Innovative Leaf Disease Mapping: Unsupervised Anomaly Detection for Precise Area Estimation

Abstract

Abstract Detecting and quantifying the diseased regions in a leaf is an important task in plant breeding in order to select plants based on disease resistance. Ratings done by eye and hand are not accurate, can be highly subjective and take a lot of work hours. Using machine learning, it is possible to generate faster more accurate data. By combining modern anomaly detection algorithms with masking algorithms a robust method capable of estimating the infected leaf area was developed, resulting in a novel method with superior results. Using unsupervised models both for the masking and for the detection, the method can easily be used for different kinds of detection tasks.

Plant phenotyping relevance

葉の病斑領域と感染面積を画像から推定する機械学習手法の開発が研究の中心であり、植物病害の表現型測定に該当する。

Code and data availability

The paper describes a plant disease area estimation method using RD++ anomaly detection on PlantVillage images and mentions a 'Diffusion Diseases Repository' for implementation, but no public URL, deposit, or availability statement for the authors' code, data, or models is provided in the supplied blocks. PlantVillage,

No evidence-backed public reproduction asset is currently recorded.