Fingerprint Based Gender Classification Using Discrete Wavelet Transform & Artificial Neural Network?

This research implements a novel method of gender classification using fingerprints. Two methods are combined for gender classifications. The first method is the wavelet transformation employed to extract fingerprint characteristics by doing decomposition up to 5 levels. The second method is the back propagation artificial neural network algorithm used for the process of gender identification. This method is experimented with the internal database of 550 fingerprints finger prints in which 275 were male fingerprints and 275 were female fingerprints. Overall classification rate of 91.45% has been achieved. Results of this analysis make this method a prime candidate to utilize in forensic anthropology for gender classification in order to minimize the suspects search list by getting a likelihood value for the criminal gender.