The traditional image quality evaluation metric

such as PSNR

cannot reflect the visual perception to the image effectively. Concerming this issue a content-based image quality assessment metric is proposed in this paper. Based on a structural-similarity-based metric(SSIM) with some modifications

our approach partitions an image into three parts: edges

textures and flat regions according the content of the image and then we apply the SSIMs to fuse each part using Sugeno fuzzy integral. The new metric combines the position and quantity information with the similarity of the image structural information and gives comprehensive evaluation to the quality of the specified image. The experiment results illustrate that the proposed metric has good correlation to the subjective perception

and can reflect the image quality effectively.