No-Reference PSNR Identification of MPEG Video Using Spectral Regression and Reduced Model Polynomial Networks

This letter proposes a no-reference MacroBlock (MB) level PSNR identification of compressed MPEG video. Features are extracted on MB basis from video bitstreams and reconstructed images. The identification problem is formalized using reduced model polynomial networks. The letter proposes a two-step identification solution in which supervised spectral regression is used to reduce the dimensionality of the feature vector prior to model estimation. Two identification scenarios are presented in the experimental results, namely, video sequence dependent and video sequence independent identification. Based on the various video sequences used in the experiments, it is shown that the average mean absolute difference between the actual and the identified PSNRs is 1 dB and 1.6 dB for the sequence dependent and sequence independent identification respectively.