An edge-preserved image denoising technique based on iterated function systems

In this paper, a new fractal-based image denoising method is proposed which can reserve the edges and remove the blocky artifacts in a denoised image. Our proposed method employs the decoupling property of the fractal code instead of the conventional fractal coding using the contrast scaling and offset parameters. This decoupling property makes it possible to denoise images more effectively and flexibly. In order to improve the visual quality of a denoised image, a range-block partitioning scheme is used to generate a set of overlapping sub-images, and each of the sub-images is represented by range-block mean values and contrast scaling factors to remove the noise. These sub-images are then averaged to produce an optimal denoised image. Experimental results show that our proposed method can achieve, on average, 4.24dB and 1.09dB increase in PSNR in the low-noise (σ < 20) and the high-noise (σ ≥ 20) conditions, respectively, when compared to an exisiting fractal-based denoising algorithm.