Method for securing and verifying a document
US-2017236355-A1 · Aug 17, 2017 · US
US10403076B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10403076-B2 |
| Application number | US-201715429093-A |
| Country | US |
| Kind code | B2 |
| Filing date | Feb 9, 2017 |
| Priority date | Feb 11, 2016 |
| Publication date | Sep 3, 2019 |
| Grant date | Sep 3, 2019 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
The invention relates to a method for securing a document including a visual element, carried out by a processing unit comprising processing means, the method comprising generation, from the visual element, of a reference security datum, and storage of the reference security datum, wherein the reference security datum is generated by means of an algorithm configured so as to generate: for any image acquired from the visual element, a security datum whereof the differences relative to the reference security datum are less than a determined threshold, and for any image acquired on a different visual element, a security datum whereof the differences relative to the reference security datum are greater than said threshold.
Opening claim text (preview).
The invention claimed is: 1. A method for securing a document including a visual element, carried out by a processing unit comprising processing means, the method comprising generation, from the visual element, of a reference security datum, and storage of the reference security datum, wherein the reference security datum is generated by processing means of an algorithm parameterized from training on a learning database, wherein, for training the algorithm, the algorithm is executed on a large number of pairs of images, and indications are provided on those which must result in substantially identical security data, on other pairs of images which must result in substantially different security data. 2. The method for securing a document according to claim 1 , wherein generation of the reference security datum is carried out during creation of the document. 3. The method for securing a document according to claim 1 , wherein the reference security datum is stored in the document, by display, for example printing, of the datum on the document or by recording of the datum in an electronic chip stored in the document. 4. The method for securing a document according to claim 3 , wherein the reference security datum is signed by the processing unit, by processing means of a signature algorithm with public key, or recorded with a certificate of authenticity obtained by application of a coding algorithm based on use of an error-correction code, so-called secure sketch. 5. The method for securing a document according to claim 1 , wherein the reference security datum is stored by being recorded in a database. 6. The method for securing a document according to claim 1 , wherein the reference security datum is stored in the document by display, for example printing, of the datum on the document and wherein the visual element is also displayed, for example printed, on the document. 7. The method for securing a document according to claim 1 , wherein the document is an electronic document preferably comprising display means. 8. The method for securing a document according to claim 1 , wherein the algorithm is selected such that reconstitution of the visual element from the corresponding security datum is impossible. 9. The method for securing a document according to claim 1 , wherein the algorithm is of the type comprising the use of histograms of gradients oriented on the visual element, or of convolutional neural networks, or of descriptor algorithm type. 10. The method for securing a document according to claim 1 , wherein the algorithm is a descriptor algorithm of BRIEF type, or of SIFT type, or of SURF type or of GLOH type, or of ORB type, or of BRISK type or of FREAK type or of LATCH type. 11. The method for securing a document according to claim 1 , wherein said algorithm being trained so as to generate: for any image acquired from the visual element, a security datum whereof the differences relative to the reference security datum are less than a determined threshold, and for any image acquired on a different visual element, a security datum whereof the differences relative to the reference security datum are greater than said threshold. 12. A computer program product stored on a non-transitory medium, comprising code instructions for carrying out a method according to claim 1 , when it is executed by processing means of a processing unit. 13. A secure document which can be obtained by carrying out a method according to claim 1 . 14. The method for securing a document according to claim 1 , wherein the visual element is an image of the face of an individual, and the algorithm is trained so as to generate: for any image acquired from the image of the face of the individual featured on the document, a security datum whereof the differences relative to the reference security datum are less than a determined threshold, and for any image acquired from an image representing another individual, or the same individual in different image acquisition conditions, a security datum whereof the differences relative to the reference security datum are greater than said threshold. 15. The method for securing a document including a visual element, carried out by a processing unit comprising processing means, the method comprising generation, from the visual element, of a reference security datum, and storage of the reference security datum, wherein the reference security datum is generated by processing means of an algorithm parameterized from training on a learning database, said algorithm being trained so as to generate: for any image acquired from the visual element, a security datum whereof the differences relative to the reference security datum are less than a determined threshold, and for any image acquired on a different visual element, a security datum whereof the differences relative to the reference security datum are greater than said threshold. 16. A method for verifying the integrity of a document secured by carrying out the method according to claim 1 , the method comprising the steps of: acquiring an image of the visual element of the document, generating, from the image, a security datum by the same algorithm as that having generated the reference security datum, comparing the security datum obtained to the reference security datum, and if the differences between the security datum and the reference security datum are less than the determined threshold, determining that the visual element is integral, if not determining that the visual element is fraudulent. 17. The verification method according to claim 16 , wherein the method further comprises, prior to the comparison step, a verification step of the integrity of the reference security datum. 18. A system for verifying a document, comprising: an image sensor, a processing unit, comprising processing means adapted to carry out, on an image acquired by the sensor, a classification algorithm, and a communications interface with a database, the verification system being configured to carry out the method according to claim 16 .
using holograms · CPC title
Learning · CPC title
involving markings added to a pattern, e.g. interstitial points · CPC title
using feature extraction, e.g. segmentation, edge detection or Hough-transformation · CPC title
Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light (G01N3/00 - G01N19/00 take precedence) · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.