摘要
讨论了一种新的基于非线性扩散方程的图像去噪方法。在分析中值曲率扩散模型去噪原理的基础上,将角点检测因子引入到该模型中控制扩散速度,使改进后的方程在非角点处进行较大扩散,在角点处停止扩散。实验结果表明,该方法不仅有效去除了图像中的噪声,而且较好地保留了图像中的角点信息,去噪效果令人满意。
A new nonlinear diffusion - based image denoising method is proposed in this work. At first the principle of Mean Curvature Motion equation is analyzed. After that a factor of corner detection is introduced into the model to control the speed of diffusion,which is faster in the position of no corner and stops in the position of corners. Experimental results show that the denoising method can not only remove the noise but also preserve the information of corners in the image.
出处
《现代电子技术》
2008年第7期188-190,共3页
Modern Electronics Technique
