Fast color-brightness-based methods for image segmentation

• US 9,552,531 B2
• Filed: 01/30/2015
• Issued: 01/24/2017
• Est. Priority Date: 01/30/2015
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Usikov, Daniel
• Primary Examiner(s): Dang, Duy M
• Application Number:
  US14/610,630
• Publication Number:
  US 20160224859A1
• Time in Patent Office: 725 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/231 Hierarchical techniques, i.e. dividing or merging pattern sets so as to obtain a dendrogram
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G06V 10/7625 Hierarchical techniques, i.e. dividing or merging patterns to obtain a tree-like representation; Dendograms

Abstract

Image segmentation utilizing the color and brightness of sections of the image to generate super-pixels is described herein. The image segmentation is implemented pixel-wise. A color triangle is utilized in the classification of the pixels. By using a hierarchical classification table, the memory usage is significantly reduced, and the image segmentation is able to be performed on-the-fly in real-time.

Claims

1. A method programmed in a non-transitory memory of a device comprising:

a. acquiring an image using a sensor of the device; and

b. performing image segmentation on the image in a color space and brightness space simultaneously, wherein performing image segmentation includes classifying gray-level pixels as belonging to a gray-level category, and subdividing remaining pixels into sub-categories by using a color triangle which is divided into sectors.

2. The method of claim 1 wherein the image segmentation is performed using a pixel-wise implementation.

3. The method of claim 1 wherein performing image segmentation utilizes color and brightness of pixels of the image to generate superpixels.

4. The method of claim 1 wherein the color triangle includes 9 divisions, 36 divisions or 15 divisions, and the color triangle is adjusted to human color perception.

5. The method of claim 1 wherein a first subset of the sectors are labeled by brightness and a second subset of sectors are labeled by average color and brightness.

6. The method of claim 1 wherein performing image segmentation includes classifying pixels by comparing a color vector of a pixel with classification information to place each pixel in a classification.

7. The method of claim 6 wherein the comparison is performed using a hierarchical classification table.

8. A system comprising:

a. a sensor in a camera configured for acquiring an image; and

b. a processor configured for performing image segmentation on the image in a color space and brightness space simultaneously, wherein performing image segmentation includes classifying gray-level pixels as belonging to a gray-level category, and subdividing remaining pixels into sub-categories by using a color triangle which is divided into sectors.

9. The system of claim 8 wherein the image segmentation is performed using a pixel-wise implementation.

10. The system of claim 8 wherein performing image segmentation utilizes color and brightness of pixels of the image to generate superpixels.

11. The system of claim 8 wherein the color triangle includes 9 divisions, 36 divisions or 15 divisions, and the color triangle is adjusted to human color perception.

12. The system of claim 8 wherein a first subset of the sectors are labeled by brightness and a second subset of sectors are labeled by average color and brightness.

13. The system of claim 8 wherein performing image segmentation includes classifying pixels by comparing a color vector of a pixel with classification information to place each pixel in a classification.

14. The system of claim 13 wherein the comparison is performed using a hierarchical classification table.

15. An apparatus comprising:

a. an acquisition device for acquiring an image;

b. a non-transitory memory for storing an application, the application for performing image segmentation on the image in a color space and brightness space simultaneously, wherein performing image segmentation includes classifying gray-level pixels as belonging to a gray-level category, and subdividing remaining pixels into sub-categories by using a color triangle which is divided into sectors; and

c. a processor coupled to the memory, the processor configured for processing the application.

16. The apparatus of claim 15 wherein the image segmentation is performed using a pixel-wise implementation.

17. The apparatus of claim 15 wherein performing image segmentation utilizes color and brightness of pixels of the image to generate superpixels.

18. The apparatus of claim 15 wherein the color triangle includes 9 divisions, 36 divisions or 15 divisions, and the color triangle is adjusted to human color perception.

19. The apparatus of claim 15 wherein a first subset of the sectors are labeled by brightness and a second subset of sectors are labeled by average color and brightness.

20. The apparatus of claim 15 wherein performing image segmentation includes classifying pixels by comparing a color vector of a pixel with classification information to place each pixel in a classification.

21. The apparatus of claim 20 wherein the comparison is performed using a hierarchical classification table.