一种基于改进分形编码的图像去噪方法

An Image Denoising Method Based on Improved Fractal Coding

提出了一种针对加性白高斯噪声(AWGN)的改进分形图像去噪方法.该方法在改进的分形编码过程中采用二次函数灰度预测,使得对无噪图像的编码效果优于传统分形编码.在改进分形编码的基础上,改进的分形图像去噪方法通过带噪图像估计原始无噪图像的分形编码参数,从而在分形解码过程中达到去除噪声的目的.实验结果比较表明,改进的分形去噪方法具有很好的去噪效果.

An improved fractal image denoising algorithm for removing additive white Gaussian noise （AWGN） was presented by adopting quadratic gray-level function. In terms of the quality of the fractal representation of noiseless images, the improved fractal coding generally performs better than the classic fractal coding. Based on the improved fractal coding, new fractal image denoising is implemented by estimating the fractal gray-level coefficients of the quadratic function of the noiseless image from its noisy observation, and hence to remove the noise in the decoding procedure. The experimental results show that, compared with other classic image denoising algorithms, the improved fractal denoising method can improve the quality of the restored image efficiently.