State of Art Survey on Plant Leaf Disease Detection

Abstract

Benefits of independent learning and extraction of features have received a lot of attention in recent years from both academic and professional circles. A subcategory of artificial intelligence is deep learning. The use of deep learning towards plant disease recognition can prevent the drawbacks associated with crop disease and production losses. In order to identify and characterize the signs of plant diseases, numerous established machine learning and deep learning architectures are used in conjunction with a number of visualization tools. The detection of leaf disease using image processing has been covered in this survey. Leaf disease diagnosis is enhanced when image segmentation is used in combination with deep learning or machine learning models. A big data collection can be segmented with the use of image segmentation, and the output is then fed to the AI algorithms on disease detection. Additionally, this survey covers the performance metrics of prior studies, which offered guidance for future advancements in plant disease detection and prevention methods.

Plant phenotyping relevance

植物葉の病徴を画像処理・機械学習で検出する方法を中心に整理したレビューであり、植物の病害状態を観測・推定するフェノタイピング手法レビューに該当する。

Code and data availability

This is a survey article on plant leaf disease detection with no paper-specific phenotype datasets, images, code, models, or supplements. Its figures are illustrative diagrams/disease photos, and Table 1 summarizes prior studies' datasets (cited works), not the authors' own assets. No availability statements or author-

No evidence-backed public reproduction asset is currently recorded.