Fingerprint orientation field estimation using ridge projection

Orientation field plays an important role in fingerprint recognition system. This paper proposes a method for estimating four-direction orientation field. It consists of four steps: (i) preprocessing fingerprint image, (ii) determining the primary ridge of fingerprint block using neuron pulses of pulse coupled neural network (PCNN), (iii) estimating block direction by projective distance variance of such a ridge, instead of a full block and (iv) correcting the estimated orientation field. Experiments on the databases of FVC2004 show that the proposed method achieves good estimation accuracy with low computational time expense. In particular, this method shows good robustness to noise, and it can be integrated into a fingerprint recognition system to improve the performance.