HIGH PERFORMANCE IRIS RECOGNITION USING PHASE BASED IMAGE MATCHING

Biomedical Engineering

With an increasing emphasis on security, the automated personal identification based on biometrics has received extensive attention. Biometrics employs physiological or behavioral characteristics to accurately identify each subject. Iris recognition draws an extensive attention of researchers now since iris is the annular part between pupil and white sclera with minute characters such as freckles, coronas and stripes. Phase based method is relatively simple and efficient compared to existing methods. This project works on the phase based image matching methods. Iris recognition using the phase components in 2D Discrete Fourier Transforms of given images offers good results. The system operates in two steps, preprocessing stage and matching stage. Preprocessing includes mainly the extraction of feature. In the Matching stage, the Effective Region is extracted and finally the matching score is calculated by using the Band Limited Phase Only Correlation function. An efficient local appearance feature extraction method based the multi-resolution Curvelet transform is also used in order to further enhance the performance. Iris Recognition on Local Curvelet Block Based Classification along with the phase components encourages both accuracy and speed.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.