The model of numerals recognition based on PCNN and FPF

One of the major problems in target recognition is that targets may be changed with translation, rotation, scale and intensity. A numerals recognition model based on PCNN (pulse-coupled neural networks) and FPF (fractional-power filter) is proposed in this paper, which use inherent ability of PCNN to extract feature and capability of FPF allowing invariance to be built into can recognize numerals with distortion effectively. The results of computer simulation show that the proposed method has a better effects compared with classical filters such as MACE. The simulation results of 340 images of the numerals from 0 to 9 with translation, rotation and scale demonstrate show that the method works well and gets high distinguishing rate.