Stereo Image Retargeting Based on Salient Feature Classification
Stereo image retargeting algorithms often adopt the same strategy to retarget various images with different features,resulting in some serious retargeting distortions such as information loss,geometric distortion,and depth change.The factors that affect the quality of stereo image retargeting results mainly include the change of salient region shape and visual depth.To solve these problems,a stereo image retargeting method based on image salient feature classification is proposed.This method divides the image into two categories:non-salient region and salient region images and combines the stereo cropping method and the stereo warping method to adopt different retargeting strategies for various feature images to reduce information loss and geometric distortion.The depth information difference between the salient region and non-salient region is used,so the perceptive depth of the salient image can be better maintained.Experimental results show that the performance of the proposed method is superior to other algorithms in subjective comparison and objective quality assessment.
万方数据
维普
