Comprehensive Review of Machine Learning and Deep Learning Methods for Plant Disease Detection via PlantVillage Dataset

Abstract

Plant diseases continue to pose a serious challenge to agriculture, leading to substantial yield losses and posing a threat to global food security. Accurate and early identification of plant diseases is crucial for effective crop management. However, traditional manual inspection methods are time-consuming, subjective, and heavily dependent on expert knowledge. With recent advances in artificial intelligence and computer vision, automated plant disease detection systems have emerged as a reliable alternative. These systems depend strongly on large, well-annotated image datasets for training and evaluation. Among publicly available resources, the PlantVillage dataset is one of the most widely used benchmarks for plant disease research. It contains over 50,000 high-resolution RGB leaf images captured under controlled conditions and covers 14 crop species, including tomato, potato, and bell pepper, along with multiple other plants. The dataset represents 38 distinct classes encompassing both healthy and diseased leaf categories. All images are collected against uniform backgrounds, providing visual consistency and making the dataset suitable for benchmarking machine learning and deep learning–based plant disease classification models. This survey provides a comprehensive review of the PlantVillage dataset and its contribution to the advancement of automated plant disease detection. It traces the progression from traditional handcrafted feature–based classifiers to convolutional neural networks, transfer learning approaches, and recent transformer-based architectures. Various methods are compared in terms of classification accuracy, generalization ability, computational efficiency, and robustness. In the survey we have identified that Transfer Learning model showed 99.75% accuracy. The survey also discusses key limitations of the dataset, particularly its controlled imaging conditions and challenges related to real-field deployment. Finally, future research directions are highlighted, including domain adaptation, explainable artificial intelligence, multi-disease recognition, and real-world agricultural applications. This work aims to offer researchers a structured understanding of the PlantVillage dataset and support the development of next-generation intelligent crop disease diagnostic systems.

Plant phenotyping relevance

PlantVillage画像を用いた植物病害状態の画像ベース推定手法とデータセットを中心に、複数の機械学習手法を比較・レビューしているため、植物フェノタイピング方法論のレビューとして含める。

Code and data availability

This is a review/survey of ML/DL methods on the PlantVillage dataset. It contains no authors' own phenotype measurements, image data, code, models, or supplements with availability statements. PlantVillage is a cited prior-work dataset, not a paper-specific asset, and no public URLs are provided in the text.

No evidence-backed public reproduction asset is currently recorded.