Unsupervised Classifier Selection Approach for Hyperspectral Image Classification

International audienceGenerating accurate and robust classification maps from hy-perspectral imagery (HSI) depends on the users choice of the classifiers and input data sources. Choosing the appropriate classifier for a problem at hand is a tedious task. Multiple classifier system (MCS) combines the relative merits of the various classifiers to generate robust classification maps. However, the presence of inaccurate classifiers may degrade the classification performance of MCS. In this paper, we propose a unsupervised classifier selection strategy to select an appropriate subset of accurate classifiers for the multiple clas-sifier combination from a large pool of classifiers. The experimental results with two HSI show that the proposed classifier selection method overcomes the impact of inaccurate classi-fiers and increases the classification accuracy significantly