Multi-Modal Biometric System Using Iris, Face and Fingerprint Images for High-Security Application
Ayesha Tarannum1, Md. Zia Ur Rahman2
1Ayesha Tarannum, Research scholar, Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Guntur-522502, (A.P.), India.
2Md. Zia Ur Rahman, Professor, Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Guntur-522502, (A.P.), India..
Manuscript received on 13 March 2019 | Revised Manuscript received on 20 March 2019 | Manuscript published on 30 March 2019 | PP: 314-320 | Volume-7 Issue-6, March 2019 | Retrieval Number: F2160037619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© 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: Biometric systems (BS) are normally used for individual’s recognition’s based on the biological characters of individuals such as ears, veins, signatures, voices, typing styles, odors, gaits, and etc. the Uni-model BS does not provide better security and recognition accuracy so the multi-model BS are introduced, but the multi-model BS consist of some drawbacks such as intra class variations, Spoof attacks, non-universality, and distinctiveness. To overcome the drawbacks and improving the performance of Multi-model biometrics and future level fusion based biometric. In this paper fingerprint, iris and face biological characters based on highly secured (using Advanced Encryption Standard (AES)) FIF-AES-MM multi-model BS is introduced. In this FIF-AES-MM system, sharpening filter is used for image enhancement which provide efficient input image for Authentication. The Empirical Mode Decomposition (BEMD) and minutiae extraction algorithms are used for feature value extraction. BEMD method is used for Face and Irish feature value extraction. Minutiae extraction meteorology is used for fingerprint Feature value extraction. The Feature level fusion (FLF) methodology is used for combining the features and Correlation methodology is used for matching, finally the FIF-AES-MM system performances are measured. The execution parametric quantity such as accuracy, execution time, error rate, Recall (R), False negative (FN), False Positive (FP), Precision (P), True Positive (TP) and True Negative (TN). The FIF-AES-MM system provides better accuracy 90%, 80, and 70%.
Keywords: Advanced Encryption Standard, Biometric systems, Bi-dimensional Empirical Mode Decomposition, Feature level fusion and Minutiae
Scope of the Article: Advanced Bioinformatics