Deep learning in tropical leaf disease detection: advantages and applications
2024
Zhiye Yao | Mengxing Huang
This paper delves into the realm of artificial intelligence, where an array of deep learning techniques has proven effective in automating crop leaf disease identification and classification. The current paper shows mature detection methodologies for apple, tomato, rice, mango, coconut, and durian leaf diseases with examples while demonstrating research on leaf disease detection in tropical plants. Through this exploration, valuable insights into the benefits and applications of detection techniques based on deep learning methods are provided for leaf disease detection. Highlighting the advantages of deep learning methods are provided for automated feature extraction and disease detection, the paper describes the salient features and challenges of the application of leaf disease detection in the tropics. In this paper, an introductory overview of a leaf disease detection model is offered and delve into the factors influencing detection accuracy and speed while proposing ways to mitigate the inherent trade-offs between these indicators. Furthermore, the challenges, such as multi-scale detection and leaf overlapping, that may occur in plants in the tropics, have been examined, enriching our understanding of deep learning-driven leaf disease detection in tropical agriculture.
Afficher plus [+] Moins [-]Mots clés AGROVOC
Informations bibliographiques
Cette notice bibliographique a été fournie par Maximum Academic Press
Découvrez la collection de ce fournisseur de données dans AGRIS