LEARNING SAMPLE SELECTION IN MULTI-SPECTRAL REMOTE SENSING IMAGE CLASSIFICATION USING BP NEURAL NETWORK

Through analyzing the influence of the learning samples’ location in the spectral space on the accuracy of multi spectral remote sensing image classification using BP neural network, a method for learning samples selection based on x 2 distribution was presented and used in TM image classification. The classified results of the 6 ground objects with BP classifier using different learning samples selecting methods and the Bayes classifier show that the BP classifier with the presented learning samples selection method can not only reduce the number of learning samples greatly which leads to shorter learning time, but also improve the classification accuracy compared with the existing methods.