DIBR-synthesized image quality assessment based on local entropy analysis

The perceptual quality of Depth-Image-Based- Rendering (DIBR) synthesized images is essential for threedimensional video applications. However, traditional image quality assessment (IQA) algorithms almost unavailable for DIBR- synthesized images, because the specific types of distortions appeared in DIBR-synthesized images are rarely considered in traditional IQA algorithms. In this paper, a new full-reference image quality assessment (FR-IQA) algorithm is proposed to evaluate the quality of DIBR-synthesized images. The image local entropy is analyzed firstly dedicate to represent the new types of distortions in DIBR-synthesized image, then the local entropy similarity map between reference image and distorted image is calculated. Finally, the quality score of distorted image is computed from the similarity map of local energy. Experimental results show that our proposed method outperforms the conventional state-of-the-art FR-IQA algorithms on the IRCCyN/IVC DIBR images database.