Paper-10 | Reg. No.:20130910|DOI:V2I2P10
Neural Network Pedestal Fingerprint Taxonomy
Mr. Samarpan.S.Jain, Prof.Murli Manohar H. – R.K.D.F Institute of Technology, Bhopal (M.P.), India
This paper introduces a new approach of fingerprint taxonomy system pedestal on ANN. Most automated fingerprint identification system uses prior taxonomy of fingerprint using minutiae as feature. But in such methods the performance of minutiae extractions relies heavily on an enhancement algorithm and also it needs improvement as they are limited to the number of classable data. Thus many fingerprints are classified together, taking a long time to match and verify a given fingerprint. So instead of taxonomy using minutiae we proposed a taxonomy system that is pedestal on individual features like singular point. Singular point detection is very robust and reliable, which overcomes the problem about rotation and translation. Taxonomy efficiency is improved using Back Propagation Algorithm because we don’t need to compare an input fingerprint image to all registered fingerprint images. The algorithm is tested accurately and reliably for many fingerprint images in FVC2004 data pedestal.