Multi-descriptor Enabled Leaf Disease Detection using Machine Learning Methods

Abstract

India is an agricultural country. Two-thirds of the Indian populations work in agriculture, making it the backbone of the country's economic system. Leaf disease is a major challenge in agriculture that affects crop yield and quality. In recent years, advancements methods for accurately and effectively detecting leaf diseases have been developed thanks to advances in machine learning and computer vision. The objective of this work is to create a machine learning-based Random Forest Regression Algorithm for automatically detecting leaf diseases. In the suggested methodology, leaf pictures are acquired, subjected to pre-processing which includes RGB image and HSV image conversion, multi-descriptor feature extraction includes Hu moments, Haralick, color histogram and classification using Random Forest Regression Algorithm. Metrics including accuracy, precision, recall, and f1-score are used to assess the system's performance by implementing in Python 3.8. The findings of the study indicate that the proposed system achieves precision 98 %, recall 98 %, f1-score 98%, test accuracy 97.81 %, while validation accuracy is 95.93 %. The developed system has potential applications in precision agriculture, enabling farmers to detect and treat plant diseases early, thereby reducing crop losses and increasing yields.