Machine Learning-Based Approaches for Tomato Pest Classification

Abstract

Insect pests are posing a significant threat to agricultural production. They live in different places like fruits, vegetables, flowers, and grains. It impacts plant growth and causes damage to crop yields. We presented an automatic detection and classification of tomato pests using image processing with machine learning-based approaches. In our work, we considered texture features of pest images extracted by feature extractors like gray level co-occurrence matrix (GLCM), local binary pattern (LBP), histogram of oriented gradient (HOG), and speeded up robust features (SURF). The three standard classification methods, including Support Vector Machine (SVM), k-Nearest Neighbour (k-NN), and Decision Tree (DT), are used to classify features of tomato pest by feature extractors mentioned above. The three classifiers have undergone a comprehensive analysis to present which classifier yields the best accuracy, and the value of best accuracy obtained using the feature extraction method. The experiment results showed that the SVM classifier's precision using the feature extracted by LBP achieves the highest value of 81.02%. MATLAB software used for feature extraction and WEKA graphical user interface for classification.