Estimating and Fusing Quality Factors for Iris Biometric Images

Hits: 0
Research Area: Uncategorized
Status: Not started  
Members:  
 
Funded by: Fundação para a Ciência e a Tecnologia Funding: 0.00 EUR
Description:

In this project we try to replicate and improve the work of [1].

It consists in building a fully automated iris image quality evaluation block that estimates defocus blur, motion blur, off-angle, occlusion, lighting, specular reflection, and pixel counts. 

First each factor is estimated individually, then the second step fuses the estimated factors into a single “score”.

Considerable improvement in iris recognition performance is demonstrated when removing poor quality images selected by this quality metric.

References
[1] N. Kalka, J. Zuo, N. Schmid and B. Cukic; Estimating and Fusing Quality Factors for Iris Biometric Images, IEEE-Transactions on Systems, Man and Cybernetics, Part B, 2009 (to appear).