Writer identification on mobile device based on handwritten

This paper deals with exploring of the potential of writer identification by handwriting on a touch-screen phone for an application in access control systems. Our aim was to examine the possibility of writer recognition by a biometric model based on handwritten password. A mobile phone-server solution based on distributed blocks is proposed. The implemented approach performs a pre-processing block, in order to segment the handwritten password on the mobile phone. It also applies a feature extraction in order to have our biometric in-formation, running on the server. The classification is done with 10 online and offline features and is classified by a Naive Bayes classifier. We have used a database of 108 handwritten genuine (12 samples came from nine users) and 36 impostors (four false samples from nine users) written on a HTC Desire mobile phone with Android 2.2. The proposed system reached an accuracy of 96.87% in writer verification. The false acceptance rate of the proposed system is 11.11%.