WO2007040380A1 - Method of generating a printed signature in order to secure the contents of text documents - Google Patents

Method of generating a printed signature in order to secure the contents of text documents Download PDF

Info

Publication number
WO2007040380A1
WO2007040380A1 PCT/MX2005/000089 MX2005000089W WO2007040380A1 WO 2007040380 A1 WO2007040380 A1 WO 2007040380A1 MX 2005000089 W MX2005000089 W MX 2005000089W WO 2007040380 A1 WO2007040380 A1 WO 2007040380A1
Authority
WO
WIPO (PCT)
Prior art keywords
signature
document
method
word
printed
Prior art date
Application number
PCT/MX2005/000089
Other languages
Spanish (es)
French (fr)
Inventor
Sergio Antonio Fernandez Orozco
Leo Hendrik Reyes Lozano
Original Assignee
Fernandez Orozco Sergio Antoni
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fernandez Orozco Sergio Antoni filed Critical Fernandez Orozco Sergio Antoni
Priority to PCT/MX2005/000089 priority Critical patent/WO2007040380A1/en
Publication of WO2007040380A1 publication Critical patent/WO2007040380A1/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00852Recognising whole cursive words
    • G06K9/00859Recognising whole cursive words using word shape
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N1/00Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
    • H04N1/32Circuits or arrangements for control or supervision between transmitter and receiver or between image input and image output device
    • H04N1/32101Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N2201/00Indexing scheme relating to scanning, transmission or reproduction of documents or the like, and to details thereof
    • H04N2201/32Circuits or arrangements for control or supervision between transmitter and receiver or between image input and image output device
    • H04N2201/3201Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title
    • H04N2201/3225Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title of data relating to an image, a page or a document
    • H04N2201/3233Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title of data relating to an image, a page or a document of authentication information, e.g. digital signature, watermark
    • H04N2201/3236Details of authentication information generation

Abstract

The invention relates to a method of generating secure documents. The invention is characterised by the way in which the signatures used to secure the documents are generated. Said signatures are formed from the text content of a printed document without requiring an electronic transcription of the text. The inventive method is based on automatically recognising the form of the words and locating the positions at which the words are repeated, without necessarily knowing the significance of same. In this way, the document can be copied or modified using any means without altering the original message contained in the document. Finally, the method can be used to secure documents printed with normal paper.

Description

A method for generating a printed signature TO ENSURE

CONTENT text documents.

TECHNICAL FIELD OF THE INVENTION This invention relates to the area of ​​security and integrity of the contents of hard copy text documents. The object of this invention is to protect the content of documents printed on plain paper from malicious changes and forgeries; however, the document allows slight alterations that do not change the message written on it. a system and method that can generate a signature that can be attached in print a text document to ensure that the content thereof has not been maliciously modified described. Furthermore, a system and method to verify if a document signed by the above procedure has been modified is described. The main features of these methods is that they require the use of special materials or technologies (such as laser, holograms or plastics); the original document does not have to be digital; the signed document can be copied without losing the properties of the firm; the signature is clearly visible; not optical character recognition is needed (as in OCR); and only the part containing text can be protected.

BACKGROUND OF THE INVENTION

Currently, there are many ways to protect electronic documents against malicious modifications. However, there are relatively few strides to protect physical documents. Among the protections available to the latter are the watermarks, the use of barcodes, special papers, holograms and printed signatures or digital water marks.

Any document required to be sure that your content has not been modified will benefit from the technology set forth herein. Examples of such documents are bank checks, deeds, wills, notarized documents, passports, etc. A brief summary of prior art related to the present invention is presented.

