Method for the graphics processing of images

• US 10,679,354 B2
• Filed: 12/30/2016
• Issued: 06/09/2020
• Est. Priority Date: 01/04/2016
• Status: Active Grant

• Current Assignee: Jean-Thierry Tchoumou
• Original Assignee: Laoviland Experience
• Inventors: Tchoumou, Jean-Thierry, Tchoumou, Pascal, Rodriguez-Torrecillas, Matthias, Jaulmes, Boris
• Primary Examiner(s): Baker, Charlotte M
• Application Number:
  US16/068,114
• Publication Number:
  US 20190012791A1
• Time in Patent Office: 1,257 Days
• Field of Search: 382173, 382115, 382278, 382107, 382118
• CPC Class Codes: G06F 16/56 having vectorial format
• CPC Class Codes: G06F 17/11 for solving equations , e.g. nonlinear equations, general mathematical optimization problems optimization specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06T 11/001 Texturing; Colouring; Generation of texture or colour inpainting G06T5/77
• CPC Class Codes: G06T 7/10 Segmentation; Edge detection motion-based segmentation G06T7/215
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/28 Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]

Abstract

A method for graphic image processing from existing source image files forming a database from which an image is extracted for said graphic processing operations. The method includes the step of implementing n (n≥1) saliency processing operations in order to form n saliency cards CSi, with i=1 to n;

• • performing a linear combination

$\frac{{\nabla }_{i=1}^N\mathrm{Ai}.\mathrm{SCi}}{\sum _{i=1}^n\mathrm{Ai}}$
in order to obtain a single resulting saliency card;

• • performing a first thresholding on the resulting saliency card; and
  • vectorizing said thresholded card.

Claims

1. A method for graphically processing images from existing source image files forming a database from which an image is extracted for said graphic processing operations, the method comprising the following steps:

implementing n (n≥

1) visual saliency processing operations on a selected source image file, based on n predetermined saliency criteria, in order to form n saliency cards CSi, where i=1 to n;

performing a linear combination

2. The method for graphic image processing according to claim 1, wherein at least one saliency criterion underlying a saliency processing is inverted.

3. The method for graphic image processing according to claim 1, wherein the threshold set for the first thresholding is varying.

4. The method for graphical image processing according to claim 1, wherein a second thresholding is performed, the threshold of which is at a level close to the threshold selected for the first thresholding, a differentiation of the white pixels resulting from the two thresholds leading to a set of pixels permitting the calculation of a contouring of the white spots resulting from the first thresholding.

5. The method for graphic image processing according to claim 1, wherein at the end of the vectorization phase, a color inversion of the black and white spots is implemented.

6. The method for graphic image processing according to claim 1, wherein at the end of the vectorization phase, the black background is removed and remains transparent.

7. The method for graphic image processing according to claim 1, wherein the filling of each group is performed by selecting a plurality of modes including at least an image mode, a color mode, a hue mode and a black and white mode.

8. The method for graphic image processing according to claim 7, wherein the image mode consists in comprises filling a given group by the image portion resulting from the source file, which has the same shape, the same surface area as the group and corresponds to the location of this group in the source image.

9. The method for graphic image processing according to claim 7, wherein the color mode comprises filling a given group with a solid color determined by a random process.

10. The method for graphic image processing according to claim 7, wherein the hue mode comprises filling a given group with the average hue stores in memory for this group.

11. The method for graphic image processing according to claim 7, wherein the black and white mode comprises filling a given group with white.