Features of underwater echo extraction based on signal sparse decomposition

It is known that classification of underwater materials by echo is not so satisfactory while surface of the materials is heavily uneven.A new method,which is based on the theory of signal sparse decomposition,to extract novel features of underwater echo has been proposed in this paper.With this method,sets of training echo samples are used as a dictionary directly instead of the common time frequency dictionary while decomposing underwater echo and abstracting the classified energy feature of the echo.Experiments on three kinds of bottom materials including the cobalt crust show that the fisher distribution with this method is superior to that of edge features and of Singular Value Decomposition features in wavelet domain.It means no doubt that much better classification result of underwater materials can be obtained with the classified energy features than the other two.It is concluded that echo samples used as a dictionary is feasible and the classified information of echo introduced by this dictionary can help to obtain better echo features.