Blind Image Quality Assessment by Visual Neuron Matrix

Abstract

Modeling of the human visual system (HVS) is considered to be the most appropriate method to evaluate the image quality. The natural image statistics (NIS) can not only reflect certain response characteristics of the visual system, but also provide accurate quantitative descriptions of the HVS. Inspired by this fact, a visual model, which is named as visual neuron matrix (VNM), is built by a statistical learning process on natural image samples. On the basis of the VNM, a blind image quality assessment (BIQA) model is proposed. First, the VNM is obtained by independent component analysis, which can simulate the visual neurons in the cerebral cortex as well as extract the visual features from test images. Then, a regression model (neural network or support vector machine) is used to associate the visual features with the quality score of a test image. The experimental results show that the proposed method is more competitive and efficient than the state-of-the-art BIQA models.