Concatenation of Spatial and Transformation Features for off-Line Signature Identification
Ravi J1, K B Raja2
1Ravi J, Department of ECE, Global Academy of Technology, Bangalore, Karnataka, India,
2K B Raja, Department of ECE, University Visvesvaraya College of Engineering, Bangalore, Karnataka, India.
Manuscript received on July 01, 2012. | Revised Manuscript received on July 05, 2012. | Manuscript published on July 10, 2012. | PP: 102-108 | Volume-1, Issue-2, July 2012. | Retrieval Number: B0169071212/2012©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: Off- Line signature is a behavioral biometric trait and is widely accepted for personal and document authentication. In this paper we propose Concatenation of Spatial and Transformation Features for Off-Line signature Identification (CSTSI) method to distinguish genuine signature form skilled forgery signatures. The Discrete Wavelet Transform (DWT) is applied on signature to derive transform domain features from all the four sub bands. The signature is preprocessed and global features are extracted leads to spatial domain features. The transform domain and spatial domain features are concatenated to obtain final set of features. The test signature features are compared with data base signature features vector using correlation technique. It is observed that the values of FAR and EER are low in the case of proposed algorithm compare to existing algorithm. As FAR value is less, that indicates skilled forgery is successfully rejects.
Keywords: Signature. Global Features, DWT, Correlation, Fusion