一种局部自适应内窥镜图像降噪模型

在内窥镜图像处理中,如何消除图像中的噪声一直是个热点问题。由于图像二进小波变换在每次分解时不进行下抽样,所以其表示同小波级数相比是冗余的,且图像二进小波变换的部分系数扰动不会带来重构图像的严重失真。因此,在相同的误判概率下,二进小波变换的图像去噪效果会好于小波级数变换的图像去噪效果。基于这个思想,文章从二进小波理论入手,提出一种自适应二进小波去噪模型,简称ADWD。该方法利用图像信息、噪声信息与小波系数之间的关系,采用局部自适应的方法识别噪声像素,避免了直接确定噪声门限的困难。实验结果及分析表明该方法对Gaussian噪声和Pepper噪声均有较高的信噪比,且对图像的细节有较好的保持能力。

A Probability Model for Local Adaptive Denoising with Medical Electronic Endoscope Image

Image denoising are always hot problems in endoscope image processing.Since downsampling does not take place in image dyadic wavelet transform at each level,image representation in dyadic wavelet domain compared with wavelet series reconstruction is very redundant and part of disturbance of image dyadic wavelet coefficients in transform domain will not lead to serious distortion.Therefore,with the same error decision probability,the better reconstruction can be expected.Based on these ideas,a probability model based on the adaptive dyadic wavelet denoising(ADWD)is proposed.Using the connection of image information,noise information,and wavelet coefficients,ADWD identifies noise pelses by a local adaptive model and avoids the difficulty of directly ensuring noise threshold.Experimental results and analysis are given to demonstrate the validity of the proposed model for Gaussian noise and Pepper noise,and the ability of keeping images details.