Multi-Objective Optimization Using Evolutionary Algorithms
Multi-Objective Optimization Using Evolutionary Algorithms
Feature Selection Using Multi-Objective Genetic Algorithms for Handwritten Digit Recognition
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
Localized iris image quality using 2-d wavelets
ICB'06 Proceedings of the 2006 international conference on Advances in Biometrics
Efficient iris recognition by characterizing key local variations
IEEE Transactions on Image Processing
Iris recognition based on zigzag collarette region and asymmetrical support vector machines
ICIAR'07 Proceedings of the 4th international conference on Image Analysis and Recognition
Level Set Approaches and Adaptive Asymmetrical SVMs Applied for Nonideal Iris Recognition
ICIAR '09 Proceedings of the 6th International Conference on Image Analysis and Recognition
Nonideal Iris Recognition Using Level Set Approach and Coalitional Game Theory
ICVS '09 Proceedings of the 7th International Conference on Computer Vision Systems: Computer Vision Systems
| Hi-index | 0.00 |
Iris recognition is a flourishing biometrics scheme; however, still there exists some technical difficulties. In this paper, an iris recognition method has been proposed based on genetic algorithms (GA) for the selection of the optimal features subset. The accurate iris patterns classification has become a challenging issue due to the huge number of textural features extracted from an iris image with comparatively a small number of samples per subject. The traditional feature selection schemes like principal component analysis, independent component analysis, singular valued decomposition etc. require sufficient number of samples per subject to select the most representative features sequence; however, it is not always realistic to accumulate a large number of samples due to some security issues. We propose GA to improve the feature subset selection by combining valuable outcomes from multiple feature selection methods. This paper also motivates and introduces the use of Gaussian Mixture Model (GMM) for iris pattern classification. The proposed technique is computationally effective with the recognition rates of 97.90% and 96.30% on the ICE (Iris Challenge Evaluation) and the WVU (West Virginia University) iris datasets respectively.