Adaptive nonlinear diffusion processes for ringing artifacts removal on JPEG 2000 images

JPEG 2000 image coding standard aims to achieve high compression performance. As the bit rate decreases, visual degradation caused by information loss on an image becomes more and more visible. We propose an adaptive nonlinear diffusion method to reduce ringing artifacts while preserving and enhancing image edges. The diffusion coefficient is the linear combination of three membership functions that correspond to the different gradient scales. The parameters are tuned using a stochastic optimization technique so that the diffusion coefficient can adapt to the given image data to achieve optimal restoration performance. Experimental results on JPEG 2000 compressed images have shown the effectiveness of the proposed nonlinear diffusion processes for ringing artifacts removal.