NIGHT VISION FACE RECOGNITION METHOD USING 2-DIRECTIONAL 2-DIMENSIONAL PRINCIPAL COMPONENT ANALYSIS ALGORITHM AND POLYNOMIAL-BASED RADIAL BASIS FUNCTION NEURAL NETWORKS

摘要

The present invention relates to a facial recognition method in an environment without lighting by obtaining an image through a night vision camera. The method comprises the following steps of: (1) obtaining image data by using a night vision camera; (2) detecting a facial area from the obtained image data, and eliminating a disturbance value; (3) reducing a data dimension of the image data; and (4) recognizing a face from the image data by using polynomial-based radial basis function neural networks (pRBFNNs).