Performance Analysis of Machine Learning Techniques in Plant Leaf Disease Detection

Abstract

Agriculture is one of the most important sectors in nutrition and economy worldwide. One of the most effective ways to combat the contraction of agricultural activities is the management of crop diseases, which impact food security and the earnings of many people. This study deals with applying a variety of ML techniques that are used in the disease diagnosis of plant leaves based on the dataset PlantVillage, especially corn, apples, and potatoes. Feature extraction was performed by Histogram of Oriented Gradients(HOG), and traditional models: Support Vector Machine, Random Forest, Logistic Regression, and Multilayer Perceptron were used for training. The ensemble techniques of bagging, XGBoost, stacking, and voting classifiers brought more improvement in the model performance. Separation of diseases with very close features is still a challenging task. The results seem quite promising for identifying leaf diseases through machine learning techniques, but because the conditions are indistinguishable, further research becomes obligatory.

Plant phenotyping relevance

植物葉の病害状態を画像から推定する機械学習手法の比較・性能分析が中心であり、植物フェノタイピング手法として収録対象。

Code and data availability

公開本文の所在を確認できませんでした。非公開または購読が必要な可能性があります。

No evidence-backed public reproduction asset is currently recorded.