基于Bubble小波的多尺度边缘提取

根据列车轮对图像的特性，主要探讨了基于小波分析的原理，并基于Bubble二进小波函数进行图像多尺度边缘提取。利用边缘相关判据排除噪声边缘，取边缘响应极大点作为配准控制点。实验结果显示，本方法能够很准确地提取出图像的主要边缘信息。

Multiscale Images Registration Approach Using Bubble Wavelet Transform to Extract Edge Feature

According to the properties of train wheel image , in this paper the concept of wavelet transform is introduced. The proposed approach applies wavelet transform to extract a number of feature points as the basis for registration. And multi scale edges of image are obtained. Each selected feature points is an edge point whose edge response is the maximum within a neighborhood. The results show that the edge has good property and can be used for matching of images.