Pattern discrimination of joint transform correlator based on wavelet subband filtering

We propose and demonstrate a Gabor wavelet prefiltering prior to classical and binarized joint transform correlator implementation to enhance texture features of fingerprints. The frequency- and orientation-selective properties of the wavelet subband filter are utilized to extract important textural features for optimal correlation recognition. A selection criterion for wavelet subbands is derived, and it is shown that the maximum signal-to-noise ratio of the correlator is achieved by optimizing the threshold level. Simulation results show that the proposed method increases the discrimination power of the correlator, especially under noisy environments.