abstract translation: 一种改进的文档认证方法，其中在自我认证文档上承载的认证数据中以高分辨率保留关键内容（例如签名）。 当生成认证数据时，签名被压缩而不进行下采样，以保持其分辨率和质量。 压缩的签名数据（位串）被嵌入在文档的图像段中。 例如，位串的每个位被存储在一个或多个图像像素的低位中。 哈希码是从比特串中计算的，并存储在打印在文档上的条形码中。 要验证扫描的文档，将从图像片段中恢复位串。 从恢复的位串中计算哈希码，并与从条形码提取的散列码进行比较。 从恢复的位串重新生成的签名与扫描的文档中的签名进行比较。

公开(公告)号：US08544748B2

公开(公告)日：2013-10-01

申请号：US12341966

申请日：2008-12-22

Applicant: Wei Ming

Inventor： Wei Ming

IPC: G06K7/10

CPC classification number: G06K17/00 ,  G06K2017/0064

Abstract: A document authenticating method is disclosed by which a plurality of two-dimensional barcode stamps are generated and printed on a back side of the document forming a color mosaic pattern. Each barcode stamp by itself is a binary barcode, but the plurality of barcode stamps as a whole are printed with different colors and/or color intensities. The barcode stamps collectively encode the content of the document to be used for document authentication.

Abstract translation: 公开了一种文件认证方法，通过该文件认证方法，生成多个二维条形码标记并将其打印在形成彩色马赛克图案的文档的背面。 每个条形码邮票本身是二进制条形码，但是整个的多个条形码邮票印有不同的颜色和/或颜色强度。 条形码标签共同编码要用于文件认证的文档的内容。

公开(公告)号：US07965894B2

公开(公告)日：2011-06-21

申请号：US12495749

申请日：2009-06-30

Applicant: Yibin Tian ,  Wei Ming

Inventor： Yibin Tian ,  Wei Ming

IPC: G06K9/68

CPC classification number: G06K9/00 ,  G06K9/00577 ,  G06T7/254 ,  G06T2207/10008 ,  G06T2207/20224 ,  G06T2207/30176

Abstract: A document alteration detection method compares a target image with an original image using a two-step process. In the first step, the original and target images are divided into connected image components and their centroids are obtained, and the centroids of the image components in the original and target images are compared. Each centroid in the target image that is not in the original image is deemed to represent an addition, and each centroid in the original image that is not in the target image is deemed to represent a deletion. In the second step, sub-images containing the image components corresponding to each pair of matching centroids in the original and target images are compared to detect any alterations.

Abstract translation: 文件变更检测方法使用两步法将目标图像与原始图像进行比较。 在第一步中，将原始图像和目标图像分割为连接的图像分量，并获得它们的质心，并比较原始图像和目标图像中图像分量的质心。 不在原始图像中的目标图像中的每个质心被认为表示相加，并且原始图像中不在目标图像中的每个质心被视为表示删除。 在第二步骤中，比较包含对应于原始图像和目标图像中的每对匹配质心的图像成分的子图像以检测任何改变。

公开(公告)号：US07930627B2

公开(公告)日：2011-04-19

申请号：US11231768

申请日：2005-09-22

Applicant: Wei Ming

Inventor： Wei Ming

IPC: G06F17/22

CPC classification number: G06F17/2211 ,  H04N1/3876

Abstract: The present application relates to an image processing apparatus and a method for matching and combining two documents with at least some overlap area. Layout features are extracted from the two documents and used to determine common layout areas of the first and second documents, where the common layout area has the same layout in the first and the second documents. Text data in the common layout areas of the first and second documents are also detected and used to determine common text data of the first and second documents, where the common text data is the same in the first and the second documents. Feature points are extracted from the common layout areas of the first and second documents based on the common text data and the first and second documents may be combined based on the feature points.

Abstract translation: 本申请涉及一种图像处理装置和用于匹配和组合具有至少一些重叠区域的两个文档的方法。 从两个文档中提取布局特征，并用于确定第一和第二文档的公共布局区域，其中公共布局区域在第一和第二文档中具有相同的布局。 还检测第一和第二文档的公共布局区域中的文本数据，并用于确定第一和第二文档的公共文本数据，其中第一和第二文档中的公共文本数据相同。 基于公共文本数据从第一和第二文档的公共布局区域提取特征点，并且可以基于特征点组合第一和第二文档。

公开(公告)号：US07567729B2

公开(公告)日：2009-07-28

申请号：US11231769

申请日：2005-09-22

Applicant: Wei Ming

Inventor： Wei Ming

IPC: G06K9/36

CPC classification number: G06T3/4038

Abstract: A method and apparatus for matching two images having areas of overlapping text, first image data, and second image data is provided. The method includes dividing the first image data into a plurality of scene segments and dividing the second image data into a plurality of scene segments, finding a text segment among the scene segments of the first image data and second image data, and detecting common text data in the text segments of the first image data and the second image data, the common text data having identical text data in the text segments of the first image data and the second image data. The method further includes extracting feature points from the first image data and the second image data based on the common text data, and combining the first image data and the second image data according to the feature points.

Abstract translation: 提供一种用于匹配具有重叠文本，第一图像数据和第二图像数据的区域的两个图像的方法和装置。 该方法包括将第一图像数据划分成多个场景段，并将第二图像数据划分成多个场景段，在第一图像数据和第二图像数据的场景段中找到文本段，以及检测公共文本数据 在第一图像数据和第二图像数据的文本段中，公共文本数据在第一图像数据和第二图像数据的文本段中具有相同的文本数据。 该方法还包括基于公共文本数据从第一图像数据和第二图像数据提取特征点，以及根据特征点组合第一图像数据和第二图像数据。

公开(公告)号：US20090086290A1

公开(公告)日：2009-04-02

申请号：US11865019

申请日：2007-09-30

Applicant: Wei Ming ,  Hiroshi Tomita

Inventor： Wei Ming ,  Hiroshi Tomita

IPC: H04N1/46

CPC classification number: H04N1/6033

Abstract: A method for compensating for color variations introduced by printer hardware limitations and other factors is described. First, the extent of color variation throughout a printed page is determined. Based on this determination, each page is partitioned into a plurality of image areas. A color profile is generated for each image area. The partition and the multiple color profiles are stored in the printer. In an actual printing process, the page of image to be printed is divided into a plurality of image areas based on the paper size and the stored partition, and the respective stored color profiles for the image areas are retrieved and used to process the digital image for printing.

Abstract translation: 描述了用于补偿由打印机硬件限制和其他因素引起的颜色变化的方法。 首先，确定印刷页面上颜色变化的程度。 基于该确定，将每个页面分割成多个图像区域。 为每个图像区域生成颜色配置文件。 分区和多色配置文件存储在打印机中。 在实际的打印处理中，基于纸张尺寸和存储的分区将要打印的图像的页面分成多个图像区域，并且检索用于图像区域的各个存储的颜色特征，并用于处理数字图像 用于打印。