公开(公告)号：US11816756B1

公开(公告)日：2023-11-14

申请号：US18134330

申请日：2023-04-13

Applicant: Equity Shift, Inc.

Inventor： Thomas Marshall Gordon, III ,  Gregory Frederick Bush

IPC: G06T1/00 ,  G06F16/93 ,  G06F16/901 ,  H04L9/00

CPC classification number: G06T1/0021 ,  G06F16/9014 ,  G06F16/93 ,  H04L9/50 ,  G06T2201/0062

Abstract: The system is disclosed for visual marking sensitive documents for leak prevention. Each time an action is taken with regard to a document (e.g., creation, viewing, downloading), that action is added to a distributed ledger, essentially creating a unique hash for a new instance of the document. This new hash is visually embedded in the document as a code comprising a plurality of differently shaded pixels, wherein some of the pixels directly encode information regarding the document (e.g., an account that generated the new instance of the document, a date, a time, a unique ID for the document, etc.) and some of the pixels do not encode information. The code is capable of being scanned either digitally or physically on a printed version of the document, such that the immediate source of the document, corresponding to who leaked the document, is able to be discerned.

公开(公告)号：US09928559B2

公开(公告)日：2018-03-27

申请号：US14776912

申请日：2014-03-14

Applicant: SEND ONLY OKED DOCUMENTS (SOOD)

Inventor： Paul Lahmi ,  Patrice Denis ,  Yan Diacono ,  Jean-Marc Ogier

IPC: G06F17/00 ,  G06T1/00

CPC classification number: G06T1/0028 ,  G06T2201/0051 ,  G06T2201/0062 ,  H04N2201/3281 ,  H04N2201/3284

Abstract: A method for watermarking a document containing at least one text portion comprising the following steps: —determining a specific character font comprising, for at least one character, an original graphic and at least one variation, each of the variations being associated with a different value, said character being termed encodable characters; —using the specific character font to encode an item of information in the text portion of the document, by replacing at least one original graphic with a variation, the original graphic and the variation or variations being identified as a single character by a first optical character recognition process referred to as standard OCR and identified as a plurality of characters by a second optical character recognition process referred to as specific OCR that is capable of determining if the represented character is the original graphic or one of the variations of same and, if so, making it possible to determine the variation that is represented, a strict order relationship being defined on the encodable characters in order to establish the order in which the encodable characters are to be processed during the decoding phase.

公开(公告)号：US09497349B2

公开(公告)日：2016-11-15

申请号：US14470499

申请日：2014-08-27

Applicant: MorphoTrust USA, LLC

Inventor： Brian Martin

IPC: G06T1/00 ,  H04N1/32

CPC classification number: G06T1/0085 ,  G06T1/0071 ,  G06T2201/0062 ,  G06T2201/0065 ,  H04N1/32299 ,  H04N1/32304 ,  H04N1/32309 ,  H04N1/32325 ,  H04N1/32352

Abstract: Some implementations may provide a computer-implemented method for validating a digital document, the method including: receiving, at a computing device, the digital document comprising at least two digital watermarks, the digital document issued by a central entity; retrieving a first digital watermark from the digital document, the first digital watermark visually presented at a first time point; retrieving a second digital watermark from the digital document, the second digital watermark visually presented at a second time point, the second digital watermark being different from the first digital watermark and the second time point being different from the first time point; and reading the digital document based on the retrieved first and second digital watermarks.

Abstract translation: 一些实现可以提供用于验证数字文档的计算机实现的方法，所述方法包括：在计算设备处接收包括至少两个数字水印的数字文档，所述数字水印由中央实体发布; 从数字文档中检索第一数字水印，在第一时间点视觉呈现第一数字水印; 从所述数字文档中检索第二数字水印，所述第二数字水印在第二时间点可视地呈现，所述第二数字水印不同于所述第一数字水印，所述第二时间点不同于所述第一时间点; 以及基于检索到的第一和第二数字水印读取数字文档。

公开(公告)号：US20160035060A1

公开(公告)日：2016-02-04

申请号：US14776912

申请日：2014-03-14

Applicant: SEND ONLY OKED DOCUMENTS (SOOD)