In US 4,835,028, US 6,414,761 and US 4,630,845 patents techniques that require the use of special papers or adding difficult optical or magnetic elements play (holograms or magnetic tapes, respectively) to ensure the authenticity and integrity of a document are described. This type of protection has the disadvantage of requiring special materials. The present invention works with any type of paper and still maintains the same level of protection. US patent 6,496,933 in a method that produces a mark in the form of image that can be added to a document to ensure authenticity described. However, the main disadvantage of this invention with respect to the presented here is required that the document is originally in an electronic format; whereas the invention described here can work with printed documents. In US 6,764,000 a system using a scanner to identify points of interest or indicia (such as watermarks, holograms, serial numbers, patterns, colors, etc.) present in the document to ensure described. These indications are compared with a database previously constructed. If enough signs are similar to those stored, the document is classified as authentic. Unlike that method, the present invention does not require the use of a database to authenticate the document. Furthermore, the invention generates a signature from the content or message written on the original document. In US 6,934,845 an invention that uses an encoding based on the blanks of a paper to hide a signature that authenticates the document described. This invention requires that a document in electronic form is used to generate the signature, and the signature is not generated with the content of the document. In contrast, the present invention differs from that in which does not require electronic document and the document content used to generate the authentication information. The invention also uses a coding based on blanks and is clearly visible. US patent 6,427,921 in a method and system that uses various types of overlapping patterns with the original image that is desired to ensure to produce a watermark described. Unlike this method and system, the present invention uses the contents of the document to generate the signature that will authenticate. Patent hkl 028 662 describes a method to ensure printed documents requires the use of a laser to illuminate the questionable document and then check the reflected pattern meet certain requirements. The present invention does not require laser technology. US 6,785,405 discloses a system that uses digital images of printed documents to verify their authenticity. The system performs the image segmentation and then compares these segments with images in a database obtaining a correlation number for each document type and segment. This phase serves to categorize the document. With this information, authentication information read the same document should have, and this information is used to verify that the document is original. Unlike this system, the present invention does not require segmentation or correlation is used. Also it does not require the use of a database of known images of documents.

US 3,069,654 patent "Method and Means for Recognizing Complex Patterns" describes a method for detecting shapes in images. However, this method can not be used by itself to protect the contents of text documents. The Safe Paper HP technology uses a watermark that is visible only when a plastic card on the signed document is placed. This watermark can be printed on any document using standard printers and inks. This watermark can not be reproduced by normal means, so that the documents can not be copied. Unlike this system, the invention presented herein are not using watermarks or require the use of special plastics to verify document integrity. Furthermore, the invention allows multiple copies of a document always Nagan as the content of the document is not altered. This allows documents generated with this system can be sent by electronic or electromechanical means (such as a facsimile). In a similar name, AIP technology SafePaper Vision uses a watermark that is invisible to secure a document. Unlike the HP technology, this watermark can be read with a scanner; but it disappears when copied or reproduced by other means. On the other hand, this system can only sign electronic documents. The present invention allows the copying of documents provided the content remains intact. In the area of ​​scientific publications, there are several methods to attach a digital signature to a printed document. M. S. Bhattacharjee and Kutter, one of these algorithms described in "Compression Tolerant Image Authentication", IEEE Inter. Conference on Image Processing, USA, pp. 435-439, 1998. This algorithm is based on the use of wavelets to generate a signature of a digital document. J. Fridrich, in "Methods for Detecting Changes in Digital Images", Proc. IEEE Int. Workshop on Intell. Communi cation Signal Processing and Systems, 1998. It uses spread spectrum signal to generate digital signatures of documents.

CY. Lin and S.-F. Chang in "A Robust Image Authentication Method Surviving JPEG Compression Lossly", SPIE Storage and Retrieval of Image / Video DataBase VOI 3312, San José, 1998, wavelets used to secure the contents of digital documents. None of the items mentioned so far working with printed documents. Furthermore, this system does not use wavelets is based on coding the content of the printed text in the document.

Zhu Baoshi, Wu Jiankang and Mohan Kankanhalli "Print Signatures for Document Authentication", in Proceedings of the ACM Conference on Computer Loth and Communications Security Washington DC, USA, pp. 145-154, 2003, used the inherent randomness to the laser printing process to verify the authenticity of a printed document. The present invention does not require the use of a specific print technology. In "Comparison ofsome Thresholding Algorithms for Text / Background Segmentation in Difflcult Document Images", published in The Seventh International Conference on Document Analysis and Recognition VOI. 2, pg. 859, Leedham, Yan, Tan Takru and describe various binarization algorithms for segmenting text documents. However, binarization itself can not be used to secure the contents of documents printed text. Our invention uses other techniques besides the binarization to achieve this goal.

