Method for marking graphical elements and method for detecting said marking in a graphical element

• US 8,885,947 B2
• Filed: 09/06/2010
• Issued: 11/11/2014
• Est. Priority Date: 09/06/2010
• Status: Active Grant

• Current Assignee: Anteleon Imaging Sarl
• Original Assignee: Anteleon Imaging Sarl
• Inventors: Startchik, Sergei
• Primary Examiner(s): Koziol, Stephen R
• Assistant Examiner(s): LE, TOTAM HA
• Application Number:
  US13/820,807
• Publication Number:
  US 20130208988A1
• Time in Patent Office: 1,527 Days
• Field of Search: 382/200
• US Class Current: 382/200
• CPC Class Codes: G06T 1/0064 Geometric transfor invariant watermarking, e.g. affine transform invariant
• CPC Class Codes: G06T 2201/0051 Embedding of the watermark in the spatial domain
• CPC Class Codes: G06T 2201/0062 Embedding of the watermark in text images, e.g. watermarking text documents using letter skew, letter distance or row distance

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).

Claims

1. A method for marking graphical elements comprising the steps of:

estimating axes of alignment of characters and symbols in said graphical element;

defining zones of high visibility around these axes of alignment;

defining at least one zone of low visibility comprising parts of said graphical element that are not comprised in any of said zones of high visibility;

selecting at least three coherent edge portions of said graphical element in said at least one zone of low visibility, such that the relative orientation of said coherent edge portions is constant or smoothly varies along their entire length, said at least three coherent edge portions comprising at least two reference edge portions and one edge portion to mark located between said at least two reference edge portions;

defining a family of smooth and non-intersecting curves, said curves intersecting all of said at least three coherent edge portions;

defining an encoding area comprising said at least three coherent edge portions and said curves, said encoding area being limited on two opposite sides by said at least two reference edges portions and on two other opposite sides by curves of said family of curves;

shifting said edge portion to mark along said curves relative to said at least two reference edge portions; and

storing information about said at least one encoding area in a descriptor of said graphical element.

2. The method of claim 1, wherein said at least one encoding area comprises four coherent edge portions, said four coherent edge portions comprising three reference edge portions and one edge portion to mark located between two of said three reference edge portions.

3. The method of claim 1, wherein said graphical element comprises text and said at least three coherent edge portions are parts of a same character of said text.

4. The method of claim 1, wherein said graphical element comprises text and said at least three coherent edge portions are parts of two neighbouring characters of said text.

5. The method of claim 1, wherein the previously set forth steps are repeated at least one more time.

6. The method of claim 1, wherein a distance of shifting said edge portion to mark is smaller or equal to 5% of the largest overall dimension of said graphical element.

7. The method of claim 1, wherein a distance of shifting said edge portion to mark is smaller or equal to 3% of the largest overall dimension of said graphical element.

8. The method of claim 1, further comprising a last step of randomly displacing edges of said graphical element, wherein said at least three coherent edge portions are not moved relative to each other.

9. A method for detecting a marking in a graphical element, comprising the steps of:

providing a descriptor of a graphical element defined according to the method of claim 1;

locating said encoding area in a digital image of said graphical element;

retrieving said at least two reference edge portions and said at least one modified edge portion of said encoding area in said digital image;

determining the relative position of said modified edge portion relative to said reference edge portions, said step of determining the relative position of said at least one modified edge portion comprising transforming said at least two reference edge portions and said at least one modified edge portion into a normalized domain wherein the position of a first one of at least two normalized reference edge portions corresponds to 0, a second one of at least two normalized reference edge portions corresponds to 1, and the value corresponding to the position of a normalized modified edge portion between said first one and second one of at least two normalized reference edge portions determines the relative position of said at least one modified edge portion.

10. The method of claim 9, wherein said step of retrieving comprises retrieving at least three reference edge portions of said encoding area in said digital image.

11. Non-transitory computer-readable medium encoded with instructions for performing the method of claim 1 when loaded on a computing device.

12. Non-transitory computer-readable medium encoded with instructions for performing the method of claim 9 when loaded on a computing device.

13. A mobile computing device with a camera programmed for performing the method of claim 9.