Inventor： Paul LAHMI ,  Patrice DENIS ,  Yan DIACONO ,  Jean-Marc OGIER

IPC: G06T1/00

CPC classification number: G06T1/0028 ,  G06T2201/0051 ,  G06T2201/0062 ,  H04N2201/3281 ,  H04N2201/3284

Abstract: A method for watermarking a document containing at least one text portion comprising the following steps: —determining a specific character font comprising, for at least one character, an original graphic and at least one variation, each of the variations being associated with a different value, said character being termed encodable characters; —using the specific character font to encode an item of information in the text portion of the document, by replacing at least one original graphic with a variation, the original graphic and the variation or variations being identified as a single character by a first optical character recognition process referred to as standard OCR and identified as a plurality of characters by a second optical character recognition process referred to as specific OCR that is capable of determining if the represented character is the original graphic or one of the variations of same and, if so, making it possible to determine the variation that is represented, a strict order relationship being defined on the encodable characters in order to establish the order in which the encodable characters are to be processed during the decoding phase.

Abstract translation: 一种用于对包含至少一个文本部分的文档进行水印的方法，包括以下步骤： - 确定特定字符字体，其包括对于至少一个字符的原始图形和至少一个变体，每个变化与不同的值相关联 所述字符被称为可编码字符; - 使用特定字符字体对文档的文本部分中的信息项进行编码，通过用变化替换至少一个原始图形，原始图形和变化或变化被第一光学字符识别为单个字符 识别过程称为标准OCR，并通过被称为特定OCR的第二光学字符识别过程被识别为多个字符，该第二光学字符识别过程能够确定所表示的字符是原始图形还是其中一个变化，如果是 ，使得可以确定所表示的变化，在可编码字符上定义严格的顺序关系，以便建立在解码阶段期间可编码字符被处理的顺序。

公开(公告)号：US20150269703A1

公开(公告)日：2015-09-24

申请号：US14220866

申请日：2014-03-20

Applicant: XEROX CORPORATION

Inventor： EDWARD N. CHAPMAN

IPC: G06T1/00 ,  H04N1/32

CPC classification number: G06T1/0021 ,  B41M3/008 ,  B41M3/10 ,  B41M3/14 ,  B42D25/333 ,  G06T2201/0051 ,  G06T2201/0062 ,  H04N1/32144 ,  H04N1/32208 ,  H04N1/32251 ,  H04N1/32561 ,  H04N2201/3239 ,  H04N2201/3243

Abstract: Methods and systems rasterize a document to produce a bitmap having first pixels of a first color as background uniformly located across a watermark region and second pixels of a second color located in a pattern forming foreground items within the watermark region. The rasterization causes the first pixels to deposit a first marking material (forming the first color) to a first height on the print media, and the rasterization causes the second pixels to deposit a second marking material (forming the second color) to a second height (different from the first height) on the print media. In the printed document, by having the first color be different from the second color and the second height be different from the first height, this causes the relative darkness between the background and the foreground items to reverse when the printed document is viewed from different angles (relative to a light source).

Abstract translation: 方法和系统光栅化文档以产生具有第一颜色的第一像素的位图，作为横跨水印区域均匀定位的背景，以及位于形成水印区域内的前景项目的图案中的第二颜色的第二像素。 光栅化使得第一像素将第一标记材料（形成第一颜色）沉积到打印介质上的第一高度，并且光栅化使得第二像素将第二标记材料（形成第二颜色）沉积到第二高度 （与第一个高度不同）在打印介质上。 在打印文档中，通过使第一颜色与第二颜色不同，第二高度不同于第一高度，这导致当从不同角度观看打印文档时背景与前景项之间的相对暗度反转 （相对于光源）。

公开(公告)号：US20150086068A1

公开(公告)日：2015-03-26

申请号：US14491941

申请日：2014-09-19

Applicant: Patrick F.X. Mulhearn ,  Michelle Mulhearn ,  Michael Shutt

Inventor： Patrick F.X. Mulhearn ,  Michelle Mulhearn ,  Michael Shutt

IPC: G06T1/00

CPC classification number: G06T1/0021 ,  G06T2201/0062 ,  G07D7/12 ,  G07D7/206

Abstract: A method of creating a document whose authenticity can be confirmed comprises printing a character on the document using a combination of a printing medium having a first appearance and a contaminant having a second appearance distinct from the first appearance, and wherein a first portion of the character has the first appearance but not the second appearance, and a second portion of the character has the second appearance; capturing an image containing the character; and storing the image and information relating to the document in a database. A method of authenticating a document comprises capturing an image of the document; identifying a pattern in the document, comparing the pattern to information in a database relating to an original pattern present on an originally printed document, to determine whether the pattern and the original pattern are within a specified level of similarity.

