Offline Signature Verification Using Structural Features

2314 Words5 Pages

1. Abstract

This paper describes a new technique for authenticating handwritten signatures using offline mode. In this technique, every single pixel that belongs to signature is considered. From the signature, every edge points / end points are extracted. These edge points / end points are connected to form a polygonal closed shape. From the polygonal shape, several values can be computed that can serve as structural features that are form factor, circularity measure, rectangularity measure, minimum enclosing rectangle, area and perimeter. These values combine together to make a verification function that can server to discriminate between genuine and forgery signatures.

2. Introduction

Recognizing a person can be done either on the basis of behavioral or physical characteristics in biometric automated methods. There are many behavioral attributes that can be voice, iris, fingerprints, and face recognition. Due to increase in fraud act from forgeries, the need for developing such secure systems for authorizing the right person has increased and these systems needs to be more sensitive to discriminate between genuine and forge person.

Among the different identification methods, the common method used in our society is to identify a person is through handwritten signature because it is an official/formal way for person identification. They are used in government, for attestation, documents authenticity etc. But with its social acceptance it’s demoralized by the forgery to make false transactions. The need is to minimize the forgery threats, research has been done and is still an interesting field for the researchers to minimize forgery signature acceptance.

Automated verificatio...

... middle of paper ...

...n Methods for Off-line Signature Verification”, Frontiers in Handwriting Recognition, 2004. IWFHR-9 2004, pages 161–166.

[18] Justino, E., Bortolozzi, F., and Sabourin, R. (2005), “A comparison of SVM and HMM classifiers in the off-line signature verification”, Pattern Recognition Letters, 6(9):1377–1385.

[19] ¨Ozg¨und¨uz, E., S¸ent¨urk, T., and Karslıgil, M. (2005), “Off-Line Signature Verification and Recognition by Support Vector Machine”, In European Signal Processing Conference.

[20] Ma, Z., Zeng, X., Zhang, L., Li, M., and Zhou, C. (2007), “A Novel Off-Line Signature Verification Based on Adaptive Multi-resolution Wavelet Zero-Crossing and One-Class-One-Network”, LECTURE NOTES IN COMPUTER SCIENCE, 4493:1077

[21] Srihari, S., Srinivasan, H., Chen, S., and Beal, M. (2008), “Machine Learning for Signature Verification”, Intelligence (SCI), 90:387–408.

More about Offline Signature Verification Using Structural Features

Open Document