Abstract:
Biometric systems are widely used by governments, businesses and organizations to identify people based to their biological characters. The main purpose to use such systems is to improve the security of systems, but they could also be used to get more information about individuals. Some biometric traits are used to authenticate a person's identity such as face, fingerprint, handwriting, signature, voice, DNA, and ear. One of the most prompting and evolving methods in biometric identification is the iris recognition as the human iris has a unique texture which includes a veriety of details. Iris recognition has gained a challenge for many researchers. Many of the challenges occur due to the errors in the method of capturing images, poor illumination, image dimensions, off-angle iris, etc. The various methods have been adopted by researchers in order to enhance and increase the performance of iris recognition.
Most of the iris recognition systems incorporate processes before the features extraction stage; first, the pre-processing stage which is done to enhance only the region of interests. This stage includes segmentation and normalization. Segmentation is used for the localization of the correct iris region by using the Circular Hough Transform technique (CHT). In the normalization stage, it converts the iris region to a suitable shape with specific dimensions. The Daugman’s Rubber Sheet Model has been used to remaps each point within the iris region to a pair of polar coordinates. Finally, to improve the normalized iris image, the Histogram Equalization (HE) technique has been implemented to facilitate the application of the feature extraction step.