Gonzalez and Woods in Chapter 5 of Image Restoration Digital Image Processing, Second Edition, USA, New Jersey, Addison-Wesley, 2002, describe some algorithms eliminate image noise. However, none of these algorithms can be used by itself to ensure the integrity of text documents. In addition to these algorithms, our invention uses other techniques to produce secure documents.

Chapter of the book Optical Character Recognition Algorithms for Image Processing and Computer Vision, JR Parker, Wiley, 1996, an algorithm that aligns the text of an image with the horizontal lines of the same is described. However, this algorithm, by itself, can not be used to secure the contents of text documents. Our invention uses other techniques besides this to achieve that objective. In "A Computational Frameworkfor Segmentation and Grouping" of Medioni, Lee and Tang, Elsevier 2000, algorithms to find oriented line segments using a methodology called tensor voting are described. However, the tensor voting itself can not be used to secure text documents. The present invention uses other techniques besides this to reach this purpose. Zhang describes a method (called Iterated Closest Points or ICP) to align figures in two dimensions in the article "Iterative Matchingfor Point Registration Form ofFree- Curves and Surfaces", International Journal of Computer Vision, VoI. 13, No. 2, pp. 119-152, 1994. Veltkamp and Hagedoom describe such algorithms (such as Chamfer Matching) on ​​"State-of-the-ari in shape matching" UU-CS Technical Report 1999-27, Utretcht University, Netherlands, 1999. Also it is possible to align figures by an exhaustive search that is simply to try all possible ways in which the figures can match. This method is usually not efficient and for this reason it is rarely mentioned in the literature, but it is obvious implementation. However, alignment algorithms of figures can not be used by themselves to generate secure documents. In addition to these techniques, our invention uses other algorithms to achieve this goal.

C. Xu and JL Prince describe a recognition algorithm and vectorization of forms (commonly called active contours or snakes) in "Snakes, Shapes and Gradient Vector Flow" IEEE Transactions on Image Processing 7 (3), pg. 359-369, March 1998. However, this algorithm can not be used alone for secure documents. Our invention uses similar techniques in a step of the method; but it uses other algorithms besides this one to produce certain documents. Bernd Jähne describes several recognition algorithms local orientation in Chapter 13 of his book "Digital Image Processing", Springer-Verlag, 1997. These algorithms are based on the Fourier Transform, gradient analysis, tensor representation, numbers of local wave and phase Hilbert transform filter and Hilbert filters quadrature Gabor filters, and variants thereof. However, all these methods produce the local orientation of an image. Besides this, other algorithms are needed to produce secure documents, as does the present invention.

AJ Menezes. PC van Oorshot, and SA Vanstone algorithms described cyclic redundancy check (CRC) and encryption with public and private key in the book "Handbook of Applied CRC Press", 1997. However, these algorithms can not be used to verify the integrity of printed documents, as these algorithms require the original byte sequence is identical at all times. This condition is not met when scanning a printed document, where the lighting conditions vary and produce different sequences of bytes in each case. Our invention works despite these variations in lighting. Finally, it notes that this patent is an extension of the patent application PCTVMX2005 / 000019 Sergio Fernandez. In that document, a system and method for secure printing of documents claimed. Our invention differs from that by the method used to secure documents (signature).

The method disclosed in this document is based on recognizing patterns and repetitions of words of a text document to generate a signature that can be attached to the paper where the document is located. But at no time use of an optical character recognizer (OCR) it is made, since they usually have some flaws (by noise in the digital image) or limitations (the need for dictionaries of words). Our method has the advantage that it is not required to have a digital document. Methods based on correlation and wavelets using textures, which are very sensitive to changes not malicious as rotation, translation and scale that may be present when scanning a document. The method given here are robust to such changes. Also it does not require the use of special materials such as holograms, special inks or laser systems for signing a document. Finally, unlike some technologies described, the invention allows the document to be copied and transmitted by any electronic, electrical or mechanical always method as the written message has not been modified. BRIEF DESCRIPTION OF THE FIGURES

Figure 1 shows a diagram of the method of printing secure documents. Figure 2 shows a diagram of the method for verifying the integrity of a signed document. 3 shows a diagram where the internal parts of the signature generation step is.

Detailed description of the invention.

