Deep learning and content-based filtering techniques for improving plant disease identification and treatment recommendations: A comprehensive review.

Abstract

The importance of identifying plant diseases has risen recently due to the adverse effect they have on agricultutal production. Plant diseases have been a big concern in agriculture, as they affect crop production, and constitute a major threat to global food security. In the domain of modern agriculture, effective plant disease management is vital to ensure healthy crop yields and sustainable practices. Traditional means of identifying plant disease are faced with lots of challenges and the need for better and efficient detection methods cannot be overemphazised. The emergence of advanced technologies, particularly deep learning and content-based filtering techniques, if integrated together can changed the way plant diseases are identified and treated. Such as speedy and correct identification of plant diseases and efficient treatment recommendations which are keys for sustainable food production. In this work, We try to investigate the current state of research, identified gaps and limitations in knowledge, and suggests future directions for researchers, experts and farmers that could help to provide better ways of mitigating plant disease problems.

Plant phenotyping relevance

植物病害の画像・深層学習による識別手法を中心に扱うレビューであり、感染植物の病害状態を観測から推定するフェノタイピング手法のレビューに該当する。

Code and data availability

This is a review article with no original phenotyping measurements, analysis code, models, or author-generated datasets. The plant disease image datasets it describes (PlantVillage, Plant Pathology 2020, PlantDoc, RoCoLe, BRACOL, etc.) are cited third-party resources surveyed by the review, not paper-specific assets,so

No evidence-backed public reproduction asset is currently recorded.