一种改进的图像去噪与增强模型  

Improved Model for Image Denoising and Enhancement

作　　者：赵杰[1] 裴建英 门国尊[2] 

机构地区：[1]河北大学电子信息工程学院,河北保定071000 [2]河北大学经济学院,河北保定071000

出　　处：《电视技术》2013年第23期31-34,共4页Video Engineering

基　　金：河北省卫生厅科研基金资助项目(20120395)

摘　　要：图像的去噪和增强越来越成为制约图像后续处理的瓶颈,为此提出一种图像去噪与增强的混合模型。该模型在各向异性扩散模型的基础上引入边缘指示函数,达到快速识别边缘的目的。在冲激滤波器的基础上,引入含有时间变量的边缘判定函数,适时控制冲激幅度的大小。而后将上述两个模型结合起来,克服了扩散模型仅依赖梯度信息来控制扩散进程的弊端,也适时地锐化了边缘。实验表明该混合模型不仅可以很好地去除图像的斑点噪声,并且可以达到图像增强效果。A novel hybrid model which is about the image denoising and enhancement is proposed in this article, the image denoising and enhancement increasingly becomes a bottleneck restricting the follow-up image of a series of processing. On the basis of anisotropic diffusion model, an edge indicator function is introduced,which can achieve the purpose of identification of the edge quickly. On the basis of shock filter,the function containing the time variable for edge judgment is introduced,which can timely control the size of the shock amplitude. When the two models combined together,on the one hand, the drawbacks of the diffusion equation which simply relies on gradient information to control the diffusion process are overcome, and then, the edge can be sharpened in a timely manner. The experiments show that the hybrid model not only can remove the image speckle noise,but also can achieve the effect of image enhancement.

关 键 词：图像去噪 图像增强 各向异性扩散 边缘指示函数 冲激滤波器 

分 类 号：TN911.73[电子电信—通信与信息系统]