SAR Image Target Recognition Based on Monogenic Signal and Sparse Representation

It is necessary to recognize the target in situation of military battlefield monitoring and civilian real-time monitoring. Sparse representation-based SAR image recognition method uses training samples or feature information construct an overcomplete dictionary, which will inevitably affect speed. In this paper, a based on monogenic signal sparse representation presented for recognition. method, extended maximum average correlation height filter used train generate templates. The features templates are extracted subdictionaries, subdictionaries combined cascade dictionary. coefficients testing over dictionary calculated by orthogonal matching tracking algorithm, realized according energy voting experimental results suggest that new approach has good terms accuracy time.