Abstract translation: 一种创建可以确认其真实性的文档的方法包括使用具有第一外观的印刷介质和具有与第一外观不同的第二外观的污染物的组合在文档上打印字符，并且其中字符的第一部分 具有第一外观而不是第二外观，并且该字符的第二部分具有第二外观; 捕获包含字符的图像; 并将图像和与文档相关的信息存储在数据库中。 一种验证文件的方法包括：获取文档的图像; 识别文档中的模式，将模式与在原始打印文档上存在的原始模式相关的数据库中的信息进行比较，以确定模式和原始模式是否在指定的相似程度之内。

公开(公告)号：US08885947B2

公开(公告)日：2014-11-11

申请号：US13820807

申请日：2010-09-06

Applicant: Sergei Startchik

Inventor： Sergei Startchik

IPC: G06K9/48 ,  G06T1/00

CPC classification number: G06K9/48 ,  G06T1/0064 ,  G06T2201/0051 ,  G06T2201/0062

Abstract: Method for marking graphical elements comprising the steps of selecting at least three coherent edge portions (6) of a graphical element (1), wherein the relative orientation of the coherent edge portions (6) is constant and/or smoothly varies along their entire length, the coherent edge portions (6) comprising at least two reference edge portions (66) and one edge portion to mark (67); defining a family of smooth and non-intersecting curves (65), said curves (65) intersecting all of the coherent edge portions (66, 67); shifting the edge portion to mark (67) along the curves (65) relative to the reference edge portions (66); and method for detecting a marking in a graphical element, comprising the steps of locating an encoding area (7) in a digital image of a graphical element (1); retrieving at least two reference edge portions (66) and at least one modified edge portion (68) of the encoding area (7) in the digital image; and determining the relative position of the modified edge portion (68) relative to the reference edge portions (66).

Abstract translation: 用于标记图形元素的方法，包括以下步骤：选择图形元素（1）的至少三个相干边缘部分（6），其中所述相干边缘部分（6）的相对取向是恒定的和/或平滑地沿其整个长度变化 ，所述相干边缘部分（6）包括至少两个参考边缘部分（66）和一个边缘部分以标记（67）; 限定一系列平滑和不相交的曲线（65），所述曲线（65）与所有相干边缘部分（66,67）相交; 沿着曲线（65）相对于参考边缘部分（66）将边缘部分移动到标记（67）; 以及用于检测图形元素中的标记的方法，包括以下步骤：将编码区域（7）定位在图形元素（1）的数字图像中; 在数字图像中检索编码区域（7）的至少两个参考边缘部分（66）和至少一个修改边缘部分（68）; 以及确定所述改进的边缘部分（68）相对于所述参考边缘部分（66）的相对位置。

公开(公告)号：US08842876B2

公开(公告)日：2014-09-23

申请号：US13551278

申请日：2012-07-17

Applicant: Geoffrey B. Rhoads ,  Tony F. Rodriguez ,  Brett A. Bradley

Inventor： Geoffrey B. Rhoads ,  Tony F. Rodriguez ,  Brett A. Bradley

IPC: G06K9/00 ,  G07F7/08 ,  G07D7/12 ,  H04L9/32 ,  G07F7/10 ,  G07F7/12 ,  G06Q20/34 ,  G06K9/46 ,  G06Q20/38 ,  G07D7/20

CPC classification number: G06K9/00456 ,  G06K9/00577 ,  G06K9/4661 ,  G06Q20/347 ,  G06Q20/388 ,  G06T1/005 ,  G06T2201/0062 ,  G06T2201/0065 ,  G07D7/12 ,  G07D7/121 ,  G07D7/2033 ,  G07F7/08 ,  G07F7/0813 ,  G07F7/1008 ,  G07F7/1016 ,  G07F7/125 ,  H04L9/3278 ,  H04L2209/608 ,  H04L2209/805

Abstract: Directional albedo of a particular article, such as an identity card, is measured and stored. When the article is later presented, it can be confirmed to be the same particular article by re-measuring the albedo function, and checking for correspondence against the earlier-stored data. The re-measuring can be performed through us of a handheld optical device, such as a camera-equipped cell phone. The albedo function can serve as random key data in a variety of cryptographic applications. The function can be changed during the life of the article. A variety of other features are also detailed.

