A New Image Enhancement Method for Face Recognition with Single Training Sample

Abstract

At present there are many methods that could deal well with frontal view face recognition when there is sufficient number of representative training samples per person. However, few of them can work well when only single training sample per person is available. In this paper, we present a training sample enhancement method based on Wavelet Transform (WT) low-frequency band to improve the performance of face recognition with a single training sample. In order to enhance the classification information of the single training sample, each training sample is combined with its WT reconstructed image based on low-frequency band into a new training sample. By using Fourier transform, the resulting spectrum representation of face image is used as the feature of the face image for recognition. The experimental results on ORL face database indicate the effectiveness of the proposed method.