Title :
A fast and efficient multiple step algorithm of iris image quality assessment
Author :
Shi, Chunlei ; Jin, Longxu
Author_Institution :
Inst. of Opt., Fine Mech. & Phys., Grad. Sch. of Chinese Acad. of Sci., Changchun, China
Abstract :
Iris recognition is one of the most reliable methods of biometrics personal identification. Poor quality iris image will be rejected by recognition system, which will result in the failure of recognition. Therefore iris image quality assessment is very essential to the iris recognition system. In this paper, a multiple step algorithm of iris image quality assessment is proposed to distinguish two kinds of poor quality images, i.e. defocus and occlusion. Experimental results show that the proposed algorithm is fast and efficient for iris image quality assessment.
Keywords :
iris recognition; biometrics personal identification; iris image quality assessment; iris recognition system; multiple step algorithm; poor quality images; poor quality iris image; Biomedical optical imaging; Biometrics; Frequency; Image databases; Image quality; Image recognition; Image sequences; Iris recognition; Least squares methods; Physics; Laplacian of Gaussian; iris image; iris localization; occlusion; quality assessment;
Conference_Titel :
Future Computer and Communication (ICFCC), 2010 2nd International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-5821-9
DOI :
10.1109/ICFCC.2010.5497537
