In the process of image mosaic,there are differences in perspective,color and texture information,which seriously affect the quality of image mosaic.To solve this problem,this paper proposes an image stitching algorithm based on improved opti-mal stitching.In the aspect of image registration,the local homography model is improved based on the super-pixel segmentation al-gorithm,which improves the accuracy of image registration and weakens the influence of parallax on the image mosaic process.In the aspect of seam cutting,based on the consideration of color difference and gradient difference information in the original smooth-ing item,significant perceptual weight and texture information are added to the smoothing item.Experiments show that the algorithm improves the accuracy of image registration,protects the structure of visually significant objects,avoids the occurrence of disloca-tion and ghosting,and can splice high-definition natural wide field of view images.
关键词
图像配准/超像素分割/接缝切割/显著性感知/纹理信息
Key words
image registration/super pixel segmentation/joint cutting/significant perception/texture information
维普
万方数据