一种基于小波变换和数据融合降噪的图像边缘检测方法

提出的一种基于小波变换和数据融合降噪的边缘检测方法,是在边缘检测前先进行去噪处理,为避免去噪不完全、微分算子对噪声敏感,在边缘检测的同时增强了噪声,并把微分算子检测得到的边缘幅值图像融合与去噪相结合。最后,对融合后的图像进行灰度阈值处理和细化,得到边缘二值图像。实验结果表明:该方法在抑制噪声的同时能较好的检测出图像的边缘。

A Noise-restrained Method of Image Edge Detection Based on Wavelet Transform and Data Fusion

This paper presents a noise-restrained method of image edge detection based on wavelet transform and data fusion.With this method,the noises can be partially removed first.Since the derivative operators are sensitive to noise, they also enhance the noises when the edges are under detection.The data from the derivative operators are thus fused in combination with the restraining noises.Finally,the binary edge image is produced by the fused image transacted by threshold operation and thinned.Experimental results show that the edge can be well detected and the noises can be restrained to some extent by this method.