基于小波变换的纹理图像分割

基于小波的纹理图像分割方法是把小波变换应用于纹理的特征提取。通过对原始纹理图像进行高阶小波分解，构成每个象素对应一个特征矢量，对所提取的特征利用均值举类算法进行分类，最终获得图像的分割结果。为了提高纹理分割图像的边缘准确性和区域性以及降低分割错误率，提出了利用特征加权来进行后分割的方法。

A Study Of Segmentation Of Textured Images Based on Wavelet Transform

The method of texture image segmentation based on wavelet-transforms to feature extraction . Through processing pyramid hierarchical wavelet for original images. each picture element correspond to a feature vector. The result of segment image can be get finally with the mean of duster-ing algorithm to classify the feature extracted. To improve the accuracy of boundary locations and region homogeneity as well as to reduce error rate in texture image segmentation, a novel approach based on using feature weighting is proposed in this paper.