Abstract
The overall performance of any iris recognition system relies on the performance of its components, which are preprocessing, feature extraction and matching. Feature extraction is the important step of such recognition system, but it is strongly dependent on the pre-processing step that is consisting of localising and normalising the iris. In this paper, Independent Component Analysis (ICA), which is a recently developed statistical method for data analysis, is applied for extracting the features for iris region of interest that are statistically independent. Based on some mathematical criteria, the performance of ICA is evaluated by using two different subsets of CASIA-V3 iris image database. The obtained results are convincing and some future improved research works are subsequently envisaged.
| Original language | English |
|---|---|
| DOIs | |
| Publication status | Published - May 2010 |
| Event | 2010 IEEE/ACS International Conference on Computer Systems and Applications (AICCSA) - Hammamet, Tunisia Duration: 1 May 2010 → … |
Conference
| Conference | 2010 IEEE/ACS International Conference on Computer Systems and Applications (AICCSA) |
|---|---|
| Period | 1/05/10 → … |
Keywords
- entropy
- feature extraction
- iris
- iris recognition
- random variables
- transforms
- vectors