Classification of iris regions using Principal Component Analysis and Support Vector Machine

Abstract

This paper presents the classification of vagina and pelvis from iris region based on iridology chart using Principal Component Analysis (PCA) and Support Vector Machine with Radial Basis Function kernel (SVM-RBF). The Circular Boundary Detector (CBD) has been introduced for localizing the iris region. This method is able to localize and segment the iris with 100% accuracy. The segmented iris was unwrapped into polar form and cropped into regions of vagina and pelvis based on iridology chart. Features obtained from the cropped regions are extracted using Principle Components Analysis (PCA) and are the inputs to SVM-RBF. Classification accuracy is computed through the comparison of each test feature vector with the target vectors. This study provides the foundation for the development of diagnostic system to monitor the health condition of human body parts.