计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (6): 68-70.

• 学术探讨 • 上一篇    下一篇

基于分类蚁群算法的彩色图像自动分类

毛 力,荚恒松,卞 锋   

  1. 江南大学 信息工程学院,江苏 无锡 214122
  • 收稿日期:2007-06-14 修回日期:2007-09-05 出版日期:2008-02-21 发布日期:2008-02-21
  • 通讯作者: 毛 力

Automatic classification of images based on classification ant colony algorithm

MAO Li,JIA Heng-song,BIAN Feng   

  1. School of Information Technology,Jiangnan University,Wuxi,Jiangsu 214122,China
  • Received:2007-06-14 Revised:2007-09-05 Online:2008-02-21 Published:2008-02-21
  • Contact: MAO Li

摘要: 为提升图像自动分类算法的通用性和鲁棒性,加快算法收敛速度,针对图像分类的特点,对传统蚁群算法进行改进,引入分类蚁群模型。随机蚂蚁识别统计图像类别,构建类别表,确定聚类中心;智能蚂蚁按相应的搜索前进策略进行分类。相比基本蚁群分类算法,该算法可以在较短的时间内完成图像的自动分类。

Abstract: To improve capability of auto classification algorithm and speed of algorithm,the ant colony algorithm based on classification is proposed.The stochastic ant realize classify images and ascertain center of conglomeration.The intellectual ant class the image.Comparing the other algorithm,the experiment indicates that this improve is more good.