With reference to said figures, the method for securing the integrity of the contents of documents printed text is constituted of:

A method for printing secure documents. Which, in turn, is constituted by a step of imaging 3, to convert a document printed text 1 in a digital image (referred to hereafter simply as "image") - This step can be implemented with any device digitiser as a scanner, a digital copier, a multifunction printer, digital camera, etc. The image obtained in said acquisition step proceeds to a step signature generation 5, to generate the element that ensures the integrity of the document (hereinafter called simply "signature"). The substeps that comprise this stage are described in detail later. The signature generated by this step is sent along with the image to print stage and annexation signature 6 for attaching said signature to the original document and thus producing a secure document printed on paper 7. The printing step may be implemented with a device as a printer, digital copier, plotter or the like. Alternatively, this section of the system may contain a stage Raster images (image raster processor, in English) 4, to convert an electronic paper 2 (such as those generated by conventional programs such as Microsoft Word or Excel) into a digital image, in order to pass this image to the signature generating step 5. these processors rasterization usually integral hardware or many printers, can be achieved with the driver of these devices.

A method for the verification of security documents. Which, in turn, it constitutes a step of acquiring images 9 (such as that described in the previous section) that converts a printed document 8 in a digital image. This image is passed to a signature analysis stage 10 to extract the signature contained in the document. This step can be a simple reader dimensional barcode. In turn, the document image passes to step signature generation 11 (described in detail in the next section of this document) for the integrity check element (signature) from the textual content of the document. The signatures extracted by these modules are passed to the document certification stage 13 which verifies that both signatures match to finally issue a certificate of authenticity of the signed document 13. Two stages of signature generation (5 and 11) which are, in turn, a binarization step 14 that converts a color image or gray scale black and white. A noise removal step 15 which removes noise from the binarized image in the previous module. A horizontal alignment stage 16 amending image tilt so that the lines of text appear horizontal. A word segmentation stage 17 to find the two-dimensional boundaries of each word in the document. A step of identifying traces 18 for the key strokes every word obtained in the previous module. A step of aligning traces 19 to align the words obtained in previous modules. And finally, a stage of combination and encryption 20 that combines information from these modules for a signature that can be attached to the original document to ensure its content.

Method for printing secure documents.

To generate a secure document, the user scans a printed document 1 in the step of acquiring images 3 or through any editor electronic text (such as Word or Excel) generates a file 2 is converted into an image by the processor Raster images 4. The image is passed to the method signature generator 5.

The first signature generator binarized image in step 14 to obtain a bitmap to black and white. Binarizing method can be any of those described in "Comparison of Some Thresholding Algorithms for Text / Background Segmentation in Difflcult Document Images" of Leedham, Yan, Tan Takru and published in The Seventh International Conference on Document Analysis and Recognition VOI. 2, pg. 859. Once the image has been binarized, step 15 removes all those small dots which are produced by noise in the measurement system. Gonzalez and Woods describe several such algorithms in Chapter 5 of Image Restoration Digital Image Processing. Second Edition, USA, New Jersey, Addison-Wesley, 2002.

The clean image is then aligned so that the lines of text appear horizontal in the image (step 16). Some procedures for accomplishing this are described in Chapter 9: Optical Character Recognition in Algor ithms for Image Processing and Computer Vision, JR Parker, Wiley, 1996. Once the document has been aligned in this way. It is passed to the segmenting words 17. At this stage a vertical histogram of the image is obtained. This histogram contains an entry for each line of the image. In each entry the amount of black pixels is stored in that row. Thus, the lines of text appear as maxima and spaces between lines as minimal. It is easy then identify the beginning and end of each line by a simple differential analysis. The beginning of each line is given by a maximum moving from a small value to a large value and end of each line changes from a high value to a small value. It is clear that one skilled in the art can easily implement an algorithm to perform the described identification. After identifying the lines of the text, the segmenter obtains a horizontal histogram for each item where the now black pixel amount for each column there in that row is stored. This histogram can again be used to identify the beginning and end of each word, using a procedure similar to that described in the previous paragraph. Thus, the segmenter produces a list of words per line, where each word is assigned a unique number (coordinate). This numbering only depends on the content of the document itself and is not altered by changing circumstances (as change in image resolution, translation, rotation, or copying methods that do not alter the content). Other techniques, such as wavelets, are affected by this kind of harmless transformations.

The positions of each word and image passed the identification stage 18. This stage dashed individually analyzes each word to obtain the straight line segments (strokes) most representative of each word. This is achieved in particular by techniques tensorial vote (described in detail in "A Computational Frameworkfor Segmentation and Grouping" of Medioni, Lee and Tang, Elsevier 2000); although the use of alternative techniques such as the Hough transform (US Patent 3,069,654 "Method and Meansfor Recognizing Complex Patterns"), active contours (snakes in English, as described in the article "Snakes, Shapes, and is not ruled gradient Vector Flow "IEEE Transactions on Image Processing 7 (3), pg. 359-369, March 1998 by C. Xu and JL Prince), or any of the techniques described in the background of this document. These technologies have been in use for several years and are widely known by any expert in the area. The tensor voting produces a tracing of each pixel of the image. To compress the data, the next step is to group the strokes according to the affinity of their direction. This is accomplished by a depth-first search termination criteria which is a difference of excessive angle between pairs of strokes. Depth-first search technique is a graph traversal which is widely known and used for several years. Again, implementing a depth-first search with the aforementioned features is a trivial task for any programmer.

The strokes thus identified are stored in a list of strokes per word and passed, along with the positions of each word, the step of aligning lines 19. At this stage, are all occurrences of each word rest of the document. To detect the occurrence of a word in the rest of the document, the word on a word fate to test stands. If it is possible to properly align the main features of the original word with the word destiny, then there is an occurrence. A variety of algorithms that allow this alignment, as described by Zhang (ICP) in "Iterative Point Matchingfor Registration of Free-Form Curves and Surfaces", International Journal of Computer Vision VOI. 13, No. 2, pp. 119-152, 1994; or by any of the methods described by Veltkamp and Hagedoom (as Chamfer Matching) in "State-of-the-art in shape matching", technical report UU-CS-1999-27, Utretcht University, Netherlands, 1999. These algorithms they have been employed for some years and are easy to implement to an expert in the area. At the end of this stage a list of replications indicating the positions in which reoccurs every word in the text must then. It can be argued that if the text does not contain repetitions of words, then it can be easily altered without this change is noticeable in the firm. However, a significant document does not usually have these features. So, in general, any change in the position or frequency of words produces a different list, which, in turn, produces a different signature and alteration is detectable.

Finally, the list of strokes of each word and the list of repetitions of each word is appended to the list of words per line in step 20 to generate a series of numbers that uniquely identify each document. This series of numbers can be encoded by itself as a two-dimensional bar code (or some other form of coding binary image); but usually, it is compressed and the result is you get a cyclic redundancy code (CRC) which is normally used as a signature. It is also possible to obtain the CRC of the original signature (uncompressed). The firm thus obtained can be as small as a 16-bit number. This number is finally printed as a normal or two-dimensional code bars in the printed image to be insured. All these methods (compression and CRC) are widely known and used.

Alternatively, step 20 can use the information of the main features of some critical sections of the document (such as a check in the figures) to generate the signature, or appended to regular signature described in the previous paragraph. It is also possible to systematically collate the list of words per line, the list of strokes per word (for the critical sections of the document) and the list of repetitions, depending on the needs of each individual document or indications user to generate the signature. Additionally, the signature generated with any of the procedures (sequence numbers describing the words and their repetitions, the sequence of key strokes words or systematic combination of these) can be encrypted with the public key document sender to better secure the document. The encrypted signature can then be processed normally (compressed and you get your CRC). Notably similar to those described for steps 14, 15, 16 and 17 procedures already used in some optical character recognizer (OCR). The novelty is that instead of trying to recognize characters to form meaningful words (such as OCR), this process recognizes any pattern and repetition of these. OCR has the disadvantages that does not work for any font (source) and also needs a dictionary for each language to disambiguate some words. Our invention is distinguished from an OCR that does not require any dictionary and works for any language and font. Moreover, by not requiring the recognition of words, the invention can easily work with handwritten text, which is still considered a difficult problem currently solved by an OCR.

Finally, the signature obtained by this method is sent along with the image to append signature stage and printing 6. This step makes the signature to a small image (two-dimensional barcode, widely known and used technology) and attached in any unused portion of the original document (for example, at the edges of the page). The modified image is printed to finally generate a secure document 7.

