Plant Diseases Classification using Machine Learning
Tan Xian, Ruzelita Ngadiran
Abstract
Abstract Plant diseases are one of source of obstruction in the quality and productivity of plants which can lead to the shortage of food supply. Therefore, plant disease classification is essential to the agriculture industry. The objective of this research is to classify the plant diseases by assessing the images of the leaves with the application of Extreme Learning Machine (ELM), a Machine Learning classification algorithm with a single layer feed-forward neural network. This work proposed image features as input where the image is pre-processed via HSV colour space and features extraction via Haralick textures. The features are then fitted in the ELM classifier to perform the model training and testing. The accuracy of ELM is then calculated after the testing has been done. The dataset used comprises of tomato plant leaves which is a subset of the Plant-Village dataset. The results produced from the ELM shows a better accuracy that is 84.94% when compared to other models such as the Support Vector Machine and Decision Tree.