A personal identification method based on finger’s outline

We propose a personal identification method based on fingerpsilas outline. In this paper first, we extract the fingerpsilas outline from a hand image acquired by the image acquisition system. Secondly we normalize the fingerpsilas outline by expanding the horizontal and vertical components into the KL expansion. The resulting fingerpsilas outline has a rotation invariant feature. Thirdly we expand the horizontal and vertical components of the normalized fingerpsilas outline into the Fourier series, respectively. Furthermore we consider a FIR system having the absolute values of the Fourier coefficients (AFC) as the input and output, respectively. It is considered that the FIR system represents the fingerpsilas outline feature. Then we can identify a person by evaluating the difference between the impulse responses of the FIR systems corresponding to the reference and the person to be identified. Finally, personal identification experiments were performed for 2180 hand images obtained from 109 persons. As the results FRR (false rejection) and FAR (false acceptance) error rates were 1.05% and 0.09%, respectively.