원문정보
초록
영어
Classification of iris templates based on their texture patterns is one of the most effective methods in iris recognition systems. This paper proposes a novel algorithm for automatic iris classification based on fractal dimensions of Haar wavelet transforms is presented. Fractal dimensions obtained from multiple scale features are used to characterize the textures completely. Haar wavelet is applied in order to extract the multiple scale features at different resolutions from the iris image. Fractal dimensions are estimated from these patterns and a classifier is used to recognize the given image from a data base. Performance comparison was made among different classifiers.
목차
1. Introduction
2. Proposed method
3. Implementation details
3.1 Iris Localization and Normalization
3.2 Decomposition
3.3 Box counting method
3.4 Classification
4. Experimental results
4.1 Training Phase
4.2 Classification Phase
4.3 Discussion
5. Conclusion
References