A target recognition method based on blocking partition and FM-TS network technology

Aiming at the special need of image processing in imaging fuze, a feature extraction method based on blocking partition to target image is studied. The image can be divided into several blocks according to their connectivity and changing trends. The structure features of each block and the relationship with other blocks are extracted. In order to recognize the conditions of missile-target encounters and the key parts of the targets reliably, we introduce the FM-TS network. The learning process of the network is given. Experimental results confirm that the algorithm can accomplish target recognition effectively.