Method for verification of secure documents.

To verify the integrity of a document 8 is scanned and converted into an image in step 9. This image is sent to a signature analysis step 10 simply reads and interprets the printed signature on the document. This step may be implemented with a reader dimensional barcode, whose use is widespread.

Additionally, after the signature has been processed with a barcode reader, it may be necessary to decrypt the sender's private key, to verify the integrity of the signature by itself has not been compromised. This is also done in step 10. Simultaneously with this step, the image is sent to the signature generation stage 11 (whose operation has already been explained above) to obtain the signature from the contents of the document 8.

Both signatures are compared in step 12. When the certification document has been maliciously modified, the signatures will be different. In that case, the certifier 12 responds indicating that the document has been altered. Otherwise, a certificate of integrity 13 is issued, indicating that the document is true to the original. The method for generating the signature is the novelty of the invention. The novelty of the method is that, using computer vision algorithms, the textual content of the printed document is analyzed to generate a signature without using a character recognizer (OCR). That is, all the information necessary to verify the integrity of the document is in the document itself, and the signature can be as small as a 16-bit number. Instead of recognizing individual characters, the shape and position of words in the text are used as a signature to ensure that the content has not been modified. No other current system can sign documents in this way without using OCR. On the other hand, systems that generate digital signatures based on wavelets have the disadvantage that the signature generated is usually relatively large. This size makes it difficult to include the signature in the blanks of the original document (usually only the margins of the text). The advantage of our method compared to methods based on wavelets is that the firm can be reduced to a size of 16 bits, facilitating their inclusion in the blanks of any document printed text. Besides this, methods based on wavelets often not withstand the changes that preserve the contents of the document, such as the resolution change and translation or rotation of the image. Our invention works despite such changes. Additionally to everything mentioned, our invention does not need a set of dictionaries of words. Not required to have the original document in electronic format. Does not require the use of special materials on paper or attachments thereto. No need to use colored plastics to display the signature. It does not require the use of lasers to illuminate the document and detect the signature. Finally, the method can be used with any language texts.

Claims

claims
1 A method of generating a printed signature, comprising the steps of binarization, noise removal, horizontal alignment, word segmentation to generate a list of words per line in which each word has associated a single coordinate, characterized by the steps of : a) Identification of the lines of words. At this stage, the tensorial vote is used for local targeting each pixel. Then local orientations are grouped by searching depth according to the affinity of their angle. This is done to identify the most representative of each word orientations and relative positions within the same. This step produces a list of strokes of each word. b) alignment lines. Using the most representative of each word strokes, it seeks to align the strokes of each word with the rest of the document. Those positions where this alignment mark is possible repetitions of the word. The positions where each word is repeated are stored in a list of repetitions. This step is implemented by a modified version of the ICP algorithm that uses only translations to align the strokes. c) Combination and encryption. At this stage the list of words per line, the list of repetitions, and the list of strokes of each word are combined to create the signature. The signature can be simple annexation of these lists, the annexation of a couple of them, or only one of these lists. It is also possible systematically interleave portions of these three lists to generate the signature, as marked by the user or according to the characteristics of each document. d) Step append signature and printing. At this stage, the signature obtained by this method becomes a two-dimensional barcode by known techniques and printed on the original document using a printer or similar device.
2 A method of generating a printed signature of claim 1 wherein the identification of strokes is done by Hough transform, active contours (snakes in English), Fourier Transform, gradient analysis, tensor representation numbers local wave and phase, the Hilbert transform, Hilbert filter, filters quadrature Gabor filters, and variants thereof, or some other similar method to obtain the local orientation of an image. 3 A method of generating a printed signature according to claims 1 and 2 wherein the dashed alignment is done by exhaustive search, Chamfer Matching, active contours (snakes) or some similar algorithm.
4 A method for generating a printed signature according to claims 1, 2 and 3 characterized in that the signature is further protected by encryption with the public key of the issuer of the document.
5 A method of generating a printed signature according to claims 1, 2, 3 and 4 characterized in that the size of the signature is reduced using compression algorithms or cyclic redundancy check (CRC).
PCT/MX2005/000089 2005-10-04 2005-10-04 Method of generating a printed signature in order to secure the contents of text documents WO2007040380A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/MX2005/000089 WO2007040380A1 (en) 2005-10-04 2005-10-04 Method of generating a printed signature in order to secure the contents of text documents

