Image processing method and apparatus

1. An image processing method, comprising:

searching for a next pixel of a skeleton branch of a target image based on an already-searched current pixel of the skeleton branch;

determining, based on a number of already-searched pixels of the skeleton branch, whether the skeleton branch is a burr branch; and

stopping searching in response to the number of the already-searched pixels of the skeleton branch reaching a threshold or that the already-searched current pixel of the skeleton branch is a branch point.

2. The method according to claim 1 , further comprising, before searching for the next pixel of the skeleton branch of the target image based on the already-searched current pixel of the skeleton branch:

determining an end point and a branch point in the target image, wherein the end point and the branch point are used for searching for the skeleton branch.

3. The method according to claim 2 , wherein searching for the next pixel of the skeleton branch of the target image based on the already-searched current pixel of the skeleton branch comprises:

searching for the next pixel of the skeleton branch based on the already-searched current pixel of the skeleton branch corresponding to an end point in the target image used as an anchor point.

4. The method according to claim 2 , wherein determining the end point and the branch point in the target image comprises:

based on values of eight neighboring pixels of the current pixel in the target image, determining whether the current pixel in the target image is the end point or the branch point.

5. The method according to claim 4 , wherein determining whether the current pixel in the target image is the end point or the branch point comprises:

in response to a sum of the values of the eight neighboring pixels of the current pixel in the target image being 1, determining that the current pixel is the end point.

6. The method according to claim 4 , wherein determining whether the current pixel in the target image is the end point or the branch point comprises:

in response to a sum of the values of the eight neighboring pixels of the current pixel in the target image being greater than or equal to 3 and values of at least three of the eight neighboring pixels are each less than or greater than a value of a previous neighboring pixel in a clockwise or counterclockwise direction by 1, determining that the current pixel is the branch point.

7. The method according to claim 2 , further comprising:

in response to a number of branch points being 0, determining, based on a number of foreground pixels of the skeleton branch, whether the skeleton branch is a burr branch.

8. The method according to claim 7 , wherein determining, based on the number of the foreground pixels of the skeleton branch, whether the skeleton branch is a burr branch comprises:

in response to the number of the foreground pixels of the skeleton branch being less than a threshold, determining that the skeleton branch is a burr branch; or

in response to the number of the foreground pixels of the skeleton branch being not less than the threshold, determining that the skeleton branch is not a burr branch.

9. The method according to claim 1 , wherein determining, based on the number of the already-searched pixels of the skeleton branch, whether the skeleton branch is a burr branch comprises:

in response to the number of the already-searched pixels of the skeleton branch reaching a threshold, determining that the skeleton branch is not a burr branch.

10. The method according to claim 1 , wherein determining, based on the number of the already-searched pixels of the skeleton branch, whether the skeleton branch is a burr branch comprises:

in response to the number of the already-searched pixels of the skeleton branch not reaching a threshold and the already-searched current pixel of the skeleton branch is a branch point, determining that the skeleton branch is a burr branch.

11. The method according to claim 1 , wherein a value of a foreground pixel in the target image corresponds to 1, and a value of a background pixel corresponds to 0.

12. The method according to claim 11 , wherein searching for the next pixel of the skeleton branch of the target image based on the already-searched current pixel of the skeleton branch comprises:

converting a value of the already-searched current pixel to 0; and

in response to only one foreground pixel being present in eight neighboring pixels of the already-searched current pixel, determining that the one foreground pixel is the next pixel of the skeleton branch.

13. The method according to claim 12 , further comprising:

in response to more than one foreground pixel being present in the eight neighboring pixels of the already-searched current pixel, determining that the already-searched current pixel is a branch point.

14. The method according to claim 12 , further comprising:

recording the already-searched current pixel, wherein a number of recorded pixels is the number of the already-searched pixels of the skeleton branch.

15. The method according to claim 14 , wherein recording the already-searched current pixel comprises:

storing position information of the already-searched current pixel into a memory.

16. The method according to claim 12 , further comprising:

in response to the skeleton branch being determined to be a burr branch, converting a value of an already-searched current branch point to 1; or

in response to the skeleton branch being determined not to be a burr branch, converting values of all the already-searched pixels of the skeleton branch to 1.

17. The method according to claim 1 , further comprising:

obtaining an input image, wherein a value of a foreground pixel of the input image corresponds to 1, and a value of a background pixel corresponds to 0; and

extracting at least one connected component of the input image to obtain at least one target image, wherein each of the at least one target image comprises one of the at least one connected component of the input image.

18. The method according to claim 1 , wherein a width of the skeleton branch is a single-pixel width.

19. An image processing apparatus, comprising:

a memory, storing computer executable instructions; and

a processor, configured to access the memory and execute the computer-executable instructions to:

search for a next pixel of a skeleton branch of a target image based on an already-searched current pixel of the skeleton branch;

determine, based on a number of already-searched pixels of the skeleton branch, whether the skeleton branch is a burr branch; and

stop searching in response to the number of the already-searched pixels of the skeleton branch reaching a threshold or that the already-searched current pixel of the skeleton branch is a branch point.

20. An image processing method, comprising:

searching for a next pixel of a skeleton branch of a target image based on an already-searched current pixel of the skeleton branch, comprising:

converting a value of the already-searched current pixel to a value representing a background pixel; and

in response to only one foreground pixel being present in eight neighboring pixels of the already-searched current pixel, determining that the one foreground pixel is the next pixel of the skeleton branch; and

determining, based on a number of already-searched pixels of the skeleton branch, whether the skeleton branch is a burr branch.