Systems and methods for reducing a plurality of bounding regions

Patent metadata

Field	Value
Publication number	US-9542751-B2
Application number	US-201514707929-A
Country	US
Kind code	B2
Filing date	May 8, 2015
Priority date	May 8, 2015
Publication date	Jan 10, 2017
Grant date	Jan 10, 2017

Abstract

A method performed by an electronic device is described. The method includes generating a plurality of bounding regions based on an image. The method also includes determining a subset of the plurality of bounding regions based on at least one criterion and a selected area in the image. The method further includes processing the image based on the subset of the plurality of bounding regions.

First claim

What is claimed is:

1. A method performed by an electronic device, comprising:
generating a plurality of bounding regions based on an image;
determining a subset of the plurality of bounding regions based on a color difference criterion and a selected area in the image, wherein the color difference criterion distinguishes between bounding regions based on a color distance between a bounding region and a respective surrounding region; and
processing the image based on the subset of the plurality of bounding regions.

2. The method of claim 1 , wherein determining the subset of the plurality of bounding regions is further based on a centeredness of each of the plurality of bounding regions relative to the selected area.

3. The method of claim 1 , wherein determining the subset of the plurality of bounding regions is further based on a comparison between a color histogram of each bounding region and a color histogram of each respective surrounding region.

4. The method of claim 1 , wherein determining the subset of the plurality of bounding regions is further based on an average size of the plurality of bounding regions.

5. The method of claim 4 , wherein the average size is at least one of a median size and mean size.

6. The method of claim 1 , wherein processing the image comprises performing one or more of object recognition, object tracking, focusing, object removal, image enhancement, cropping or compression.

7. The method of claim 1 , wherein generating the plurality of bounding regions is based on a gradient-based bounding region generation algorithm.

8. The method of claim 1 , wherein determining a subset of the plurality of bounding regions based on the color difference criterion and the selected area in the image comprises:
rejecting any of the plurality of bounding regions that fail one or more of a centeredness criterion or a first size criterion; and
selecting a bounding region that meets one or more of the color difference criterion or a second size criterion.

9. The method of claim 8 , wherein the second size criterion is met for a bounding region with a weighted median size or a weighted mean size.

10. The method of claim 1 , wherein determining a subset of the plurality of bounding regions based on the color difference criterion and the selected area in the image comprises:
rejecting any of the plurality of bounding regions that fail a centeredness criterion to produce a plurality of remaining bounding regions;
determining a color distance between each of the plurality of remaining bounding regions and a respective surrounding region; and
selecting a bounding region with a largest color distance.

11. An electronic device, comprising:
a processor configured to generate a plurality of bounding regions based on an image, to determine a subset of the plurality of bounding regions based on a color difference criterion and a selected area in the image, wherein the color difference criterion distinguishes between bounding regions based on a color distance between a bounding region and a respective surrounding region, and to process the image based on the subset of the plurality of bounding regions.

12. The electronic device of claim 11 , wherein the processor is configured to determine the subset of the plurality of bounding regions further based on a centeredness of each of the plurality of bounding regions relative to the selected area.

13. The electronic device of claim 11 , wherein the processor is configured to determine the subset of the plurality of bounding regions further based on a comparison between a color histogram of each bounding region and a color histogram of each respective surrounding region.

14. The electronic device of claim 11 , wherein the processor is configured to determine the subset of the plurality of bounding regions further based on an average size of the plurality of bounding regions.

15. The electronic device of claim 14 , wherein the average size is at least one of a median size and mean size.

16. The electronic device of claim 11 , wherein the processor is configured to process the image by performing one or more of object recognition, object tracking, focusing, object removal, image enhancement, cropping or compression.

17. The electronic device of claim 11 , wherein the electronic device further comprises:
an image sensor coupled to the processor, wherein the image sensor is configured to capture the image;
a memory coupled to the processor, wherein the memory is configured to store bounding region data;
a display coupled to the processor, wherein the display is configured to present the image; and
an input interface coupled to the processor, wherein the input interface is configured to receive input indicating the selected area.

18. The electronic device of claim 11 , wherein the processor is configured to:
reject any of the plurality of bounding regions that fail one or more of a centeredness criterion or a first size criterion; and
select a bounding region that meets one or more of the color difference criterion or a second size criterion.

19. The electronic device of claim 18 , wherein the second size criterion is met for a bounding region with a weighted median size or a weighted mean size.

20. The electronic device of claim 11 , wherein the processor is configured to:
reject any of the plurality of bounding regions that fail a centeredness criterion to produce a plurality of remaining bounding regions;
determine a color distance between each of the plurality of remaining bounding regions and a respective surrounding region; and
select a bounding region with a largest color distance.

21. A computer-program product, comprising a non-transitory computer-readable medium having instructions thereon, the instructions comprising:
code for causing an electronic device to generate a plurality of bounding regions based on an image;
code for causing the electronic device to determine a subset of the plurality of bounding regions based on a color difference criterion and a selected area in the image,

wherein the color difference criterion distinguishes between bounding regions based on a color distance between a bounding region and a respective surrounding region; and
code for causing the electronic device to process the image based on the subset of the plurality of bounding regions.

22. The computer-program product of claim 21 , comprising code for causing the electronic device to determine the subset of the plurality of bounding regions further based on a centeredness of each of the plurality of bounding regions relative to the selected area.

23. The computer-program product of claim 21 , comprising code for causing the electronic device to determine the subset of the plurality of bounding regions further based on a comparison between a color histogram of each bounding region and a color histogram of each respective surrounding region.

24. The computer-program product of claim 21 , comprising code for causing the electronic device to determine the subset of the plurality of bounding regions further based on an average size of the plurality of bounding regions.

25. The computer-program product of claim 21 , comprising code for causing the electronic device to perform one or more of object recognition, object tracking, focusing, object removal, image enhancement, cropping or compression.

26. The computer-program product of claim

Assignees

• Qualcomm Inc

Inventors

• Mannino Matteo Toti
• Zhong Xin
• Gao Dashan
• Dane Gokce

Classifications

• G06T7/11

  Region-based segmentation · CPC title

• G06F3/0488

  using a touch-screen or digitiser, e.g. input of commands through traced gestures · CPC title

• G06T2207/30196

  Human being; Person · CPC title

• G06T2207/10024

  Color image · CPC title

• G06T2210/12

  Bounding box · CPC title