Human Face Recognition using Soft Computing RBF

This paper proposes a new approach which derived from soft computing, for the construction of radial basis function neural network (RBFN). In training, the centres of radial basis functions are determined by soft computing. Experimental results show that the proposed soft computing RBFN in the human face recognition outperforms the conventional RBFN. It results in less sensitivity to learning parameters, faster convergence and lower recognition error. Hence, soft computing is expected to be a new alternative way to the construction of RBFN model in human face recognition