The Implementation of GLCM and ANN Methods to Identify Dragon Fruit Maturity Level

Abstract

The identification of the maturity level of dragon fruit in this study was divided into two groups of ripeness: the unripe and the ripe. This study aims to classify the maturity level based on dragon fruit images using the feature extraction method, the gray level co-occurrence matrix (GLCM). This research method consists of converting RGB data to grayscale, image normalization, detection of dragon fruit maturity, feature extraction, and identification. Data collection from real data totaled 60 images used in this study consisting of 40 training data and 20 testing data which are RGB image data in JPG format. Each data consists of 2 maturity categories. Training data consists of 20 images of 99% ripe dragon fruit and 20 images of 85%. Meanwhile, the testing data consisted of 10 of 99% ripe dragon fruit images and 10 of 85% ripe dragon fruit images. The image data is processed into a grayscale image which then detects the ripeness of the dragon fruit. After the maturity of the dragon fruit is obtained, segmentation is carried out on the location of the dragon fruit found. Then the feature calculation is performed using the Gray Level Co-Occurrence Matrix (GLCM). The Artificial Neural Network (ANN) algorithm is used for the identification process. The final test results show that the proposed method has been able to detect dragon fruit maturity level with an accuracy of = 9/10* 100% = 90%, calculated using the confusion matrix. Thus, implementing the Gray Level Co-Occurrence Matrix