Dependence structure of Gabor wavelets for face recognition
Chaorong Li, Yu Xue, Yuanyuan Huang · 2017
Up to today, face recognition is an open research subject in biometrie identification. In this paper we propose a method for face recognition based on the dependence structure of Gabor wavelet. As a useful tool, Gabor wavelets are widely used in image processing field. The strong dependencies exist in the domain of Gabor wavelets due to Gabor filters are not nonorthogonal. We have found that the dependence structure of Gabor wavelets can be used as the feature of face image, and hence it can be used to face recognition. In the proposed method, Gaussian copula is employed to describe the dependence structure of Gabor wavelets. Experiments of face recognition show the proposed method obviously improves the representation performance of Gabor wavelets, and is robust to low resolution face images.