2D/3D FACE RECOGNITION USING NEURAL NETWORK BASED ON HYBRID TAGUCHI-PARTICLE SWARM OPTIMIZATION

In this paper, we present a neural network classifier with hybrid evolutionary algorithm for solving 2D/3D face recognition problems. We first use Gabor wavelets to extract local features at different scales and orientations for gray facial images, then combine the texture with the surface feature vectors based on principal component analysis (PCA) to obtain feature vectors. We propose a neural network classifier based on hybrid Taguchi-particle swarm optimization (HTPSO) algorithm for face recognition. Experimental results demonstrate that the proposed HTPSO learning method has a better recognition rate than those of other approaches.