Efficient Signatures Verification System Based on Artificial Neural Networks

H. Said-Ahmed, E. Natsheh

Abstract


Biometrics refer to the system of authenticating identities of humans, using features like retina scans, thumb and fingerprint scanning, face recognition and also signature recognition. Signatures are a simple and natural method of verifying a person’s identity. It can be saved as an image and verified by matching, using neural networks. Signature verification can be offline or online. In this work, we present a system for offline signature verification. The user has to submit a number of signatures that are used to extract two types of features, statistical features and structural features. A vector obtained from each of them is used to train propagation neural network in the verification stage. A test signature is then taken from the user, to compare it with those the network had been trained with. A test experiment was carried out with two sets of data. One set is used as a training set for the propagation neural network in its verification stage. This set with four signatures form each user is used for the training purpose. The second set consists of one sample of signature for each of the 20 persons is used as a test set for the system. A negative identification test was carried out using a signature of one person to test others’ signatures. The experimental results for the accuracy showed excellent false reject rate and false acceptance rate.

Full Text:

PDF

References


Karouni, A. , Daya, B. and Bahlak, S. (2011). Offline Signature Recognition Using Neural Networks Approach. World Conference on Information Technology –Bhacesehir University. Science Direct, 2 -4.

Kaur, R. , and Aujla, G.S. (2014). Review on: Enhanced Offline Signature Recognition Using Neural Network and SVM. International Journal of Computer Science and Information Technologies, 5 (3) 1 -4.

Biswas, S. , Kim, T.K. , and Bhattacharyya, D. (2010). Features Extraction and Verification of Signature Image using Clustering Technique. International Journal of Smart Home. 4 (3), 2 – 10.

Jarad,M. , Al-Najdawi, N. and Tedmori,S. (2014). Offline Handwritten Signature Verification System Using a Supervised Neural Network Approach. 2014 6th International Conference on CSIT. 2 -6

Choudhary, N.Y. , Patil, R. Bhadade, U. and Chaudhari, B.M. (2013). Signature Recognition & Verification System Using Back Propagation Neural Network. International Journal of IT, Engineering and Applied Sciences Research. 1 – 7.

Malekar, M.D. and Patel, S. (2013). Off-line Signature Verification Using Artificial Neural Network. International Journal of Emerging Technology and Advanced Engineering. 3 (9). 1 – 4.

Sthapak, S. , Khopade, M. , and Kashid, C. (2013). Artificial Neural Network Based Signature Recognition & Verification. International Journal of Emerging Technology and Advanced Engineering, 3(8). 2 – 7.

Kovari, B. , and Charaf, H. (n.d.). Feature matching in off-line signature verification. Recent Researches in Communications and Computers. 2 - 4.

Jambi, K. (2001). “Different Approaches for Arabic Signature recognition”, Al-Azhar University Engineering Journal, vol. 12, 45-53.

Nguyen, Vu. , Blumenstein, M. , and Leedham, G. (2009). Global Features for the Off-Line Signature Verification Problem. 2009 10th International Conference on Document Analysis and Recognition. 1 – 4.

Natsheh, E. (2013), Personalized Web Documents Filtering by Analyzing User Browsing Behaviors, International Journal of Information Studies (IJIS), 5(2), 57-65.

Natsheh, E. (2012). "Taxonomy of Clustering Methods Used in Fuzzy Logic Systems", Journal of Telecommunication, Electronic and Computer Engineering (JTEC), vol.4, no.1, pp. 65-72.

Shikha, P. , and Shailja, S. (2013). Neural Network Based Offline Signature Recognition and Verification System. Research Journal of Engineering Sciences, 2 (2) 1 – 4


Refbacks

  • There are currently no refbacks.


ISSN : 2590-3551, eISSN : 2600-8122     

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0).

Best viewed using Mozilla Firefox, Google Chrome and Internet Explorer with the resolution of 1280 x 800