Application of Support Vector Machine to shape recognition of plant disease spot

Shape recognition of plant disease spot is a learning problem with small training set of sample. A new recognition method, Support Vector Machine (SVM) was presented, which has excellent learning and generalization ability in solving learning problem with small training set of sample. In this paper, classification method of SVM for shape recognition of plant disease spot was discussed. Experiments with tomato disease were conducted and the results proved that the SVM method was fit for classification of plant disease spot, and outperformed other classification methods for shape recognition of plant disease spot. The comparison of different kernel functions for SVM shows that liner kernel function is most suitable for shape recognition of plant disease spot.