Introduction to statistical pattern recognition (2nd ed.)
Introduction to statistical pattern recognition (2nd ed.)
Statistical Richness of Visual Phase Information: Update on Recognizing Persons by Iris Patterns
International Journal of Computer Vision
High Confidence Visual Recognition of Persons by a Test of Statistical Independence
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Fusion of Two User-friendly Biometric Modalities: Iris and Face
IEICE - Transactions on Information and Systems
Biometrics: Personal Identification in Networked Society
Biometrics: Personal Identification in Networked Society
| Hi-index | 0.00 |
In this paper, we present a new scheme for iris recognition from focus-varying sequences of iris images. Most of the current state-of-the-art iris recognition systems use the highly focused iris images to obtain high accuracy. These systems does not recognize defocused iris images. They also take much focusing time to acquire the high quality images. Unlike the current iris recognition systems, our proposed method can correctly recognize the defocused iris images because the iris image sequences have more information than single still images. We also apply a feature extraction method using direct linear discriminant analysis on wavelet subband to extract discriminative low-dimensional feature vectors. Our experimental results show that defocused images may be correctly recognized if we use multifocus image sequences as gallery images for iris recognition. In addition, The proposed system preserves both high security and user convenience.