IRIS Recognition for Authentication systems

IRIS Recognition for Authentication systems

Iris recognition is considered to be the most reliable biometric authentication system. Very few iris recognition algorithms were commercialized. There are different methods proposed in the iris segmentation and feature extraction phase. Digitized gray scale images were used for determining the performance of the system. The circular iris and pupil of the eye image can be segmented using Morphological operators and Hough transform. The localized iris region can then be normalised into a rectangular block to account for imaging inconsistencies. Finally, the iris code can be generated using 2D Gabor Wavelets. A bank of Gabor filters has been used to capture both local and global iris characteristics to generate 2400 bits of iris code. By measuring the Hamming distance the matching of the iris code is done. For accuracy, the hamming distance can be chosen as 0.35.
The existing systems use the ideal eye images with less occluding parts for their testing. However the real time image of the eye can be captured with a lot of occluding parts, the effect of such occluding parts may result in the false non-matching. Some of the problems are outlined below,
• Eyelids and eyelashes bring about some edge noises and occlude the effective regions of the iris. This may lead to the inaccurate localization of the iris, which results in the false non-matching.
• The corneal and specular reflections will occur on the pupil and iris region. When the reflection occurs in the pupil from iris pupil border, the detection of the inner boundary of the iris fails.
• The orientation of the head with the camera may result in the orientation of the iris image to some extent.