A reduced reference approach based on bidimensional empirical mode decomposition for image quality assessment

In this paper, we present a reduced reference method for image quality assessment (RRIQA). This method is based on statistical properties of the bidimensional empirical mode decomposition (BEMD) components, called intrinsic mode function (IMF). First we decompose both reference and distorted images to IMFs, then we compute the distance between marginal probability distributions of each IMF coefficients of the reference image, and its corresponding IMF of the distorted image using the Kullback Leibler divergence (KLD) as a measure of image distortion. To summarize the histogram of each IMF coefficients of the reference image, we use the Generalized Gaussian density model (GGD), in order that only a vector of few features will be needed for the image quality assessment(IQA) purpose. This method is simple to implement and it outperforms some existing results especially for the blur and the white noise distortion.