AUTOMATING THE IDENTIFICATION AND EVALUATION OF THE POSITION OF AXIAL TRIRADIUS ON PALM PRINT: AN APPROACH TO EARLY DETECTION OF CONGENITAL HEART DISEASES

Abstract

In this paper, we propose a novel method to detect Congenital Heart Diseases (CHDs) using digital palm images. An Axial triradius is one of the features of palm whose position can be used to detect CHDs. In palm print image, axial triradius is identified using a pattern matching algorithm which is a well-known algorithm in image processing. Along with axial triradius, two more triradii are identified. One triradius is located near the little finger and another one located near the index finger. The location of all these three triradii is obtained. Two vectors are drawn from axial triradius, one vector towards left triradius and another vector towards right triradius. The angle at axial triradius is calculated. The angle obtained is used to detect CHDs. Here template matching method has been proposed to identify triradii on palmprint images. Using this approach CHDs such as Fallot’s Tetralogy (FT), Atrial Septal Defect (ASD), Ventricular Septal Defect (VSD) and Coarctation of the Aorta (COA) can be detected. This paper deals with the angle at axial triradius which is calculated for two different people to determine the disease. Out of these two, one person is clinically diagnosed as suffering from FT and another person is healthy. The proposed method can predict that the person is suffering from TF. The proposed method has been used to detect the angle at axial triradius by taking palm images of 100 FT patients, 100 ASD patients, 100 VSD patients, 100 COA patients and 100 healthy people. The result obtained has proved the correctness of the results of previous research works to a certain extent. The present approach allows the automation towards the identification of triradii and evaluation of the position of axial triradius along with the results of its application on some sample images.