Fast Iris Localization Method Based on Morphology and Least Squares Fitting of CircleReportar como inadecuado




Fast Iris Localization Method Based on Morphology and Least Squares Fitting of Circle - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Iris localization is a key technology in iris recognition system. Considering the properties of physical eyes and iris images, a novel fast iris localization method based on morphology and nonlinear least Squares fitting of circle is proposed. This method consists of two steps: the inner circle localization and the outer circle localization; the former use the methods of morphology, thresholding and maximum connected component successively to locate the inner circle; the latter finds a group of points which locate in outer circle with prior knowledge of inner circle and methods of morphology and thresholding firstly, then locate the outer circle through nonlinear least Squares fitting of circle. The experiment results on CASIA V3.0 Interval and CASIA V1.0 iris image database show that the proposed method can maintain the performance in robustness and precision, and outperforms the existed methods in speed.

KEYWORDS

iris recognition; is localization; morphology; east Squares fitting of circle 基

Cite this paper







Autor: Hailiang Shi, Tao Wei

Fuente: http://www.scirp.org/



DESCARGAR PDF




Documentos relacionados