IRIS Recognition Using Machine Learning Techniques

In this paper, we are recognizing or detecting the Iris textures. Iris texture can be considered as a physical password since it has unique features for every person. Iris recognition is an important and reliable biometric system for access control. Iris biometric is widely used as a system for maintaining data security, such as ATM, cellular phone, etc. Moreover, the biometric has a very high sensitivity and accuracy for recognition than the other. Therefore, it is one of the preferred and distinctive biometric methods for identification purposes. The project is implemented in MATLAB using mmu-iris-dataset. The proposed method is performed using the machine learning algorithm of Random Forest. Image Processing is performed at the initial stage where segmentation and feature extraction of the given input is performed. Here we use Circular Hough transform for segmentation and then features are extracted from the segmented image using LBP (Local Binary Pattern) method. The extracted features are saved as a dataset and trained by the considered machine learning algorithm.  

Keywords: Iris recognition, Segmentation, Circular Hough transform, LBF Feature Extraction, Machine Learning, Random Forest.