一种用于图像匹配识别的高斯-脉冲混合噪声去除方法

摘要

简要分析了无人机所拍摄数字图像中噪声的产生原因与数学分布模型,结合图像匹配的实际需求,提出了一种高斯-脉冲噪声混合噪声去除方法,并采用ASIFT匹配算法对提出去噪方法的实际应用效果进行检验.该方法首先采用自适应中值滤波方法去除图像中的脉冲噪声,然后采用OWT SURE-LET算法去除图像中的高斯白噪声.实验结果表明:该算法不仅运算时间更短,而且图像匹配效果稳定.%The generation reason and mathematical distribution model of noise in the image obtained by UAV are briefly analyzed,and a hybrid demising method for Gaussian-impulse mixed noise is proposed and the practical application effect of the method is test by using ASIFT matching algorithm. The method can be described as follows:Firstly,remove the impulse noise of image by adaptive median filter. Secondly,OWT SURE-LET algorithm is utilized to denoise the Gaussian white noise. Experimental results show that the algorithm has stable image matching effect with less computation time.