Image Quality Assessment using PSO-GSA Optimization Algorithm

In this paper, we present new method to the objective image quality evaluation based on discrete wavelet transform (DWT) and Particle Swarm Optimization and Gravitational Search algorithms (PSO-GSA). DWT is applied on the difference between the original and degraded image, which is decomposed into approximation and detail sub-bands. DWT coefficients are computed using Haar wavelet filter banks. The coefficients are used to compute new image quality measure that is defined as perceptual weighted difference between coefficients of original and degraded image. Weighting factors for wavelet sub-bands have been experimentally determined using PSO-GSA algorithm to achieve the best possible correlation with results of subjective (perceptual) image quality evaluation. Test case results demonstrate that the proposed technique has high correlation with results of subjective test and low computational time important for real-time applications. The test cases also show that this image quality assessment method has a better results than traditional method and it can accurately reflect the image visual perception of the human eye.