Reduced reference image quality assessment based on wavelet domain singular value decomposition
Feiyan Zhang, Tao Sun, Ya-Fei Tu, Qianqing Qin · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2009
The traditional image quality assessment methods based on pixels have many limitations. Such as the lack of consideration of the image structure, or the need of a complete reference image. To avoid these problems, this paper presented a new image quality assessment method based on weighted singular value decomposition in wavelet domain (WWSVD). In this algorithm, the singular value vector difference and the mean bias between the original image and the distorted image are considered to evaluate the distortion degree. Many tests were conducted to evaluate the performance, the 227 testing images of JPEG2000 compression were come from the Live Image Quality Assessment Database, Release 2005. The results showed a great improvement in both the consistency with the DMOS (Differential Mean Opinion Score, DMOS) and the stability when applied to a large range of compression rates.