Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (28): 202-204.DOI: 10.3778/j.issn.1002-8331.2009.28.061

• 图形、图像、模式识别 • Previous Articles     Next Articles

Texture classification based on wavelet packet transform and ant colony algorithm

LI Feng,CAO Peng,LI Chun-yue,LV Hui   

  1. Computer and Communication Engineering Institute,Changsha University of Science & Technology,Changsha 410076,China
  • Received:2008-05-26 Revised:2008-09-04 Online:2009-10-01 Published:2009-10-01
  • Contact: LI Feng

基于小波包变换和蚁群算法的纹理分类

李 峰,曹 鹏,李春月,吕 回   

  1. 长沙理工大学 计算机与通信工程学院,长沙 410076
  • 通讯作者: 李 峰

Abstract: A new texture classification method which combining wavelet packet transform and ant colony algorithm is proposed.At first,image’s texture feature is extracted using wavelet packet transform,and then ant colony algorithm is used for training and classification.Experiments show that it is an effective attempt which wavelet packet transform and ant colony algorithm are applied to texture classification.

Key words: texture classification, wavelet packet transform, ant colony algorithm, feature extraction

摘要: 提出了一种小波包变换和蚁群算法相结合的纹理分类新方法。首先采用小波包变换提取纹理图像的纹理特征向量,然后用蚁群算法进行训练和分类。实验表明小波包变换和蚁群算法应用到纹理分类领域,是一次有效的尝试。

关键词: 纹理分类, 小波包变换, 蚁群算法, 特征提取

CLC Number: