Recent works in the area of biometrics have shown that fusion at segmentation level (FSL) has contributed to the robustness in iris recognition compared with the recognition obtained from a single segmentation. Different segmentation algorithms can produce different iris textural information from the same image. Considering FSL and combining a method for quality evaluation of images, in this paper we present the analysis of the improvement on textural information in human iris images. The images set for the experiments were four international databases, MBGC-V2 (iris video database), CASIA-V3-Interval, CASIA V4 Thousands and UBIRIS v1 (iris image databases). The Equal Error Rate is used as metric to show the improvement of the recognition rates and hence the textural information improvement.
CITATION STYLE
Llano, E. G., García-Vázquez, M. S., Zamudio-Fuentes, L. M., Colores Vargas, J. M., & Ramírez-Acosta, A. A. (2017). Analysis of the improvement on textural information in human iris recognition. In IFMBE Proceedings (Vol. 60, pp. 373–376). Springer Verlag. https://doi.org/10.1007/978-981-10-4086-3_94
Mendeley helps you to discover research relevant for your work.