Design and implementation of a multispectral iris capture system

Most commercial iris recognition systems use infrared or near-infrared cameras to capture the iris images because they show rich and complex textures that can be used to identify a person. This paper presents the design and implementation of a multispectral iris acquisition system that can efficiently capture and store iris images exposed under different wavelengths of illumination. The goal is enable the study of wavelength effects on iris recognition performance. A set of multispectral illuminators is designed to sequentially activate for short periods of time to expose the iris to spectral bands in the 405 nm – 1550 nm range. A specialized camera is used to capture iris images for each wavelength. A software program was developed to control the illuminators, camera, and the image acquisition process.

[1]  John Daugman,et al.  Probing the Uniqueness and Randomness of IrisCodes: Results From 200 Billion Iris Pair Comparisons , 2006, Proceedings of the IEEE.

[2]  Robert K. Rowe,et al.  Fingerprint enhancement using a multispectral sensor , 2005, SPIE Defense + Commercial Sensing.

[3]  Anil K. Jain,et al.  A Multispectral Whole-Hand Biometric Authentication System , 2007, 2007 Biometrics Symposium.

[4]  Bruce J. Tromberg,et al.  Face Recognition in Hyperspectral Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Diego A. Socolinsky,et al.  Multispectral Face Recognition , 2008 .

[6]  A. Ross,et al.  Multispectral Iris Analysis : A Preliminary Study , 2006 .

[7]  Moon Gi Kang,et al.  Multispectral iris authentication system against counterfeit attack using gradient-based image fusion , 2007 .

[8]  Arun Ross,et al.  Exploring multispectral iris recognition beyond 900nm , 2009, 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems.