Detection of Cholesterol Levels by Analyzing Iris Patterns using Backpropagation Neural Network

Abstract

Detecting cholesterol levels with iridology can be an alternative method for checking human’s health. Iridology analyzes diseases and weaknesses of the body based on the shape and structure of the iris. This study uses image processing to analyze patterns in the outer portion of the iris bordering the sclera. Colored iris images are converted to grayscale to facilitate image processing. The results of color conversion still contain noise so that the Median Filter is used to eliminate noise in the image. The iris image which is still in the form of polar is transformed into a rectangular shape. This is used to facilitate the taking of the area to be analyzed. Next, the iris image is filtered using a Gaussian Filter to get smooth results. This is used to remove lines on the iris image after being converted into a rectangular shape. From the filtered image, the statistical value is calculated using the Gray Level Co-Occurance Matrix (GLCM). This is a comparison method which will produce several statistical characteristics, namely Energy, Correlation, Contrast, and Homogeneity. The four statistical characteristics will be used as input data for training using the Backpropagation Neural Network method that will produce output in the form of normal cholesterol or high cholesterol. The results of experiments on thirty images obtained an accuracy of 96.67%.