Performance evaluation for ATR system based on backward cloud with less samples

In the recent years, as the development of automatic target recognition (ATR) technology, the performance evaluation for it becomes more and more important. In order to solve the problems of needing artificial intervene and needing too many samples in the existent evaluation methods, we proposed a new performance evaluation method for ATR system based on the backward cloud. In this method, we use numerical value features which are contained in the recognition result samples to denote the performance of the ATR algorithm, therefore we can do the evaluation without artificial intervene and with much less number of samples compared with other existent ones. At last, the simulation proved the advantages above.