Novel Feature ExtractionTechnique For Off-LineSignature Verification System
SAMUEL ADEDEJI DARAMOLA, Samuel Ibiyemi · Covenant University Repository (Covenant University) · 2010
Feature extraction stage is the most vital 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. Inability to extract robust features from a static image of signature has been contributing to higher verification error-rates particularly for skilled forgeries. In this paper, we propose an off-line signature verification system that incorporates a novel feature extraction technique. Three new features are 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. The proposed system has 1% error in rejecting skilled forgeries and 0.5% error in accepting genuine signatures. These results are better in comparison with the results obtained from previous systems.