基于特征探测函数的图像去噪  

Image Denoising Based on Feature Detection Function

作　　者：任丽莎[1] 贾瑞芝[1] 杨莹[1] 

机构地区：[1]重庆理工大学数学与统计学院,重庆400054

出　　处：《重庆理工大学学报（自然科学）》2011年第9期43-47,共5页Journal of Chongqing University of Technology：Natural Science

基　　金：重庆市科委项目(CSTC;2010BB2310)

摘　　要：借助于图像信息结构张量的思想,构造出一个图像特征探测函数,然后在结合TV正则项的各向异性扩散可以保持边界的特点以及高阶PDE可以降低块状效应的的优势,提出了一个新的加权的图像去噪模型。利用数值模拟实验说明此模型的有效性。Firstly, we construct an image feature detection function in term of the thought of image structure tensor. Secondly, combining the advantage of the TV regularization term＇ s anisotropic diffusion which can protect image edge well with the superiority of the high order PDE which can reduce stair case, we propose a new weighted image denoising model. Finally, we offer some experimental simula- tions and compare the results of our model with those of TV model. The results show that the restoration effect of our model is more effective than that of TV model.

关 键 词：TV模型 高阶PDE 特征探测函数 图像去噪 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP751.1[自动化与计算机技术—计算机科学与技术]