Method and Device for Obtaining an Image of a Crumpled Document From an Image of Said Document When Same is Crumpled

Patent №

US 9,025,904

Granted

2015-05-05

Filed 2012

Owner

MORPHO

+1 more

Lab

AI components

1

vision

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

13504539

The present invention relates to a method and device for obtaining an image of a crumpled document from an image of this document when it is crumpled. The method comprises a step of determining a three-dimensional geometric model of the surface of the crumpled document by triangulation of three-dimensional points defined from the pattern of a target extracted from the image of this document when it is crumpled; the method is characterized in that it comprises a step of determining a projection of the three-dimensional geometric model onto a so-called acquisition plane, by means of error minimization of this projection under constraints of preserving defined geometric characteristics in the vicinity of the three-dimensional points, and in that it comprises a step of superimposing the textures associated with the three-dimensional model onto the projection of this model thus determined. The present invention likewise relates to target patterns that make it possible to improve the quality of the image resulting from the method to be improved and/or to reduce the cost for computing said image.

VisionG06T 15/10G06T 3/06G06T 3/073G06T 5/70G06V 30/40G06V 10/247

AI classification

Vision1.00
Machine learning0.02
Natural language0.00
Planning0.00
Evolutionary computation0.00
Speech0.00
Knowledge representation0.00
AI hardware0.00

Ownership

MORPHO

assignment · 291900330

IDEMIA IDENTITY & SECURITY FRANCE

namechg · 525480761

Assignors

DOUBLET, JULIEN, VERILHAC, MICHAEL, REVELIN, STEPHANE, PICARD, SYLVAINE

On an employer assignment, the assignors are typically the inventors.

From the same owner

© 2026 NYSGPT2525 LLC