Comparison between linear discrimination analysis and support vector machine for detection of pesticide on spinach leaf by hyperspectral imaging with excitation-emission matrix

The performances of support vector machine (SVM) and linear discrimination analysis (LDA) for detecting pesticide on spinach leaf were investigated. Fluorescence images of spinach leaves without any treatment, treated with pure water and methamidophos solution were taken under 561 different wavelength conditions to acquire hyperspectral excitation-emission matrix (EEM) data. Then LDA and SVM were applied to EEMs of pixels randomly sampled from the data for classification of treatment. Misclassification rates were 18.8% and 9.9% for LDA and SVM respectively. Also, the obtained results revealed that when SVM applied pixel-wise of hyperspectral data, methamidophos treated leaves could be distinguished visibly from the others.