Image splicing method and apparatus
The present invention relates to an image splicing method and apparatus. The image splicing method includes: acquiring a first image and a second image; determining a to-be-processed region within the overlapping region, where a region within the overlapping region except the to-be-processed region is a remaining region; obtaining a weight value of each adjacent pixel pair of the remaining region; setting a weight value of an adjacent pixel pair within the to-be-processed region; determining a splicing path having the least seam line intensity of all splicing paths; and performing image splicing on the first image and the second image along the optimal seam line. According to the image splicing method and apparatus of the present invention, a seam line can be excluded from a to-be-processed region, so as to ensure that the to-be-processed region is spliced naturally and to improve subjective perception of a user in viewing an image.
1. An image splicing method, comprising:
acquiring a first image and a second image, wherein an overlapping region exists between the first image and the second image;
determining a to-be-processed region within the overlapping region, wherein a region within the overlapping region except the to-be-processed region is a remaining region;
acquiring a luminance component or chrominance component of each pixel of the remaining region, and obtaining a weight value of each adjacent pixel pair of the remaining region according to luminance components or chrominance components of all the pixels of the remaining region;
setting a weight value of each adjacent pixel pair within the to-be-processed region, wherein a weight value of any adjacent pixel pair of the to-be-processed region is greater than a weight value of any adjacent pixel pair of the remaining region;
determining a splicing path having the least seam line intensity of all splicing paths within the overlapping region as an optimal seam line, wherein the seam line intensity is a sum of weight values of all adjacent pixel pairs that the splicing path goes through; and
performing image splicing on the first image and the second image along the optimal seam line.
2. The image splicing method according to claim 1 , wherein the setting a weight value of each adjacent pixel pair within the to-be-processed region comprises:
selecting the largest weight value of weight values of all the adjacent pixel pairs within the remaining region; and
setting the weight value of each adjacent pixel pair within the to-be-processed region to be greater than the largest weight value.
3. The image splicing method according to claim 1 , wherein the setting a weight value of each adjacent pixel pair within the to-be-processed region comprises:
acquiring a luminance component or chrominance component of each pixel of the to-be-processed region, and obtaining a weight value of each adjacent pixel pair of the to-be-processed region according to luminance components or chrominance components of all the pixels of the to-be-processed region;
selecting the largest weight value of weight values of all the adjacent pixel pairs within the remaining region and all adjacent pixel pairs within the to-be-processed region; and
setting the weight value of each adjacent pixel pair within the to-be-processed region to be greater than the largest weight value.
4. The image splicing method according to claim 1 , wherein the determining a to-be-processed region within the overlapping region comprises:
determining the to-be-processed region according to a preset size within the overlapping region, wherein a size of the to-be-processed region is the same as the preset size.
5. The image splicing method according to claim 1 , wherein the determining a to-be-processed region within the overlapping region comprises:
determining a position and size of a face region in the first image, and determining a position and size of a face region in the second image; and
determining the to-be-processed region within the overlapping region according to the position and size of the face region in the first image and the position and size of the face region in the second image.
6. An image splicing apparatus, comprising:
a processor, and a computer readable storage medium storing computer executable instructions, the processor configured to execute the computer executable instructions which, when executed, configure the apparatus to:
acquire a first image and a second image, wherein an overlapping region exists between the first image and the second image;
determine a to-be-processed region within the overlapping region, wherein a region within the overlapping region except the to-be-processed region is a remaining region;
acquire a luminance component or chrominance component of each pixel of the remaining region, and obtain a weight value of each adjacent pixel pair of the remaining region according to luminance components or chrominance components of all the pixels of the remaining region;
set a weight value of each adjacent pixel pair within the to-be-processed region, wherein a weight value of any adjacent pixel pair of the to-be-processed region is greater than a weight value of any adjacent pixel pair of the remaining region;
determine a splicing path having the least seam line intensity of all splicing paths within the overlapping region as an optimal seam line, wherein the seam line intensity is a sum of weight values of all adjacent pixel pairs that the splicing path goes through; and
perform image splicing on the first image and the second image along the optimal seam line.
7. The image splicing apparatus according to claim 6 , wherein the processor configured to execute the computer executable instructions which, when executed, configure the apparatus to:
select the largest weight value of weight values of all the adjacent pixel pairs within the remaining region; and
set the weight value of each adjacent pixel pair within the to-be-processed region to be greater than the largest weight value.
8. The image splicing apparatus according to claim 6 , wherein the processor configured to execute the computer executable instructions which, when executed, configure the apparatus to:
acquire a luminance component or chrominance component of each pixel of the to-be-processed region, and obtain a weight value of each adjacent pixel pair of the to-be-processed region according to luminance components or chrominance components of all the pixels of the to-be-processed region;
select the largest weight value of weight values of all the adjacent pixel pairs within the remaining region and all adjacent pixel pairs within the to-be-processed region; and
set the weight value of each adjacent pixel pair within the to-be-processed region to be greater than the largest weight value.
9. The image splicing apparatus according to claim 6 , wherein the processor configured to execute the computer executable instructions which, when executed, configure the apparatus to:
determine the to-be-processed region according to a preset size within the overlapping region, wherein a size of the to-be-processed region is the same as the preset size.
10. The image splicing apparatus according to claim 6 , wherein the processor configured to execute the computer executable instructions which, when executed, configure the apparatus to:
determine a position and size of a face region in the first image, and determine a position and size of a face region in the second image; and
determine the to-be-processed region within the overlapping region according to the position and size of the face region in the first image and the position and size of the face region in the second image.