Wavelet-Based Feature Extraction and Recognition of Infrared Target

Feature extraction builds up the basis of pattern classification and recognition. The infrared image information of the target mainly concentrates on the low frequency part after being transformed by wavelet. In this paper, we propose a new kind of moment algorithm to obtain some real translation, rotation and scaling invariant features of the infrared target, and we also use neural network to classify targets. The simulation result shows that the applied method can recognize the target classification efficiently and reliably