METHOD FOR IDENTIFYING A SIGN ON A DEFORMED DOCUMENT

• US 20160104039A1
• Filed: 10/08/2015
• Published: 04/14/2016
• Est. Priority Date: 10/10/2014
• Status: Active Grant

• Current Assignee: IDEMIA Identity and Security France SAS (Advent International Corporation)
• Original Assignee: Morpho (Advent International Corporation)
• Inventors: Rouh, Alain, Beaudet, Jean, Rostaing, Laurent
• Granted Patent: US 10,025,977 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• CPC Class Codes: G06V 10/20 Image preprocessing
• CPC Class Codes: G06V 10/225 based on a marking or identifier characterising the area
• CPC Class Codes: G06V 10/243 by compensating for image skew or non-uniform image deformations
• CPC Class Codes: G06V 10/247 by affine transforms, e.g. correction due to perspective effects; Quadrilaterals, e.g. trapezoids
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text

Abstract

This invention relates to a method for identifying a sign on an image of a document that can be deformed comprising:

an acquisition (E1) of said digital image of said document;

a determination (E2) in the acquired image of at least one candidate sign region using an image segmentation algorithm,

for each candidate sign region, a calculation (E3) of a signature comprising a piece of information concerning the location in the acquired image of said candidate sign region and a region descriptor concerning the local characteristics of the image in said region,

an identification (E4) of a sign on the image of the document using the calculated signatures comprising jointly a comparison (E41) of the calculated signatures with reference signatures concerning sign regions of document models, said comparison being carried out according to a geometric deformation model of said document, and an estimation (E42) according to said comparison of said geometric deformation model.

Claims

1. Method for identifying at least one sign on at least one image of a document that can be deformed,

said method being implemented by a data processing device able to be connected to a first storage device and characterised in that it comprises steps of:

acquiring (E1) said at least one digital image of said document;

determining (E2) in the acquired image at least one sub-part of the image acquired, referred to as candidate sign region, using an image segmentation algorithm,

for each candidate sign region, calculating (E3) a signature comprising a piece of information concerning the location in the acquired image of said candidate sign region and a region descriptor concerning the local characteristics of the image in said region,

identifying (E4) at least one sign on said at least one image of said document using the calculated signatures,

said step of identifying comprising jointly a comparison (E41) of the calculated signatures with reference signatures concerning sign regions of document models stored in the first storage device, said comparison being carried out according to a geometric deformation model of said document, and an estimation (E42) according to said comparison of said geometric deformation model.

2. Method of identification as claimed in claim 1, wherein for each candidate sign region:

said step of comparing comprises;

a comparison of the signature calculated for said region with said reference signatures stored in said first storage device,

a putting into correspondence of the calculated signature with a reference signature according to said comparison and to a geometric deformation model of the current document stored in a second storage device connected to said data processing device, in such a way as to identify said candidate sign region,

and said step of estimating (E42) comprises;

an estimating of a new geometric deformation model of said document from said current geometric deformation model and from said correspondence,

a storing in the second storage device of said new deformation model as a current deformation model.

3. Method of identification according to claim 1, wherein said document is a game ticket or an identity document.

4. Method of identification according to claim 1, wherein a sign to be identified is a geometric figure, a character, a group of characters or a graphical element.

5. Method of identification according to claim 1, wherein a sign to be identified is a pattern delimited by a closed contour.

6. Method of identification according to claim 3, wherein a sign to be identified is a box, a circle, a star or an alphanumeric character or a specific pattern of the issuing country of an identity document.

7. Method of identification according to claim 3, wherein a signature further comprises information on the scale.

8. Method of identification according to claim 3, wherein a descriptor of a sign region relates to information on the contour and/or on the content of said sign region.

9. Method of identification according to claim 3, wherein the deformation model is determined using an inverse distance weighting algorithm or an splines interpolation algorithm.

10. Computer programme product comprising code instructions for the executing of a method of identification as claimed in claim 3 when this programme is executed by a processor.

11. Device for identifying at least one sign on at least one image of a document that can be deformed,

characterised in that it comprises a data processing device able to be connected to a first storage device comprising:

a module for acquiring said at least one digital image of said document;

a module for determining in the acquired image of at least one subpart of the image acquired, referred to as candidate sign region, using an image segmentation algorithm,

a module for calculating a signature for each candidate sign region comprising a piece of information concerning the location in the acquired image of said candidate sign region and a region descriptor concerning the local characteristics of the image in said region,

a module for identifying at least one sign on said at least one image of said document using the calculated signatures,

said module for identifying comprising a module for comparing of the calculated signatures with reference signatures concerning sign regions of document models stored in said first storage device, according to a geometric deformation model of said document, and a module for the joint estimating of said geometric deformation model according to said comparison.