Quality evaluation of DIBR 3D images based on blind watermarking

The quality evaluation of stereoscopic images is becoming increasingly important in 3D multimedia applications. Watermarking-based quality evaluation has been a promising technology for 3D content quality evaluation. In this work, we propose a novel quality evaluation scheme for depth-image-based rendering (DIBR) 3D images. The scheme utilizes the watermarking technique to evaluate the quality of watermarked images under various distortions. In this scheme, the watermark is embedded into the selected coefficients of dual-tree complex wavelet transform sub-bands of the center view. The virtual left and right views are synthesized from the watermarked center view and the associated depth map using the DIBR technique at the receiver side. The watermark can be detected from the three views individually, and the quality of these views under various attacks can be estimated by examining the degradation of corresponding extracted watermarks. In addition, the quality evaluation is made possible by checking the generated mapping curve, which maps the normalized correlation of the extracted watermark to the quality measure of the watermarked image under distortions. There is a high correlation between the estimated quality and the calculated quality. The experimental results demonstrate that the proposed scheme has good performance of quality evaluation for DIBR 3D images under JPEG compression, JPEG 2000 compression, Gaussian noise, and Gaussian blur. Moreover, our proposed scheme exhibits superiority over other related methods in terms of evaluation accuracy.