A novel objective quality assessment method of 3D video

This paper focuses on objective assessment methods of 3D video and presents a novel 3D objective quality assessment method that integrates perceived quality of image and depth. We chose 3D videos in left plus right format as evaluation object and got an overall 3D perception quality value by using the Radical Basis Function (RBF) neural network. The quality scores of image and depth were respectively calculated by SSIM and correlation coefficient algorithm. Experimental results show that the proposed algorithm correlates well with the subjective scores.

[1]  A. Gotchev,et al.  Classification of stereoscopic artefacts , 2009 .

[2]  Patrick Le Callet,et al.  Stereoscopic images quality assessment , 2007, 2007 15th European Signal Processing Conference.

[3]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[4]  A. Parker.  Binocular depth perception and the cerebral cortex , 2007, Nature Reviews Neuroscience.

[5]  Andreas Klaus,et al.  Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure , 2006, 18th International Conference on Pattern Recognition (ICPR'06).