Image quality assessment based on the correlativity and the discrete wavelet transform

A novel image quality assessment is proposed based on the characteristics of wavelet coefficients of images and the correlativity in this paper. Firstly, the reference image and the distorted images are decomposed into several levels by means of the wavelet transform respectively. Secondly, the approximation and detail coefficients of the reference image are as the reference sequences and the approximation and detail coefficients of the distorted images are as the comparative sequences respectively. And the correlativity values are calculated between the reference sequences and the comparative sequences respectively. Moreover, the image quality assessment matrix of every distorted image can be constructed based on the correlativity values and the image quality can be assessed. The algorithm makes full use of perfect integral comparison mechanism of the correlativity and the well matching of discrete wavelet transform with multi-channel model of human visual system. The experimental results show that the proposed algorithm can not only evaluate the integral and detail quality of image fidelity accurately but also bears more consistency with the human visual system than the traditional method PSNR.