37th IEEE Asilomar Conference on Signals, Systems and Computers, Nov. 2003

 

Multi-scale Structural Similarity for Image Quality Assessment

Zhou Wang1, Eero P. Simoncelli1 and Alan C. Bovik2

 (Invited Paper)

1Laboratory for Computational Vision (LCV), New York University, New York, NY 10003

2Laboratory for Image and Video Engineering (LIVE), The University of Texas at Austin, Austin, TX 78712

PDF File (492K)

Abstract: The structural similarity image quality assessment approach is based on the assumption that the human visual system is highly adapted for extracting structural information from the scene, and therefore a measure of structural similarity can provide a good approximation to perceived image quality. This paper proposes a novel multi-scale structural similarity method, which supplies more flexibility than single-scale methods in incorporating the variations of image resolution and viewing condition. Experimental comparisons demonstrate the effectiveness of the proposed method.