EAgeBioS: Enhanced Biometric System to handle the Effects of Template Aging
Sunil Kumar1, Vijay Kumar Lamba2, Surender Jangra3

1Sunil Kumar*, Computer Science and Engineering, I.K.G. Punjab Technical University, Jalandhar, Punjab, India.
2Vijay Kumar Lamba, Electronics and Communication Engineering, Global College of Engineering and Technology, Ropar, Punjab, India.
3Surender Jangra, Computer Science and Applications, Guru Teg Bahadur College, Sangrur, Punjab, India. 

Manuscript received on October 17, 2019. | Revised Manuscript received on 25 October, 2019. | Manuscript published on November 10, 2019. | PP: 3669-3677 | Volume-9 Issue-1, November 2019. | Retrieval Number: A4756119119/2019©BEIESP | DOI: 10.35940/ijitee.A4756.119119
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 are well-known security systems that can be used anywhere for authentication, authorization or any kind of security verifications. In biometric systems, the samples are trained first and then it can be used for testing in long runs. Many recent researches have shown that a biometric system may fail or get compromised because of the aging of the biometric templates. The fact that temporal duration affects the performance of the biometric system has shattered the belief that iris does not change over lifetime. This is also possible in the case of iris. So, the main focus of this work is to analyze the effect of aging and also to propose a new system that can deal with template aging. We have proposed a new iris recognition system with an image enhancement mechanism and different feature extraction mechanisms. In this work, three different features are extracted, which are then fused to be used as one. The full system is trained on a dataset of 2500 samples for the year 2008 and testing is done in three different phases (i) No-Lapse, (ii) 1-Year Lapse and (iii) 2-Year Lapse. A portion of the ND-Iris-Template-Aging dataset [11] is used with a period of three years lapse. Results show that the performance of the hybrid classifier AHyBrK [17] is improved as compared to KNN and ANN and the effect of aging in terms of degraded performance is clear. The performance of this system is measured in terms of False Rejection Rate, Error Rate, and Accuracy. The overall performance of AHyBrK is 51.04% and 52.98% better than KNN and ANN respectively in terms of False Rejection Rate and Error Rate whereas the accuracy of this proposed system is also improved by 5.52% and 6.04% as compared to KNN and ANN respectively. This proposed system also achieved high accuracy for all the test phases.
Keywords: Template Aging, Hybrid Classifier, Feature Extraction, Feature Fusion, Quality Enhancement
Scope of the Article: Quality Control