Denoising Based On Fractal Coding Of Images

Fractal image encoding is a novel method to image compression. Since it is proposed, there has been significant interest in it for its high compression rate and independent resolution. Most of the researches have been done to reduce its encoding time. And with the process of computer technology and fractal image encoding arithmetic, the time fractal encoding costs has been lessened from several hours to several seconds. Fractal image encoding has satisfied the need of factual application already.Fractal image encoding technology, with its continual progress, has been applied not only in its initial purpose, image compression, but in a multitude of fields, such as digital watermarking. However, to the best of our knowledge, little attention has been given to the use of such fractal-based methods for the purpose of image enhancement and restoration. If the noisy image is simply fractally coded, a significant amount of the noise is suppressed. Because when an image is polluted by noise, its fractal properties have been damaged and it will be difficult to find the optimal blocks to restore the image. So the noisy image is somehow denoised.We can go a step further and estimate the fractal code of the original noise-free image from that of the noisy image. The resulting fractal code yields a significantly enhanced and restored representation of the original noisy image. The experimental results showed when the compression rate is about 10, the noise is depressed effectively.And also, we propose several advanced methods to improve the quality of decoding image such as quad-tree dividing. The quad-tree dividing is a common dividing method of fractal image compression. It permits the use of different resolutions or block sizes for different parts of the image. The finer resolutions (smaller sub-blocks) will be used near edges and other high activity areas. These areas yield noisy fractal representations while preserving the edges well.And we also proposed an approach to eliminate the blocking artifacts of the encoding image employing its independent resolution of fractal coding. Firstly, the image was decoded at lower resolutions than the original.Then we restore the image to the original resolution by the bilinear interpolation techniques. Experiments show that the proposed scheme can eliminate the blocking artifactsThe enhancement is consistent with the human visual system where extra smoothing...