Plant Species Identification Based on Independent Component Analysis for Hyperspectral Data

By investigating the possibility of plant species classification based on independent component analysis (ICA) for hyperspectral data with minor difference, the framework of a general plant species classification model that consists of ICA based data reduction, classifier training and verification is proposed in this paper. Five different types of discriminant analysis classifiers including Linear, Quadratic, DiagLinear, DiagQuatic and Mahalanobis, with data reduction that based on principal components analysis (PCA) and ICA, are implemented and compared. Accuracy assessment of classification for real leaf hyperspectral data is demonstrated, indicating that data reduction based on ICA performs better than that of PCA. Moreover, the proposed classification model with ICA based data reduction and Quadratic Discriminant Analysis works best, and its accuracy is about 98.35% with dimension 25 reduced from 2500.