Identification of Condition of Corn Plant Based on Leaf Image Features Using Gray Level Co-Occurrence Matrix and Backpropagation Neural Network

Abstract

This study aims to identify the condition of corn plants based on imagery leaf using the gray level co-occurrence matrix (GLCM) method and artificial neural network (ANN) backpropagation. The GLCM method is used for extracting features from image leaf corn, whereas ANN backpropagation is used for classification condition plant corn based on features. The classification was done using a dataset of corn leaves with four conditions: healthy, leaf spot, blight, and leaf rust. Next, the leaf features are extracted using method GLCM and training on model ANN backpropagation to classify conditions of corn plants. After training on the model, the next step is model evaluation using the confusion matrix method. The research results show that the technique can produce accuracy, which is tall enough to identify condition corn plants, with an accuracy of 95%. This indicates that the use of GLCM and ANN backpropagation can be a good alternative in determining the condition of corn plants. This research provides benefits in facilitating the identification of the state of corn plants quickly and accurately.