Prediction of Structural Similarity Index of Compressed Video at a Macroblock Level

This letter proposes a multipass system for predicting the Structural Similarity Indices (SSIM) of compressed video. The prediction is performed in the absence of the original reference and it is carried out on macroblock basis. Distinguishing macroblock features are extracted from compressed bit streams and reconstructed videos. Optimal feature sets are then computed using stepwise regression. The multipass system uses reduced model polynomial regression for quality prediction. At intermediate passes, the predicted SSIM indices are concatenated to the original set of features allowing for higher prediction accuracy. The polynomial weights used for predicting the SSIM indices are computed in the final pass. Comparisons with existing work reveal that the proposed solution is more consistent and offers higher prediction accuracy.