Performance boosting of successive geometric centers, grid & texture based feature vector for dynamic signatures using soft biometric features

Abstract

Online signature recognition is one of the important behavioral biometric trait. This signature has information of x, y, z variations, pressure, azimuth of pen tip, altitude of pen tip. This makes online handwritten signature based biometric system more accurate than the static ones. In this paper new set of features are proposed for online or dynamic signature recognition. Geometric centers, Grid & Texture features based feature vector and their extraction mechanism is proposed here. Originally these features were proposed for static system but authors have proposed modification in the extraction mechanism so that these features are implied for dynamic signatures and they encompass the dynamic nature of the signature. The performance of proposed feature vector is further improved by soft biometric traits of the signature.