Face recognition based on Fourier-Bessel transformation
Dali Gao, Zhaoquan Cai · 2016
In order to improve the recognition rate of face recognition when factors like gesture and illumination are involved so that the efficient of recognition decrease, this paper proposes a new face recognition method based on Gabor feature and Fourier-Bessel analysis. In this method, the face features are extracted based on Gabor wavelet and Fourier-Bessel transformation, and the methods of Adaboost and Support Vector Machine are combined for face verification. Hence, the proposed method avoids the training degradation problems brought by the traditional dimension reduction method. The experiment shows that the proposed method is better than the traditional method such as PCA and LDA.