To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Uncertainty Theory Based Iris Recognition System |
|
Author |
Majd BELLAAJ, Dorra SELLAMI, Imen KHANFIR KALLEL |
| Citation |
Vol. 26 No. 8 pp. 11-22 |
|
Abstract |
The performance and robustness of the iris-based recognition systems still suffer from uncertainty and imprecision in the collected data. This paper makes an attempt to address these imperfections and deals with important problem for real system. We proposed a new method for iris recognition system to treat imperfection iris information. Several factors cause different types of degradation in iris data such as the poor quality of the acquired pictures, the partial occlusion of the iris region due to light spots, or lenses, eyeglasses, hair or eyelids, and adverse illumination and/or contrast. All of these factors are open problems in the field of iris recognition and affect the performance of iris segmentation, its feature extraction or decision making process, and appear as imperfections in the extracted iris signature. The aim of our experiments is to model the variability and ambiguity in the iris data with the uncertainty theory. This paper illustrates the importance of the use of this theory for modeling or/and treating encountered imperfections. Several comparative experiments are conducted on three subsets of the CASIA-V4 iris image database namely Thousand, Interval and Twins. Compared to a conventional iris recognition system relying on the uncertainty theory, experimental results show that our proposed model improves the iris recognition system in terms of Detection Error Trade-off (DET) curve, Equal Error Rates (EER), Area Under the receiver operating characteristics Curve (AUC) and Accuracy Recognition Rate (ARR) statistics. |
|
Keywords |
Iris recognition system, iris feature imperfections, probability theory, possibility theory. |
|
URL |
