摘要
用分水岭方法进行图像分割时,容易造成图像的过度分割。为了克服这种缺点,提出了一种基于小波变换和分水岭算法的图像分割方法,该方法首先利用小波变换产生多分辨率图像,然后对最低分辨率图像进行应用标记的分水岭分割,得到初始的分割区域,最后利用区域标记和小波反变换,得到高分辨率图像的分水岭分割结果,从而较好地解决了分水岭变换方法中的过度分割问题。
Watershed based image segmentation has the drawback of over - segmentation. Combining the wavelet and watersheds , this paper proposes an image segmentation method which solves this problem. Wavelet transform is first used to create multi - resolution images. Then the marker- controlled watershed segmentation algorithm is applied to ,segment the lowest- resolution image and get the initial watershed segmentation. At last, labeled images and inverse wavelet transform are used together to get the full - resolution image. The experiment results show that this method is a solution for the over- segmentation problem .
出处
《计算机技术与发展》
2006年第1期17-19,22,共4页
Computer Technology and Development
关键词
小波变换
分水岭
图像分割
数学形态学
wavelet transform
watershed
image segmentation
mathematical morphology
