Biometric authentication has become a popular research topic due to its applicability to amongst other things, the prevention of fraud in financial transactions. Handwritten signature verification, in contrast with other biometric based authentication schemes such as fingerprint and retinal scanning, has the advantage that it is already widely used to endorce financial transactions. However, very little verification on these signatures are done today in practical scenarios. This paper reports on our ongoing research on automatic handwritten signature verification.

We investigate the feasibility of using the Radon transform and a dynamic programming algorithm to authenticate handwritten signatures on checks. Since there no dynamic information is available as in the case of the online problem where signatures are typically captured by means of a digitising tablet, the offline problem poses serious challenges. Our present system achieves an equal error rate of approximately 23% when only very high quality forgeries (skilled forgeries) are considered and an equal error rate of approximately 10% in the case of only casual forgeries. 1 Introduction Although handwritten signatures are by no means the most reliable means of personal identification, it remains one of the most widely acceptable means of personal identification. It is also non intrusive, inexpensive and one of the most commonly used personal identification systems. . A number of reasonably reliable online signature verification systems exist, see for example [9, 2]. These systems find p...

This paper presents a secure real-time remote user authentication system based on dynamic handwritten signature verification. The system allows users to establish their identities to other parties in real-time via a trusted verification server. The system can be used to gain remote access to restricted content on a server or to verify a signature on a legal document. State of the art dynamic verification techniques are combined with proven cryptographic methods to develop a secure model for remote handwritten signature verification.

Signature verification is a challenging task, because only small set of genuine samples can be acquired and usually no forgeries are available in real application. In this paper, we propose a new two-stage statistical system for automatic on-line signature verification. Our system is composed of a simplified GMM model for global signature features, and a discrete HMM model for local signature features. To be practical, we introduce specific simplification strategies for model building and training. Our system requires only 5 genuine samples for new users and relies on only 3 global parameters for quick and efficient system tuning. The experiment results show that our system works effectively with very small training set of genuine samples only. 1.

Signature sample synthesis is the generation of synthetic signature from a user’s signature samples. It is a special case of handwriting sample synthesis which generates novel handwriting in a particular person’s handwriting style. A handwriting or signature synthesis system has two basic modules: the modeling module and the synthesis module. In the modeling module, the system collects handwriting/signature samples of a specific writer (online or offline), and identifies and stores the basic characteristics of samples (for example, shape and spatial layout). In the synthesis module, synthetic glyphs are generated from the stored templates, and they may be further aligned and connected to form synthetic handwriting data. Main Body Text

In Handwritten signatures analyzed for forgery have to undergo feature extraction process, due to varied samples in size rotation and intra-domain changes, invariance has to be achieved during feature extraction process; circular Hidden Markov Model with discrete radon transform approach of feature extraction provides invariance. On other hand Scale Invariant Feature Transform (SIFT) has inherent invariant feature extraction approach. This paper compares both approaches on common signature databases for False acceptance rate(FAR),False Rejection Rate(FRR) and