Quality assessment of Gaussian blurred images using symmetric geometric moments

A novel objective full-reference image quality assessment metric based on symmetric geometric moments (SGM) is proposed. SGM is used to represent the structural infiormation in the reference and test images. The reference and test images are divided into (8 x 8) blocks and the SGM up to fourth order for each block is computed. SGM of the corresponding blocks of the reference and test images are used to form the correlation index or quality metric of each block. The correlation index of the test image is then obtained by taking the average of all blocks. The performance of the proposed metric is validated through subjective evaluation by comparing with objective methods (PSNR and MSSIM) on a database of 174 Gaussian blurred images. The proposed metric performs better than PSNR and MSSIM by providing larger correlation coefficients and smaller errors after nonlinear regression fitting.