Fingerprint Classification Method based on J-divergence Entropy and SVM
Gongping Yang, Yilong Yin, Xiuyan Qi · Applied Mathematics & Information Sciences · 2013
Fingerprint classification is one of the key technologies in Automatic Fingerp rint Identification System (AFIS). However, the performance of most recent fingerprint classification methods is lo w when the quality of the fingerprint image was low. To overcome this problem, a novel method based on j-divergence entropy and SVM (Support Vector Machine) classifier is proposed in this paper. Firstly, our method transforms the fingerprint images from spatial doma in to frequency domain and constructs the directional images according to frequency spectrum energy. Secondly, eigenvector around the core point is extracted. Thirdly, the dimension of eigenvector is reduced by j-divergence entropy. At last, the input image is classified by SVM classifier. Experimental results on NIST-4 database show the validity of our method, and the classification accuracy reaches 9 4.7% for four-class classification and 91.5% for five-class classification with zero rejection rate.