Vein Recognition Based on Fusing Multi HMMs with Contourlet Subband Energy Observations

In order to recognize ones identity accurately, a dorsal hand vein recognition algorithm based on establishing and fusing multi Hidden Markov Models (HMMs) is proposed in the paper, where multi-scale subband energies are used as the features of HMMs after the vein images are processed by Contourlet transform. In the proposed algorithm near infrared light source array whose light intensity can be adjustable is applied, and the dorsal hand vein image sequence is acquired through increasing the light intensity gradually. Then every vein image is processed by Contourlet transform, subband energies under three scales are computed and used as the features of three HMMs. Finally, the probabilities of three HMMs generating observable symbol sequences are calculated and fused, and the result of fusion is compared to threshold, then the vein recognition process is completed. Experiments show that the proposed algorithm can make the discrimination between true and false matching maximum, and comparing with the recognition algorithms based on feature points or vein information fusion, the correct recognition rate is improved.