A Labelled Dataset of Healthy and Diseased Maize from Tanzania
Résumé
Abstract Early detection of crop diseases is essential for improving maize productivity and strengthening food security, particularly in regions where agriculture is the main source of livelihood. This paper presents a labelled image dataset of healthy and diseased maize leaves collected in Tanzania to support the development of machine learning models for crop disease diagnosis. The dataset includes data on: healthy leaves, and diseased leaves of Maize Lethal Necrosis (MLN) and Maize Streak Virus (MSV) which are among the most significant threats to maize production in the country. All images are annotated to support tasks such as image classification, object detection and image segmentation. The dataset comprises a total of 243,539 labelled images covering multi-season, making it one of the largest publicly available maize image datasets from Tanzania. It serves as a valuable resource for researchers and practitioners advancing artificial intelligence applications in agriculture.
Citer ce document
Accès au document
Texte intégral en lecture en ligne, réservé aux abonnés SPHAERO et aux membres de l'institution. Se connecter
Voir l'article sur le site de la revueAuteur(s)
Statistiques
Consultations : 1
Téléchargements : 0