Comparative Analysis of MSER and DTW for Offline Signature Recognition

This paper describes the signature as a one of the most robust and widely used trait in biometric verification. The signature is also known as behavioral biometric property. We present comparative analysis of offline signature recognition based on Dynamic Time Warping (DTW) and Maximally Stable Extremely Regions (MSER). The MSER system reported accuracy of 95.371% where FAR is 5.25% and FRR is 4% whereas DTW system reported accuracy of 70.5% and average horizontal projection WER 70% and average vertical projection WER of 71%.