Fast Approximate Eyelid Detection for Periocular Localization
Iris is considered to be one of the most reliable traits and is widely used in the present state-of-the-art biometric systems. However, iris recognition fails for unconstrained image acquisition. More precisely, the system cannot properly localize the iris from low quality noisy unconstrained image, and hence, the successive modules of biometric system fails. To achieve recognition from unconstrained iris images, the periocular region is considered. The periocular (periphery of ocular) region is proven to be a trait in itself and can serve as a biometric to recognize human, though with a lower accuracy compared to iris. In this paper, we propose a novel technique to localize periocular region on the basis of eyelid information extracted from eye image. The proposed method will perform periocular localization successfully even when iris detection fails. Our method detects the horizontal edges as eyelids and the rough map of eyelids gives the radius of iris, which is used to anthropometrically derive the periocular region. The proposed method has been validated on standard publicly available databases : UBIRISv1 and UBIRISv2, and is found to be satisfactory.
KeywordsPeriocular recognition Eyelid detection Personal identification
Unable to display preview. Download preview PDF.
- 1.Adam, M., Rossant, F., Amiel, F., Mikovikova, B., Ea, T.: Eyelid Localization for Iris Identification. Radioengineering 17(4), 82–85 (2008)Google Scholar
- 2.Bakshi, S., Sa, P.K., Majhi, B.: Optimised periocular template selection for human recognition. BioMed Research International 2013, 1–14 (2013)Google Scholar
- 3.Bakshi, S., Tuglular, T.: Security through human-factors and biometrics. In: 6th International Conference on Security of Information and Networks, pp. 463–463 (2013)Google Scholar
- 4.Cui, J., Wang, Y., Tan, T., Ma, L., Sun, Z.: A Fast and Robust Iris Localization Method Based on Texture Segmentation. In: Biometric Authentication and Testing, National Laboratory of Pattern Recognition, Chinese Academy of Sciences (2004)Google Scholar
- 5.He, Z., Tan, T., Sun, Z., Qiu, X.: Robust eyelid eyelash and shadow localization for iris recognition. In: 15th IEEE International Conference on Image Processing, pp. 265–268 (2008)Google Scholar
- 7.Mahlouji, M., Noruzi, A.: Human Iris Segmentation for Iris Recognition in Unconstrained Environments. IJCSI International Journal of Computer Science Issues 9(1), 3, 149–155 (2012)Google Scholar
- 8.Masek, L.: Recognition of Human Iris Patterns for Biometric Identification. In: Bachelor of Engineering Thesis at The University of Western Australia (2003)Google Scholar
- 11.Radman, A., Zainal, N., Ismail, M.: Efficient Iris Segmentation based on eyelid detection. Journal of Engineering Science and Technology 8(4), 399–405 (2013)Google Scholar
- 12.Thalji, Z., Alsmadi, M.: Iris Recognition Using Robust Algorithm for Eyelid, Eyelash and Shadow Avoiding. World Applied Sciences Journal 25(6), 858–865 (2013)Google Scholar
- 13.Valentina, C., Hartono, R.N., Tjahja, T.V., Nugroho, A.S.: Iris Localization using Circular Hough Transform and Horizontal Projection Folding. In: Proceedings of International Conference on Information Technology and Applied Mathematics (2012)Google Scholar
- 14.Xu, G., Zhang, Z., Ma, Y.: Improving the Performance of Iris Recognition System Using Eyelids and Eyelashes Detection and Iris Image Enhancement. In: 5th IEEE conference on Cognitive Informatics, pp. 871–876 (2006)Google Scholar