Automatic Recognition of Radar Signal Based on Time-Frequency Image Shape Character

Radar signal recognition is one of the key technologies of modern electronic surveillance systems. Time-frequency image provides a new way for recognizing the radar signal. In this paper, a series of image processing methods containing image enhancement, image threshold binarization and mathematical morphology is utilized to extract the shape character of smoothed pseudo wigner-ville time-frequency distribution of radar signal. And then the identification of radar signal is realized by the character. Simulation results of eight kinds of typical radar signal demonstrate that when signal noise ratio (SNR) is greater than -3 dB, the Legendre moments shape character of the time-frequency image is very stable. Moreover, the recognition rate by the character is more than 90 per cent except for the FRANK code signal when SNR > -3 dB. Test also show that the proposed method can effectively recognize radar signal with less character dimension through compared with exitsing algorithms.