The Emerging of Signature Recognition as a Reliable Biometric Authentication Technology

Part 1 : Introduction –

Penulis: Fajar Kusumaningayu, I Nyoman Aditya Yudiswara, Fadhillah Moulita Andiani

Pembimbing dan Editor: Dr. Eng. Nico Surantha

The article is the first part of the serial article about the signature recognition. The article consists of three parts, i.e. the introduction, the automatic signature recognition, and the implementation of signature recognition. Signature is one of a widely used authentication method in the world. Handwritten signatures have been thoroughly used as one of the identification techniques in several credential documents such as identity card, passport, bank account, school admission, etc. Signature is the reflection a personal identity; it is not only able to represent their emotion and their behaviour toward others and their self but also display their dominant trait and potentials in certain fields [1]. All those reasons make signature forgeries became a regular occurrence.

Signature recognition is a technique that one should have in order to escape from being the victim of this crime. Signature verification is one of the biometric technologies; biometric verification can be classified into two big sections: first is the physical traits such as iris, fingerprints, and face recognition, and the second section is behaviour trait such as speech, signature, and gait recognition [2].

There are two types of signature recognition which are human signature recognition and automated signature recognition done by computerization. The study has been conducted to find out the rating of human signature recognition, the signatures were taken from BiosecureID with 20 signer and 240 signatures. It had 400 participants with has no experience as a Forensic Document Examiner. The result shows the rate of false acceptance is 50%-75% for not being able to differentiate between original and forgeries signature [3]. While in automatic signature recognition there are two methods that widely used which are online and offline signature recognitions [4].

Previous studies had combined their finding in order to bring a better accuracy result on recognizing the signatures, thus it can become reliable method to determine whether a signature is genuine or forgeries, so it can be applied as one of biometric authentication technique. This article will get insight into the information about automatic signature recognition.

References

[1] A. Venkatesh, A. Bhanpurawala, and S. Chowdhury, “Demonstration of Signature Analysis Using Intelligent Systems,” in Advances in Computing, Communication, and Control. ICAC3 2013. Communications in Computer and Information Science, 2013, vol. 361, pp. 199–206.

[2] K. W. Boyer, V. Govindaraju, and N. K. Ratha, Eds., “Special Issue on Recent Advances in Biometric Systems,” in IEEE Trans. on Syst., Man and Cybernetics – Part B, 2007, vol. 37, no. 5, pp. 1091–1095.

[3] D. Morocho, J. Hernandez-ortega, A. Morales, J. Fierrez, and J. Ortega-garcia, “On the evaluation of human ratings for signature recognition,” in 2016 IEEE International Carnahan Conference on Security Technology (ICCST), 2016, pp. 1–5.

[4] M. R. Deore and S. M. Handore, “A Survey on Offline Signature Recognition and Verification Verification Schemes,” in 2015 International Conference on Industrial Instrumentation and Control (ICIC), 2015, pp. 165–169.