 |
Technical Program
Paper Detail
| Paper: | MA-P3.2 |
| Session: | Fingerprint and Iris Analysis |
| Time: | Monday, October 9, 09:40 - 12:20 |
| Presentation: |
Poster
|
| Title: |
AN EMPIRICAL MODE DECOMPOSITION APPROACH FOR IRIS RECOGNITION |
| Authors: |
Jen-Chun Lee; Chung Cheng Institute of Technology | | | | | Ping S. Huang; Chung Cheng Institute of Technology | | | | | Chung-Shi Chiang; Chung Cheng Institute of Technology | | | | | Te-Ming Tu; Chung Cheng Institute of Technology | | | | | Chien-Ping Chang; Chung Cheng Institute of Technology | | |
| Abstract: |
Biometrics is inherently a reliable technique to identify human's authentication by his or her own physiological or behavioral characteristics. Empirical Mode Decomposition (EMD), a multiresolution decomposition technique, is adaptive and appears to be suitable for non-linear, non-stationary data analysis. EMD analyzes the signal locally and separates the component holding locally the highest frequency from the rest into a separate component. In this paper, we adopt the EMD approach to extract residual components from the iris image as the features for recognition. Three different similarity measures have been evaluated. Experimental results show that three metrics have achieved similar performance. Therefore, the proposed method has demonstrated to be promising for iris recognition and EMD is suitable for feature extraction. |
|
