Feature Extraction Enhancement Techniques in Iris Biometrics Recognition Security System |
Author(s): |
Umang Varshney , NIELIT GORAKHPUR; Dr. A. K. D. Dwivedi, NIELIT GORAKHPUR |
Keywords: |
Iris Recognition; DWT (Discrete Wavelet Transform); HD (Hamming Distance); CHT (Circular Hough Transform) |
Abstract |
The accuracy of an iris recognition system is largely dependent upon the technique employed in encoding the local phase of the iris texture so as to extract maximum information. The earliest and most commonly used Gabor wavelets yield a local phase representation distributed over several scales and orientations generating extremely efï¬cient feature vectors. One of the very promising attempts at obtaining a useful phase information is from the ï¬eld of analytic signals and wavelets. In this paper, we suggest that the distinctive ability of the discrete wavelets to simultaneously extract local phase and orientation can be exploited with improved feature extraction for iris recognition applications. In order to test the effectiveness of the proposed method, the reconstructions obtained using discrete wavelet phase are compared with the Gabor and Fourier counterparts. The analysis has been done via Image Processing, Computer Vision and Wavelet Toolbox in MATLAB. |
Other Details |
Paper ID: IJSRDV5I60384 Published in: Volume : 5, Issue : 6 Publication Date: 01/09/2017 Page(s): 620-623 |
Article Preview |
|
|