Back to results
US 12,530,750 B2Granted
Image processing method and apparatus, electronic device, storage medium and chip
AssigneeBeijing Xiaomi Mobile Software Co., Ltd.
InventorsShuai Liu, Jingyuan Xiao, Pan Ye, Chaoyu Feng, Lei Lei
Life of this patent
Estimating the term…
Abstract
An image processing method is provided. The method includes: obtaining a to-be-processed image; extracting attribute information of the to-be-processed image; determining an image processing strategy corresponding to the to-be-processed image according to the attribute information; and obtaining a target image by processing the to-be-processed image according to the image processing strategy.
Claims18
An image processing method, comprising:
- obtaining a to-be-processed image,
- extracting attribute information of the to-be-processed image,
- determining an image processing strategy corresponding to the to-be-processed image according to the attribute information, and
- obtaining a target image by processing the to-be-processed image according to the image processing strategy,
- wherein the attribute information of the to-be-processed image comprises alignment difficulty of each of at least one to-be-aligned image region and an aligned image region,
- determining the image processing strategy corresponding to the to-be-processed image according to the attribute information comprises:
- determining a target image alignment strategy corresponding to each of the at least one to-be-aligned image region according to the alignment difficulty of each of the at least one to-be-aligned image region, and
- obtaining the target image by processing the to-be-processed image according to the image processing strategy comprises:
- obtaining a pixel corresponding relation between corresponding to-be-aligned image regions in the to-be-processed image and a candidate image by aligning the corresponding to-be-aligned image regions according to the target image alignment strategy, wherein the candidate image is adjacent to the to-be-processed image,
- obtaining a fused image of each of the at least one to-be-aligned image region by fusing the corresponding to-be-aligned image regions according to a preset fusion strategy and the pixel corresponding relation between the corresponding to-be-aligned image regions,
- obtaining a fused image of the aligned image region by fusing a plurality of aligned image regions corresponding to each other in the to-be-processed image and the candidate image according to the preset fusion strategy, and
- obtaining the target image by splicing the fused image of each of the at least one to-be-aligned image region and the fused image of the aligned image region.
9 more elements
An electronic device, comprising:
- a memory storing a computer program;
- and
- a processor, when executing the computer program in the memory, is configured to:
- obtain a to-be-processed image,
- extract attribute information of the to-be-processed image,
- determine an image processing strategy corresponding to the to-be-processed image according to the attribute information, and
- obtain a target image by processing the to-be-processed image according to the image processing strategy,
- wherein the attribute information of the to-be-processed image comprises alignment difficulty of each of at least one to-be-aligned image region and an aligned image region, and the processor is further configured to:
- determine a target image alignment strategy corresponding to each of the at least one to-be-aligned image region according to the alignment difficulty of each of the at least one to-be-aligned image region,
- obtain a pixel corresponding relation between corresponding to-be-aligned image regions in the to-be-processed image and a candidate image by aligning the corresponding to-be-aligned image regions according to the target image alignment strategy, wherein the candidate image is adjacent to the to-be-processed image,
- obtain a fused image of each of the at least one to-be-aligned image region by fusing the corresponding to-be-aligned image regions according to a preset fusion strategy and the pixel corresponding relation between the corresponding to-be-aligned image regions,
- obtain a fused image of the aligned image region in the to-be-processed image by fusing a plurality of aligned image regions corresponding to each other in the to-be-processed image and the candidate image according to the preset fusion strategy, and
- obtain the target image by splicing the fused image of each of the at least one to-be-aligned image region and the fused image of the aligned image region.
10 more elements
Dependencies are inferred from the claim text.