Research on SVM Plant Leaf Identification Method Based on CSA.

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.