A COMPARATIVE STUDY OF BIOMETRIC AUTHENTICATION BASED ON HANDWRITTEN SIGNATURES

Rajdeep Das, Sangeeta Dhar, Sabarni Das, Saurav Dutta, Subra Mukherjee*

Abstract: With the increasing concerns for security, automated systems for authorization and authentication have become enormously important in every sector today. There are many methods for personal identification such as smart cards, PIN (personal Identification Number), passwords, etc. Regardless of the efficiency and accuracy of these systems, these systems can be always be stolen, lost, forgotten, cracked, hacked, etc. And it is for this reason biometric based authentication system have gained a lot of importance worldwide. A biometric system is essentially a pattern-recognition system that recognizes a person based on a feature vector derived from a specific physiological (face, iris, retina, voice, palm prints, hand geometry) or behavioral characteristic (signature, voice, keystroke pattern) that the person possesses. This system is more accurate as these characteristics are unique for a particular person and vary almost negligibly over time. In this paper we have presented a comparative study of recent advances in biometric authentication based on mainly offline Hand-written signatures.

Keywords: Biometrics, online and offline signature verification, authentication, feature extraction, region of interest (ROI), Artificial Neural Network.

DOI: https://doi.org/10.15623/ijret.2013.0212004