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/MX2005/000089 WO2007040380A1 (en) 2005-10-04 2005-10-04 Method of generating a printed signature in order to secure the contents of text documents

Publications (1)

Publication Number Publication Date
WO2007040380A1 true WO2007040380A1 (en) 2007-04-12

Family

ID=37906381

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/MX2005/000089 WO2007040380A1 (en) 2005-10-04 2005-10-04 Method of generating a printed signature in order to secure the contents of text documents

Country Status (1)

Country Link
WO (1) WO2007040380A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3200255A2 (en) 2016-01-06 2017-08-02 Konica Minolta, Inc. Organic electroluminescent element, method for producing organic electroluminescent element, display, and lighting device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4641347A (en) * 1983-07-18 1987-02-03 Pitney Bowes Inc. System for printing encrypted messages with a character generator and bar-code representation
EP0702322A2 (en) * 1994-09-12 1996-03-20 Adobe Systems Inc. Method and apparatus for identifying words described in a portable electronic document
US6279828B1 (en) * 1999-03-01 2001-08-28 Shawwen Fann One dimensional bar coding for multibyte character
US20010047476A1 (en) * 2000-05-25 2001-11-29 Jonathan Yen Authenticatable graphical bar codes

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4641347A (en) * 1983-07-18 1987-02-03 Pitney Bowes Inc. System for printing encrypted messages with a character generator and bar-code representation
EP0702322A2 (en) * 1994-09-12 1996-03-20 Adobe Systems Inc. Method and apparatus for identifying words described in a portable electronic document
US6279828B1 (en) * 1999-03-01 2001-08-28 Shawwen Fann One dimensional bar coding for multibyte character
US20010047476A1 (en) * 2000-05-25 2001-11-29 Jonathan Yen Authenticatable graphical bar codes

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3200255A2 (en) 2016-01-06 2017-08-02 Konica Minolta, Inc. Organic electroluminescent element, method for producing organic electroluminescent element, display, and lighting device

Similar Documents

Publication Publication Date Title
Huang et al. Detection of copy-move forgery in digital images using SIFT algorithm
Brassil et al. Electronic marking and identification techniques to discourage document copying
Zhao et al. Robust hashing for image authentication using Zernike moments and local features
US8301893B2 (en) Detecting media areas likely of hosting watermarks
US8059858B2 (en) Identification document and related methods
US7570784B2 (en) Identification and protection of security documents
US7028902B2 (en) Barcode having enhanced visual quality and systems and methods thereof
EP2257909B1 (en) Secure item identification and authentication system and method based on unclonable features
US7991198B2 (en) Visible authentication patterns for printed document
EP1333658B1 (en) Apparatus and method for producing a watermarked document and for authenticating the same
CN101366266B (en) Method and device for embedding and detecting digital watermark in text document
US7974495B2 (en) Identification and protection of video
AU2008270125B2 (en) Method and device for securing documents
EP1202552B1 (en) Method for generating and detecting watermarks
JP4783021B2 (en) 耐偽 forming resistance and tambour labels having characteristics generated at random
US6782116B1 (en) Apparatus and methods for improving detection of watermarks in content that has undergone a lossy transformation
US8144368B2 (en) Automated methods for distinguishing copies from original printed objects
US6748533B1 (en) Method and apparatus for protecting the legitimacy of an article
EP1432234B1 (en) Systems and methods for providing hardcopy secure documents and for validation of such documents
US6272245B1 (en) Apparatus and method for pattern recognition
US7711140B2 (en) Secure recorded documents
DK2024899T3 (en) Means of use of the material surface microstructure as a unique identifier
JP3804012B2 (en) Alteration determination method of the document image and the system, and a control program thereof
US7206431B2 (en) System and method for generating and verifying a self-authenticating document
US20040001606A1 (en) Watermark fonts

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application
NENP Non-entry into the national phase in:

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC OF 220708

122 Ep: pct application non-entry in european phase

Ref document number: 05803573

Country of ref document: EP

Kind code of ref document: A1