A Novel Approach for Signature Verification using Artificial Neural Network
Vibha Pandey1, Sanjivani Shantaiya2
1Vibha Pandey, M.tech.(Information Security) Scholar from DIMAT, Raipur (C.G.), India.
2Sanjivani Shantaiya, Assistant professor in dept of Computer Science & Engineering at Disha Institute of Management & Technology, Raipur (C.G.) India.
Manuscript received on July 17, 2012. | Revised Manuscript received on August 25, 2012. | Manuscript published on August 30, 2012. | PP: 163-166 | Volume-1 Issue-6, August 2012. | Retrieval Number: F0647081612/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper presents a new technique for off-line signature verification and recognition. The proposed system is based on morphological features (Shape features).Feature extraction stage is the most essential and difficult stage of any off-line signature verification system. The accuracy of the system depends mainly on the effectiveness of the signature features use in the system. The present research work incorporates a novel feature extraction technique for off-line signature verification system. There are nine features extracted from a static image of signatures using this technique. From the experimental results, the new features proved to be more robust than other related features used in the earlier systems. This approach is implemented in MATLAB and it verifies signatures taking into consideration several novel features and success rate achieved is 99.5%.
Keywords: Signature, Morphological, Feed Forward Neural Network, Feature Extraction, offline- signature recognition & verification.