Intra-Modal Score Level Fusion for off-Line Signature Verification
Prashanth C R1, K B Raja2, Venugopal K R3, L M Patnaik4
1Prashanth C R, Department of Electronics and Communication Engineering, Vemana Institute of Technology, Visvesvaraya Technological University, Bangalore, India.
2K B Raja, Department of Computer Science and Engineering, University Visvesvaraya College of Engineering, Bangalore University, Bangalore, India.
3Venugopal K R, Department of Computer Science and Engineering, University Visvesvaraya College of Engineering, Bangalore University, Bangalore, India.
4L M Patnaik, Honorary Professor, Indian Institute of Science, Bangalore, India.
Manuscript received on July 01, 2012. | Revised Manuscript received on July 05, 2012. | Manuscript published on July 10, 2012. | PP: 179-187 | Volume-1, Issue-2, July 2012. | Retrieval Number: B0181071212/2012©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: Signature is widely used as a means of personal verification which emphasizes the need for a signature verification system. Often the single signature feature may produce unacceptable error rates. In this paper, Intra-modal Score level Fusion for Off-line Signature Verification (ISFOSV) is proposed. The scanned signature image is skeletonized and exact signature area is obtained by preprocessing. In the first stage 60 centers of signature are extracted by horizontal and vertical splitting. In the second stage the 168 features are extracted in two phases. The phase one consists of dividing the signature into 128 blocks using the center of signature by counting the number of black pixels and the angular feature in each block is determined to generate 128 angular features. In the second phase the signature is divided into 40 blocks from each of the four corners of the signature to generate 40 angular features. Totally 168 angular features are extracted from phase one and two to verify the signature. The centers of signature are compared using correlation and the distance between the angular features of the genuine and test signatures is computed. The correlation matching score and distance matching score of the signature are fused to verify the authenticity. A mathematical model is proposed to further optimize the results. It is observed that the proposed model has better FAR, FRR and EER values compared to the existing algorithms.
Keywords: Biometrics, Off-line Signature Verification, Image Splitting, Center of Signature, Angular Features, Correlation.