一种结合小波模极大值法和Canny算子的目标提取方法

A Target Extraction Method Combining Wavelet Modulus Maximum Method and Canny Operator

针对基于小波变换的目标提取中忽略低频子图像的一些重要信息的问题.提出了一种基于小波变换的模极大值法和Canny算子的目标提取方法.在小波域中,通过求解局部小波系数模型的极大值点提取(检测)高频边缘,利用Canny算子提取(检测)低频边缘.然后根据融合规则对两个子图像边缘进行融合.实验结果表明,该方法不仅能有效地增强图像边缘,而且能准确地定位图像边缘.

This paper focuses on the problem of ignoring some important information of lowfrequency sub-images in target extraction based on wavelet transform.A modulus maxima method based on wavelet transform and a target extraction method based on Canny operator are proposed.In the wavelet domain,the high-frequency edges are extracted(detected) by solving the maximum value points of the local wavelet coefficient model,and the low-frequency edges are extracted(detected) by the Canny operator.The two sub-image edges are then fused according to the fusion rule.Experimental results show that this method can not only effectively enhance the edge of the image,but also accurately locate the edge of the image.