Orisyncrasy—An Ear Biometrics on the Fly Using Gabor Filter
Ear has many unique features which can be used for uniquely identifying an individual. Ear as a biometric is very effective and efficient as the medical studies have shown that the significant changes in the shape of the ear happen only before the age of 8 years and after the age of 70 years. The ear is fully grown till the age of 8 years and after that it grows symmetrically by 1.22 mm per year. Also, ear starts to bulge downwards after the age of 70 years. The skin colour distribution of the ear is almost uniform. Ear biometric system can capture the ear from a distance even without the knowledge of the subject under test as it is a passive biometric system. Ear is hard to replicate which will be helpful to reduce cybercrime. Digital cameras capture profile face of the subject at different angles and orientations, from which ear is segmented and further using Gabor filter features are extracted which is fed to a machine learning model to train our data. As Gabor features are extracted from ear images at different angles and different orientations, the system is invariant to rotation of profile face in same or different planes.
KeywordsEar biometrics Gabor filter Security Authentication Connected component analysis Pattern recognition Machine learning
All the participants are hereby expressing their approval for usage of photographs therein and we are not under any influence. We take the responsibility involved in the publication of our paper. Authors have taken permission to conduct the experiments.
- 1.Valecha H, Ahuja V, Valechha L, Chawla T, Sengupta S (2018) Orisyncrasy: an ear biometrics on the fly using machine learning techniques. In: Pandian A, Senjyu T, Islam S, Wang H (eds) Proceedings of the international conference on computer networks, big data and IoT (ICCBI - 2018), Springer, Switzerland, pp 1005–1016. https://doi.org/10.1007/978-3-030-24643-3_120Google Scholar
- 4.Iannarelli A (1989) Ear identification. Paramount PublishingGoogle Scholar
- 5.Burge M, Burger W (1998) Ear biometrics. In: Biometrics: personal identification in networked society. Springer, Berlin, pp 271–286Google Scholar
- 7.Benzaoui A, Hezil N, Boukrouche A (1945) Identity recognition based on the external shape of the human ear, May 1945Google Scholar
- 8.Yan P, Bowyer KW, IEEE (2007) Human ear recognition using geometrical features extraction. IEEE Trans Pattern Anal Mach Intell 29(8) (2007)Google Scholar
- 9.Said EH, Abaza A, Ammar H (2008) Ear segmentation in color facial images using mathematical morphology. IEEEGoogle Scholar
- 10.Minhas S, Javed MY (2009) Iris feature extraction using gabor filter. In: International conference on emerging technologiesGoogle Scholar
- 11.Wang J, Sun X (2010) Fingerprint image enhancement using a fast Gabor filter. In: Proceedings of the 8th world congress on intelligent control and automation, July 2010Google Scholar
- 12.Mao K, Zhang H, Li W, Chai T (2010) Selection of gabor filters for improved texture feature extraction. In: IEEE 17th international conference on image processing, Sept 2010Google Scholar
- 13.Saravanan V, Sindhuja R (2013) Iris authentication through gabor filter using DSP processor. In: IEEE conference on information and communication technologiesGoogle Scholar
- 14.Yu L, Wang Z, Dou R, Wang J (2010) A new framework of biometric encryption with filter-bank based fingerprint feature. In: 2nd international conference on signal processing systemsGoogle Scholar