摘要
基于经典的模型,提出一种新的扩散模型。该模型在第一阶段利用小波域wiener滤波时图像进行消噪,之后通过各向异性扩散去除伪。噪声图像经过方法处理后,既消除了小波去噪经常出现的伪效应,又避免了偏微分方程方法去噪中出现的阶梯效应,较好保存了细节,提高了峰值信噪比,大量实验表明它是一种有效的去噪方法。
A model of nonstandard diffusion is presented based classical Perona - Malik model. The adaptive wiener filtering in the wavelet domain is used to denoise contaminated image, and then anisotropic diffusion is used to smooth the Gibbs. Experimental results show that the model is effective in image processing while retaining details, improving the visual quality and avoiding the staircasing phenomenon at the same time.
出处
《电子科技》
2007年第6期47-50,共4页
Electronic Science and Technology
