| 基于排列组合熵和灰度特征的纹理分割 |
| |
| 引用本文： | 钱诚,范影乐,庞全. 基于排列组合熵和灰度特征的纹理分割[J]. 计算机应用, 2006, 26(3): 586-0588 |
| |
| 作者姓名： | 钱诚 范影乐 庞全 |
| |
| 作者单位： | 杭州电子科技大学,模式识别与图像处理实验室,浙江,杭州,310037;杭州电子科技大学,模式识别与图像处理实验室,浙江,杭州,310037;杭州电子科技大学,模式识别与图像处理实验室,浙江,杭州,310037 |
| |
| 基金项目： | 中国科学院资助项目;浙江省自然科学基金 |
| |
| 摘 要： | 提出了一种基于排列组合熵和灰度特征的纹理分割方法。该方法将不同方向上的排列组合熵与灰度均值、灰度方差结合起来构成一个多维特征向量，利用模糊C均值聚类算法进行聚类实现纹理图像的分割。实验结果表明该方法对纹理分布均匀的图像有着良好的分割效果。在保持较高纹理分割精度的前提下，该方法能减小计算复杂度，并且具有较强的鲁棒性和抗噪声能力。
|
| 关 键 词： | 纹理分割 排列组合熵 灰度特征 模糊C均值聚类 |
| 文章编号： | 1001-9081（2006）03-0586-03 |
| 收稿时间： | 2005-09-21 |
| 修稿时间： | 2005-09-21 |
Texture segmentation method based on permutation entropy and gray feature |
| |
| QIAN Cheng,FAN Ying-le,PANG Quan. Texture segmentation method based on permutation entropy and gray feature[J]. Journal of Computer Applications, 2006, 26(3): 586-0588 |
| |
| Authors: | QIAN Cheng FAN Ying-le PANG Quan |
| |
| Affiliation: | Laboratory of Pattern Recognition and Image processing, Hangzhou Diaazi University, Hangzhou Zhejiang 310037, China |
| |
| Abstract: | A method for texture segmentation was presented. According to a feature vector which was made up of the permutation entropies calculated in many different directions, gray average and gray deviation, the method made the texture segmentation by fuzzy c-means algorithm. The experiment results show that the method has a good performance on segmenting images with textures distributed uniformly. On the premise of keeping high precision in texture segmentation, the method reduces the computational complexity, and has the ablility of robustness and noise resistance. |
| |
| Keywords: | texture segmentation permutation entropy gray feature fuzzy c-means cluster |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用》浏览原始摘要信息 |
|
点击此处可从《计算机应用》下载全文 |
|
