www.tjprc.org editor@tjprc.org
International Journal of Computer Science Engineering
and Information Technology Research (IJCSEITR)
ISSN(P): 2249-6831; ISSN(E): 2249-7943
Vol. 4, Issue 2, Apr 2014, 21-30
© TJPRC Pvt. Ltd.
OFFLINE SIGNATURE VERIFICATION USING HU’S MOMENT
AND GABOR WAVELET TRANSFORM
PRIYANKA BAGUL
1
& LEENA RAGHA
2
1
Department of Computer Science & Engineering, Ramrao Adik Institute of Technology,
Navi Mumbai, Maharashtra, India
2
Department of Information Technology, Ramrao Adik Institute of Technology,
Navi Mumbai, Maharashtra, India
ABSTRACT
The signature of a person is an important biometric attribute of a human being which can be used to authenticate
human identity. However human signatures can be handled as an image and recognized using computer vision and NN
techniques. With modern computers, there is need to develop fast algorithms for signature recognition. There are various
approaches to signature recognition with a lot of scope of research. In this report, off-line signature verification using NN
is proposed, where the signature is captured and presented to the user in an image format. Signatures are verified based on
parameters extracted from the signature using various transform techniques. In our project we will use Hu’s moment,
Radon transform and Gabor wavelet transform. By combining this transform technique we will extract more features and
will get more accurate output.
KEYWORDS: Signature Verification, Human Signatures, Feature Extraction and Classification, Verification
Techniques
1. INTRODUCTION
Human signatures provide secure means for sanctioning legal documents. It is widely acceptable and collectable
biometric characteristic. The problem arises when someone is trying to copy our signature and steal our identity then it
could be used to make serious damage to us. Therefore, there is a need for adequate protection of our signature and it needs
to be known who actually signed a document. So nowadays, automatic signature verification becomes an essential
component as it particularizes in handling signatures.
1.1 Techniques for the Signature Verification
Signature verification can be grouped into two methods
Online
The online method uses a stylus and an electronic tablet connected to a computer to extract information about the
signature. This method empowers dynamic information such as stroke sequence, number of strokes, pressure, acceleration,
and direction of each stroke to be captured while a signature is being written [1] [2].
Offline
In the offline signature verification techniques, images of the signatures written on a paper are obtained using a