计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (18): 221-223.

• 工程与应用 • 上一篇    下一篇

基于遗传算法和支持向量机的玉米品种识别

王宏勇,侯惠芳,刘素华   

  1. 河南工业大学 信息科学与工程学院,郑州 450001
  • 收稿日期:2007-09-18 修回日期:2007-12-11 出版日期:2008-06-21 发布日期:2008-06-21
  • 通讯作者: 王宏勇

Maize seed recognition based on genetic algorithm and multi-class SVM

WANG Hong-yong,HOU Hui-fang,LIU Su-hua   

  1. College of Information Science and Engineering,Henan University of Technology,Zhengzhou 450001,China
  • Received:2007-09-18 Revised:2007-12-11 Online:2008-06-21 Published:2008-06-21
  • Contact: WANG Hong-yong

摘要: 提出了一种基于遗传算法(GA)和支持向量机(SVM)的玉米种子的图像特征选择和分类识别的新方法。该方法首先用遗传算法对采集到的玉米种子图像的特征进行优化,而后采用决策二叉树的支持向量机分类算法对玉米品种进行识别。该分类算法将分类器分布在各个结点上,构成多类支持向量机,减少了分类器的数量和重复训练样本的数量。实验结果表明该方法能选出适合于识别的玉米种子特征并能对玉米种子进行正确地识别。

Abstract: A new image feature and variety method of maize seed recognition based on Support Vector Machine(SVM) and Genetic Algorithm(GA) is proposed.Firstly,this method optimizes the image feature of maize seed by genetic algorithm.Then,it uses multi-class SVM—decision binary tree to recognize the maize seed.This classification method distributes classifier to each node to constitute multi-class SVM,which reduces the number of SVM classifier and duplicates training samples.The experiment shows that this method can select the suitable maize seed image feature and recognize precisely the maize seeds.