BIOMETRIC KEYSTROKE RECOGNITION BASED ON HYBRID SVD AND WAVELET FOR FEATURE TRANSFORMATION

Abstract

The main aim of this work is using keystroke biometric system as behavioral type of biometrics and improving the accuracy and dependability of the system. In this proposed we've pre-processed the data of dynamic keystroke by converting the feature to one dimensional vector. In feature extraction we've used a Wavelet Energy (WE) by implementing 2D dimensional Discreet Wavelet (2D-DWT) into four-level and computing the energy for the Singular Value Decomposition (SVD). SVD is computed on the result of wavelet and saved in a file for training information. Wavelet transform Daubchies “DBI” basic function has advantage that provide a good energy localization in the frequency domain as other wavelet transforms and then using Elman networks (Backpropagation) for training and testing the system and its useful in such areas as signal processing and prediction where time plays a dominant role.