Method, apparatus, and computer readable medium for adjusting color annotation of an image

Patent metadata

Field	Value
Publication number	US-10909724-B2
Application number	US-201816233863-A
Country	US
Kind code	B2
Filing date	Dec 27, 2018
Priority date	Dec 29, 2017
Publication date	Feb 2, 2021
Grant date	Feb 2, 2021

Abstract

Embodiments of the present disclosure provide a method, apparatus, and computer readable storage medium for processing an image. The method described herein includes determining a to-be-processed first region and a to-be-processed second region in an input image, the first region is at least partially filled with a first color, the second region is at least partially filled with a second color, and the first region and the second region are adjacent regions sharing a common boundary region. The method further includes shrinking the first region and the second region, to enable neither of the shrunken first region and the shrunken second region to include the boundary region. The method further comprises expanding the shrunken first region and the shrunken second region, to enable the boundary region to be filled with at least one color of the first color or the second color.

First claim

What is claimed is:

1. A method for processing an image, the method comprising:
determining a to-be-processed first region and a to-be-processed second region in an input image, the first region at least partially filled with a first color, the second region at least partially filled with a second color, the first region and the second region being adjacent regions sharing a common boundary region, wherein the determining comprises:
acquiring a color dictionary, the color dictionary indicating a plurality of valid colors filled in regions in the input image; and
determining the first region and the second region adjacent to each other, in response to determining that the first color and the second color are included in the plurality of valid colors;

shrinking the first region and the second region, to enable neither of the shrunken first region and the shrunken second region to include the boundary region; and
expanding the shrunken first region and the shrunken second region, to enable the boundary region to be filled with at least one color of the first color or the second color,
wherein the color dictionary further indicates the first color being associated with a first priority level and the second color being associated with a second priority level, and the expanding the shrunken first region and the shrunken second region comprises:
executing image dilation on the shrunken first region, to add a plurality of pixels having the first color near a first boundary of the shrunken first region;
executing image dilation on the shrunken second region, to add a plurality of pixels having the second color near a second boundary of the shrunken second region; and
executing image superposition on the dilated shrunken first region and the dilated shrunken second region obtained after the image dilation based on the first priority level and the second priority level.

2. The method according to claim 1 , wherein the shrinking the first region and the second region comprises:
removing the boundary region from the first region and the second region.

3. The method according to claim 1 , wherein the shrinking the first region and the second region comprises:
executing image erosion on the first region, to remove a plurality of pixels near a first boundary of the first region in the first region; and
executing image erosion on the second region, to remove a plurality of pixels near a second boundary of the second region in the second region.

4. The method according to claim 1 , wherein the executing image superposition on the dilated shrunken first region and the dilated shrunken second region obtained after the image dilation comprises:
enabling the dilated shrunken first region obtained after the image dilation to at least partially cover the dilated shrunken second region obtained after the image dilation, in response to the first priority level being higher than the second priority level.

5. The method according to claim 1 , wherein the input image comprises a third region, the third region is filled with a third color excluded in the plurality of valid colors, and the method further comprises:
selecting a fourth color best matching the third color from the plurality of valid colors; and
filling the third region with the fourth color to replace the third color.

6. The method according to claim 5 , wherein the selecting the fourth color comprises:
determining respective distances between the third color and the plurality of valid colors, the distances indicating corresponding differences between the third color and the plurality of valid colors; and
selecting a valid color having a smallest distance between the valid color and the third color from the plurality of valid colors as the fourth color.

7. The method according to claim 6 , wherein the third color is represented by a first vector, the fourth color is represented by a second vector, and the distance between the third color and the fourth color is a Euclidean distance between the first vector and the second vector.

8. An apparatus for processing an image, comprising:
at least one processor; and
a memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:
determining a to-be-processed first region and a to-be-processed second region in an input image, the first region at least partially filled with a first color, the second region at least partially filled with a second color, the first region and the second region being adjacent regions sharing a common boundary region, wherein the determining comprises:
acquiring a color dictionary, the color dictionary indicating a plurality of valid colors filled in regions in the input image; and
determining the first region and the second region adjacent to each other, in response to determining that the first color and the second color are included in the plurality of valid colors;

shrinking the first region and the second region, to enable neither of the shrunken first region and the shrunken second region to include the boundary region; and
expanding the shrunken first region and the shrunken second region, to enable the boundary region to be filled with at least one color of the first color or the second color,
wherein the color dictionary further indicates the first color being associated with a first priority level, and the second color being associated with a second priority level, and the expanding the shrunken first region and the shrunken second region comprises:
executing image dilation on the shrunken first region, to add a plurality of pixels having the first color near a first boundary of the shrunken first region;
executing image dilation on the shrunken second region, to add a plurality of pixels having the second color near a second boundary of the shrunken second region; and
executing image superposition on the dilated shrunken first region and the dilated shrunken second region obtained after the image dilation based on the first priority level and the second priority level.

9. The apparatus according to claim 8 , wherein the shrinking the first region and the second region comprises:
removing the boundary region from the first region and the second region.

10. The apparatus according to claim 8 , wherein the shrinking the first region and the second region comprises:
executing image erosion on the first region, to remove a plurality of pixels near a first boundary of the first region in the first region; and
executing image erosion on the second region, to remove a plurality of pixels near a second boundary of the second region in the second region.

11. The apparatus according to claim 8 , wherein the executing image superposition on the dilated shrunken first region and the dilated shrunken second region obtained after the image dilation comprises:
enabling the dilated shrunken first region obtained after the image dilation to at least partially cover dilated shrunken the second region obtained after the image dilation, in response to the first priority level being higher than the second priority level.

12. The apparatus according to claim 8 , wherein the input image comprises a third region, the third region is filled with a third color excluded in the plurality of valid colors, and the operations further comprises:
selecting a fourth color best matching the third color from the plurality of valid colors; and
filling the third region with the fourth color to replace the third color.

13. The apparatus according to claim 12 , wherein the selecting the fourth color comprises:
determining r

Assignees

• Baidu online network technology beijing co ltd

Inventors

• Duan Xiong
• Lang Xianpeng
• Zhou Wang
• Yan Miao
• Zhan Yifei
• Ma Changjie
• Jin Yonggang

Classifications

• G06T7/12 Primary

  Edge-based segmentation · CPC title

• G06T7/90 Primary

  Determination of colour characteristics · CPC title

• G06T11/10

  Texturing; Colouring; Generation of textures or colours (retouching, inpainting or scratch removal G06T5/77) · CPC title

• G06V10/56

  relating to colour · CPC title

• G06V10/267

  by performing operations on regions, e.g. growing, shrinking or watersheds · CPC title