Multi-matcher on-line signature verification in DWT domain

Abstract

The paper presents a multi-matcher on-line signature verification system which fuses the verification scores in the pen-position parameter and the pen-movement angle parameter at the decision level. The pen-position parameter consists of horizontal, x, and vertical, y, coordinates, and the pen-movement angle parameter is derived from the pen-position parameter. Features of pen-position and pen-movement angle are extracted by sub-band decomposition using the discrete wavelet transform (DWT). In pen-position, high frequency sub-band signals are considered as individual features to enhance the difference between a genuine signature and its forgery. On the other hand, low frequency sub-band signals are utilized as features for suppressing the intra-class variation in the pen-movement angle. Verification is achieved by adaptive signal processing using the extracted features. Verification scores in the pen-position and the pen-movement angle are integrated using a weighted sum rule to make the total decision. Experimental results show that fusion of pen-position and pen-movement angle can improve verification performance.