Research on Face Recognition Based on Three Layer Image Generation

In face recognition with single training sample cases the question of the low recognition rate, proposed a method of a kind of three layer virtual image. Using singular perturbation method to highlight the facial features, increase the quantity, scale change and sample attitude through the geometric transformation method, the spatial distribution of the improved method based on sample distribution. The experimental results on ORL face database show that this method can effectively on the single sample problem in the training sample pretreatment.