Offline Signature Verification System using a Set of Simple Shape Based Geometric Features

International Journal of Computer Trends and Technology (IJCTT)          
© - April Issue 2013 by IJCTT Journal
Volume-4 Issue-4                           
Year of Publication : 2013
Authors :Amit Kishore Shukla, Shreyas Singh


Amit Kishore Shukla, Shreyas Singh"Offline Signature Verification System using a Set of Simple Shape Based Geometric Features"International Journal of Computer Trends and Technology (IJCTT),V4(4):511-514 April Issue 2013 .ISSN Published by Seventh Sense Research Group.

Abstract: -Signature is mostly used as a means of personal verification focused the need for an automatic verification system. Verification can be categorized either Offline or Online it depends on the application which is used. Online systems uses information which are dynamic in nature information are captured at the time the signature is performed. Offline systems work on the scanned image of a signature. In this paper we present a prototype for the Offline Verification of signatures using a set of simple shape based geometric features. The features that are used in this paper are The Baseline Slant Angle Of The Signature Sample, The Aspect Ratio Of The Signature Sample, The Normalized Area Of The Signature Sample, The Center of Gravity Of The Signature Sample and The Slope Of The Line Joining The Center Of Gravity Of The Vertical Splitting Of The Signature Sample . Before extracting the features of signature we have to perform, the preprocessing of a scanned image because we have to remove any spurious noise present in the signature sample. The system is initially trained using a database of signatures obtained from those individuals whose signatures have to be authenticated by the system. For every object a mean signature is obtained by integrating the above said features which are derived from a set of sample of genuine signatures. This mean signature acts as the template for verification against a claimed test signature. Euclidian distance which is in the feature space between the claimed signature and the template serves as a measure of similarity between the two. If this distance is less than a predefined threshold & the test signature is verified to be that of the claimed subject else detected as a forgery


[1] Ostu N., `A Threshold Selection Method from Gray Level Histogram, Man and Cybernetic, SPC-8, 1978 pp. 62-69.
[2]. Gonzalez R.C., Woods E., `Digital Image Processing`, Addison-Wesley, 1993
[3]. Larkins and Mayo, Adaptive Feature Thresholding for offline signature verification, 23rd International Conference In Image and Vision Computing New Zealand (2008), pp. 1- 6.
[4]. Coetzer, Herbst and Preezp , Offline Signature Verification Using the Discrete Radon Transform and a Hidden Mar Model,EURASIP Journal on Applied Signal Processing 2004.
[5]. Almudena, Fernandez, Pecharroman and Fierrez , Off-line signature verification ystem based on contour features, 11th International Conference on Frontiers in Handwriting Recognition,2008.
[6]. Debasish, Banshidhar and Jena, Improved Offline Signature Verification Scheme Using Feature Point Extraction, 7th IEEE International Conference on Digital Object Identifier .
[7]. Hanmandlu, Mohd. Hafizuddin, Vamsi, Offline Signature Verification and forgery detection using fuzzy modeling, Pattern Recognition, Volume 38, March 2005, Pages 341- 356.
[8]. Piyush and Rajagopalan, Offline signature verification using DTW,Pattern Recognition Letters, Volume 28, 1 Sep. 2007.
[9]. Bradley, Serestina, An off-line signature verification system, Signal and mage Processing Applications (ICSIPA), 2009.
[10]. Prakash and Guru, Geometric Centroids and their Relative Distances for off-line Signature Verification, 10th International Conference on Digital Object Identifier: 2009, Page(s): 121 125.

Keywords — Offline Signature Verification, Forgery, Feature Extraction, FAR, FRR.