Research on SVM Plant Leaf Identification Method Based on CSA

• 作者: Haijun Lin Xuhui Zhang Yang Liu Yukun Liu
• 来源期刊: 国际计算机前沿大会会议论文集
• 学科: 社会科学
• 关键词: Image identifying Support VECTOR machine CLONAL selection algorithm GEOMETRIC FEATURES TEXTURE FEATURES
• 年，卷（期）: 2016,（2）
• 页码范围: 48-49
• 页数: 2页
• 分类号: C5

摘要

In view of the longer training and recognition time of plant leaf classifier,this paper proposes a method of blade recognition based on the combination of clonal selection algorithm and support vector machine.The method uses the blade geometry and texture features as the identification feature,building a blade recognition classifier based on support vector machine,in order to obtain the optimal kernel function parameter and the penalty factor,using cross validation characteristics of immune clonal selection algorithm to optimize the kernel function parameter and the penalty factor.Experimental results show that compared with BP neural network and other two methods,the proposed method has a higher recognition accuracy and training speed.