Biometric signature authentication using machine learning techniques: Current trends, challenges and opportunities

Biometric systems are playing a key role in the multitude of applications and placed at the center of debate in the scientific research community. Among the numerous biometric systems, handwritten signature verification has got keen interest over the last three decades. Handwritten signature verification is the behavioral bio-metric system that discriminates the genuine signature from the pre-stored known signatures. It has been researched in the number of application areas like banking, financial and business transactions, cheque processing, access control and e-business etc. In this article, we surveyed the techniques of offline and online signature verification systems according to the taxonomy of classification model. A detailed background of signature verification system along with the available datasets are presented comprehensively. At the end, we presented the most notable challenges that guide the readers towards the current trends and future directions of the domain.