摘要
苗木图像分割是形态参数提取的前提条件。利用小波变换及分开-合并法实现了对苗木图像的分割。对图像的色度分量进行小波变换。其变换系数作为分开-合并法中区域一致性的度量。通过改变小波变换的尺度,可以将边缘与噪声区分开来,减小图像分割中噪声带来的影响,有利于提高分割的准确性。实验表明,该算法取得了满意的结果。
Image segment is an essential technique to extract the morphology features. In this paper, the wavelet transform and the region splitting- merging are used to segment the image of a conifer seedling. Wavelet transform is performed on hue component of seedling image. The coefficient of wavelet transform is used as measure of region uniform in splitting - merging algorithm. The image edge and noise can be distinguished by changing scale of wavelet transform, and the adverse effect noise is able to be reduced. It is benefit to improve the accuracy of segment. The result of segment algorithm is satisfying.
出处
《东北电力学院学报》
2005年第6期9-13,共5页
Journal of Northeast China Institute of Electric Power Engineering
关键词
图像分割
形态参数
小波变换
分开-合并法
Simage segment
Morphology features
Wavelet transform
Splitting - merging algorithm
