Method of Non-reference Image Quality Assessment of SSIM Based on Regional Weighted Entropy
Tong Zhang, Zhao Shuna, Li Xue · 2014
The traditional SSIM haven't considered the limitation of the Human Visual System, which different attention paid to different area in the same picture, and information of the picture itself, leading to the final results are inconsistent between objective and subjective evaluating effects. A new image weighted index, which is regional weighted information entropy index, is put forward to solve this problem. This method divide image into visual region of interest based on the image edge features. By calculated space influence factor and regional entropy of each interest area, formulating regional weighted entropy. The weighted value of each visual interest region is generated after normalization of regional weighted information entropy, and the average weighted structural similarity of all visual interest areas is used as the image assessing index. Test results show that the new method fits human visual system characteristics, and correlates well with subjective perception scores.