Age Group Estimation from Human Iris
- 17 Downloads
The paper presents the approach to determine the age group of a person from an iris structure using less number of features. The performance of a proposed method is evaluated based on five different classifiers. Our methodology improves on earlier methods in terms of classification accuracy and F1 score. The study also proved that human iris structure has age-related information and therefore can be used to predict age. The existing iris biometric systems can be advanced with this method if they show an age in spite of just accepting or rejecting a person.
KeywordsFeature extraction Iris biometrics Age group estimation Machine learning
Authors would like to acknowledge and thanks to UGC SAP (II) DRS Phase-I and Phase-II F. No. 3-42/2009 and 4-15/2015/DRS-II for KVKRG_Iris database and support to this work and the department of computer science and information technology, Dr. Babasaheb Ambedkar Marathwada University, Aurangabad, Maharashtra, India.
Declaration Authors declare that they have taken the due permission to use the image of the person in the paper, and hence, if any litigation arises in the future, authors are solely responsible.
- 2.Browning, K., Orlans, N.: Biometric Aging Effects of Aging on Iris Recognition. MITRE (2014)Google Scholar
- 3.Aslam, T.M., Tan, S.Z., Dhillon, B.: Iris recognition in the presence of ocular disease NCBI. 6 May 2009Google Scholar
- 5.Fairhurst, M., Erbilek, M.: Analysis of physical ageing effects in iris biometrics. IET Comput. Vis. Special Issue: Future Trends in Biometric Processing (2010)Google Scholar
- 6.Bowyer, K.W., Baker, S.E., Hentz, A., Hollingsworth, K., Peters, T., Flynn, P.J.: Factors that degrade the match distribution in iris biometrics. Open Access Springer Link (2009)Google Scholar
- 7.Fenker, S.P., Bowyer, K.W.: Analysis of template aging in iris biometrics, In: 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Providence, RI, pp. 45–51 (2012)Google Scholar
- 8.Mehrotra, H., Vatsa, M., Singh, R., Majhi, B.: Does Iris Change Over Time? PLOS-ONE Open access Journal (2013)Google Scholar
- 10.Ageing eyes hinder biometric scans. http://www.nature.com/news/ageing-eyes-hinder-biometric-scans-1.10722 (2013)
- 11.Baker, S., Bowyer, K.W., Flynn, P.: Empirical evidence for correct iris match score degradation with increased time lapse between gallery and probe matches. In: International Conference on Biometrics, pp. 1170–1179 (2009)Google Scholar
- 13.Dubbelman, M., Sicam, V.A.D.P., Van der Heijde, G.L.: The shape of the anterior and posterior surface of the aging human cornea. Vis. Res. 46(6–7), 993–1001 (2006)Google Scholar
- 14.Melange, P.A., Sable, G.S.: Age group estimation and gender recognition using face features. Int. J. Eng. Sci. 7, 1–7 (2018)Google Scholar
- 15.Batool, N., Chellappa, R: Modeling and detection of wrinkles in aging human faces using marked point processes. In: European Conference on Computer Vision ECCV, pp. 178–188 (2012)Google Scholar
- 16.Rybintsev, A: Age estimation from a face image in a selected gender-race group based on ranked local binary patterns. Complex Intell. Syst. 93–104 (2017)Google Scholar
- 17.Ku, C.L., Chiou, C.H., Gao, Z.Y., Tsai, Y.J., Fuh, C.S.: Age and gender estimation using multiple-image features. Lecture Notes in Computer Science, vol. 8232 (2013)Google Scholar
- 18.Erbilek, M., Fairhurst, M., Abreu, M.C.D.C.: Age prediction from iris biometrics. In: 5th International Conference on Imaging for Crime Detection and Prevention. ICDP (2013)Google Scholar
- 19.Sgroi, A., Bowyer, K.W., Flynn, P.J.: The prediction of old and young subjects from iris texture. In: International Conference on Biometrics (ICB), published on IEEE Digital Explore (2013)Google Scholar
- 20.KVK-R Multimodal Biometric Database. http://kvkale.in/academics-2/multimodal-biometric-laboratory/outcome-of-mrrl/
- 21.Machine Learning Tutorial-2. Recall, Precision, F1-measure, Accuracy Ch. 5. https://www.cs.odu.edu/~mukka/cs495s13/Lecturenotes/Chapter5/recallprecision.pdf
- 22.Choose classifier options. https://in.mathworks.com/help/stats/choose-a-classifier.html