Classification of Remote Sensing Image Based on Adaptive GA and Improved BP Algorithm

An image classification method is presented,which trains the BP neural network (BPNN) by combing adaptive GA and improved BP algorithm.The experiment uses adaptive GA training the BPNN to get an approximate optimal solution in the whole area,and then use improved BP algorithm to modify the solution to a better one.The result shows that it is superior to improved BP algorithm in the convergence speed and classification accuracy.