Perceptual noise shaping in dual-tree complex wavelet transform for image coding

In this paper, we extend the idea of noise shaping for dual-tree complex wavelet transform (DCWT) image coding to a perceptual-based noise shaping. In classical noise shaping, the spatial error information is compensated by adding it back into the whole DCWT domain, which allows the retained to coefficients have better capability to approximate the original image. The proposed perceptual noise shaping introduces a perceptual weight to the spatial errors. The weight involves the structural similarity (SSIM) measurement and other adjustment parameters to shape the spatial errors. Experimental results show that the perceptual noise shaping has better results for visual quality and provides higher SSIM index than classical noise shaping. For example, the proposed perceptual noise shaping achieves an overall SSIM of 0.891 for the 8 bit 512×512 “barbara” compared to 0.878 in classical noise shaping when 5000 coefficients are retained.