Abstract:

The non-subsampled contourlet transform has multi-scale and multi-directional characteristics, which can extract the image texture and structure information accurately and precisely simulate the multi-resolution characteristic of the human visual system. Based on this, we propose a blind image quality assessment algorithm based on non-subsampled contourlet transform. Firstly, the algorithm decomposes the images on spatial domain by non-subsampled contourlet transform. Secondly, the features such as high frequency amplitude, average gradient and information entropy, which can effectively reflect the characteristics of human visual distortion degree, are extracted in each direction. Finally, the features are input into the efficient multi kernel learning machine to learn and predict image quality scores. Cross experimental results on multi-kind distortion database and three single distortion databases show that the algorithm is superior in performance and can predict image quality distortion well and has very good subjective and objective consistency.

Key words: blind image quality assessment, non-subsampled contourlet transform, multiple kernel learning, information entropy