Files and links (1)
Open Access CC BY V4.0
Journal article
A survey of deep learning techniques for image-based disease detection in dicot plants
Information processing in agriculture
2026
Abstract
Deep learning techniques have become popular for detecting dicot plant diseases with high accuracy and throughput. Their recent impact on agriculture has been significant, helping minimize crop losses and improve management efficiency and productivity. Detecting dicot plant disease from imagery is challenging because overlapping leaves and shadows make it difficult to capture clear images. Moreover, different diseases can sometimes show very similar symptoms. This paper reviews state-of-the-art deep learning techniques used in dicot plant disease detection. We covered well-curated 140 scientific papers published between 2016 and 2025. We developed a taxonomy for these works covering key aspects such as data acquisition, dataset preparation, image pre-processing, feature extraction, and the implementation of deep learning models. We summarized the current challenges and future research opportunities in this area. We found that most studies use short-range images, whereas mid or long-range images could make disease detection more practical at scale. To provide a roadmap for future studies, we discuss various detection scales (leaf/fruit/stem, plant, and field) along with different data acquisition sources (handheld devices, UAVs, and robots).
Details
- Title
- A survey of deep learning techniques for image-based disease detection in dicot plants
- Authors/Creators
- Adeeba AnisPenghao WangChengdao LiFerdous Sohel
- Publication Details
- Information processing in agriculture
- Publisher
- Elsevier B.V
- Identifiers
- 991005875444107891
- Copyright
- © 2026 The Authors
- Murdoch Affiliation
- Centre for Crop and Food Innovation; School of Information Technology; School of Medical, Molecular and Forensic Sciences
- Language
- English
- Resource Type
- Journal article
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
Source: SDGs in the Output
Metrics
1 Record Views