Signature Detection Using Image Processing and Matlab
Uploaded by
IJRASETPublicationsSignature Detection Using Image Processing and Matlab
Uploaded by
IJRASETPublications8 VI June 2020
http://doi.org/10.22214/ijraset.2020.6074
International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.429
Volume 8 Issue VI June 2020- Available at www.ijraset.com
Signature Detection using Image Processing and
Matlab
Aditi Narayan1, Harshita Khare2, Om Prakash Singh3
1, 2, 3
Electronics and Communication Department, RKGIT, Ghaziabad, India
Abstract: Signature has been a special feature that helps in unique identification of an individual. Mostly the business and
financial transactions are done using this unique feature i.e. signatures. Keeping this fact in mind we need to provide automatic
signature methods that also provides authenticity. If we talk about documents such as bank cheques, there the manual
verification of signatures are really tough to be maintained.
Keywords: Signature Recognition, MATLAB, Accuracy Recognition, Training Set.
I. INTRODUCTION
By biometrics we mean an individual’s identification by their physical and biological features automatically. The answer to
simplicity of access to these personal authentication system is biometrics.
Various applications of biometrics include banking, passports stealing mails etc.
An important aspect of biometrics is signatures. One method for distinguishing signatures is image processing .It uses unique
structural feature extracted from the contour of signature.
This project helps in development of an efficient signature detection system. The structure of this signature detection system is the
basis the pattern algorithm.
II. LITERATURE OVERVIEW
Earlier, other biometric methods have also come into existence but only a handful of them were accepted. While working on this
project of ours we also studied various methods found earlier.
In 2001, BiBa signature scheme was introduced by Adrian Perrig. This scheme uses one way function that work without trapdoors.
BiBa is one of the fastest methods. It uses small signatures and to verify these signatures it works at twice the speed.
BiBa stands for Bins and Balls signature.
III. SIGNATURE RECOGNITION
The signature in off line signature verification system is taken as an image which is a unique way of the handwriting of an
individual. As compared to on-line signature verification systems, off-line systems are difficult to design as many desirable
characteristics such as the order of strokes, the velocity and other dynamic information are not available in the off-line case. Although
difficult to design, most financial transactions are done on paper so offline signature verification is indeed and important aspect. The
basic construction for any signature verification system needs a solution for sub-problem:
A. Data Acquisition
B. Pre processing
C. Feature Extraction
©IJRASET: All Rights are Reserved 487
International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.429
Volume 8 Issue VI June 2020- Available at www.ijraset.com
IV. FUTURE SCOPE
The authenticity and security of our transactions that we do daily can be improved by using Signature Verification and Detection
technology.
In this paper we represent offline signature verification. Here the signature that is done on a paper is scanned and presented in the
form of image.
This technique is useful and suitable for applications such as passports, bank transactions, etc.
V. CONCLUSION
Although the existence of an automatic signature verification tool is necessary, it is not yet applied in most of the institutions
dealing with fianance. The reason is that most of the currently available tools work with a highest accuracy of ca. 80%, which makes
them not reliable in the verification task. For many years, researchers are trying to develop more robust signature verification tools
using the advances in image processing algorithms. The proposed model was successfully verified signatures of users with a lowest
accuracy of 85%, indicating its promising implementation and making a room for more improvements that have to be investigated.
The future work of this paper is to enhance the feature extraction step of the algorithm by adopting features related to cross
correlation, and signature energy and skewness. Finally, an automatic feature extraction tool may be developed to predict the
relevant features, which define each signature and reduce the verification effort.
©IJRASET: All Rights are Reserved 488
International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.429
Volume 8 Issue VI June 2020- Available at www.ijraset.com
REFERENCES
[1] Arti Agrahari, Abhishek Verma, Arti dubey. Garima Singh“Signature Verification System Using MATLAB” 2nd International Conference on Role of
Technology in Nation Building (ICRTNB-2013)
[2] Vaishali M. Deshmukh, Sachin A. Murab “Signature Recognition &Verification Using ANN” International Journal of Innovative Technology and Exploring
Engineering (IJITEE) ISSN: 2278-3075, Volume-1, Issue-6, November 2012
[3] Suhail Odeh and Manal khalil “Apply Multi-Layer Perceptrons Neural Network for Off-line signature verification and recognition” IJCSI International Journal
of Computer Science Issues, Vol. 8, Issue 6, No 2, November 2011 ISSN (Online): 1694-0814
[4] Meenakshi S Arya & Vandana S Inamdar “A Preliminary Study on Various Off-line Hand Written SignatureVerification Approaches” ©2010 International
Journal of Computer Applications (0975 – 8887) Volume 1 – No. 9
