Underwater Target Recognition Based on Module Time-frequency Matrix

Abstract

Underwater target recognition based on S-transform with module time-frequency matrix similarity is studied in the paper. Compute the similarity rate between S-transform with module time-frequency matrix of test sample and which of normal sample. The test sample is classified according to maximum similarity principle. The method can achieve target recognition directly without using auxiliary classifier. The computing process is simple and fast. Simulation and test show the method is suited to underwater target recognition because of its high recognition rate and insensitive to noise.