Abstract translation: 测量和存储特定物品（例如身份证件）的定向反照率。 当文章稍后呈现时，可以通过重新测量反照率函数和检查与早期存储的数据的对应关系来确认是相同的特定文章。 可以通过我们的手持式光学设备（例如配备有相机的手机）进行重新测量。 反照率功能可以作为各种加密应用程序中的随机密钥数据。 该功能可在文章的使用期限内更改。 还详细介绍了各种其他功能。

公开(公告)号：US20140003649A1

公开(公告)日：2014-01-02

申请号：US13997258

申请日：2011-12-23

Applicant: Gaoyang Wang ,  Wenfa Qi ,  Lidong Wang ,  Bin Yang

Inventor： Gaoyang Wang ,  Wenfa Qi ,  Lidong Wang ,  Bin Yang

IPC: G06T1/00

CPC classification number: G06T1/0021 ,  G06K9/348 ,  G06K2209/01 ,  G06T2201/0051 ,  G06T2201/0062 ,  G06T2201/0083

Abstract: The application provides a method for partitioning a watermark image with western language characters, comprising: partitioning a western language characters image along rows and columns to form a plurality of character image blocks; identifying valid character image blocks from the formed character image blocks; counting sizes of the valid character image blocks to determine if the image corresponds to a document with a large font size or a document with a small font size; dividing words in the image into a plurality of groups, wherein each divided group in the document with large font size has different numbers of words from that with small font size; and dividing equally the divided word groups into multiple portions corresponding to watermark image blocks. The application further provides a device for partitioning a watermark image with western language characters. The operability of watermark embedding process can be ensured through the above technical solution.

Abstract translation: 该应用程序提供了一种用于用西方语言字符分割水印图像的方法，包括：沿着行和列划分西方语言字符图像以形成多个字符图像块; 从形成的字符图像块中识别有效的字符图像块; 计算有效字符图像块的大小，以确定图像是否对应于具有较大字体大小的文档或具有小字体大小的文档; 将图像中的单词划分成多个组，其中具有大字体大小的文档中的每个划分组具有与具有小字体尺寸的单词不同的字数; 并将划分的字组分成相当于水印图像块的多个部分。 该应用还提供了一种用于用西语字符分割水印图像的设备。 通过上述技术方案可以确保水印嵌入过程的可操作性。

公开(公告)号：US08538068B2

公开(公告)日：2013-09-17

申请号：US13629599

申请日：2012-09-27

Applicant: Donglin Wang ,  Shutian Yin ,  Yunming Zhang ,  Ningsheng Liu ,  Yuansong Liang ,  Changwei Liu ,  Peng Gao ,  Yongzhi Lou ,  De Ouyang

Inventor： Donglin Wang ,  Shutian Yin ,  Yunming Zhang ,  Ningsheng Liu ,  Yuansong Liang ,  Changwei Liu ,  Peng Gao ,  Yongzhi Lou ,  De Ouyang

IPC: G06K9/00

CPC classification number: G06T1/0064 ,  G06T2201/0062 ,  H04N1/32203 ,  H04N1/32219 ,  H04N1/32229 ,  H04N1/32288 ,  H04N1/32299 ,  H04N1/32336 ,  H04N2201/3283 ,  H04N2201/3284

Abstract: A novel method is disclosed for detecting hidden information in a document comprising characters, including: determining layout transformation for each character in the document for detection compared with the original document; obtaining a code sequence embedded in the document for detection based on the layout transformation of each character in the document for detection and the predetermined embedding rule; decoding the code sequence to get the hidden information embedded in the document for detection.

Abstract translation: 公开了一种用于检测包括字符的文档中的隐藏信息的新颖方法，包括：与原始文档相比，确定用于检测的文档中的每个字符的布局变换; 基于用于检测的文档中的每个字符的布局变换和预定的嵌入规则，获得嵌入文档中用于检测的代码序列; 对代码序列进行解码以获取嵌入文档中的隐藏信息进行检测。