Okra disease dataset for classification and segmentation: Dataset collection, analysis and applications.
Journal:
Data in brief
Published Date:
Jul 3, 2025
Abstract
The early diagnosis of okra leaf diseases is crucial for maintaining crop health and ensuring high agricultural productivity. To facilitate the development of robust deep learning models for automated disease detection, we present a comprehensive dataset of 2500 okra leaf images collected from real-time agricultural fields in India. The dataset consists of six classes, including healthy leaves (Class 0) and five diseased categories: Leaf Curly Virus (Class 1), Alternaria Leaf Spot (Class 2), Cercospora Leaf Spot (Class 3), Phyllosticta Leaf Spot (Class 4), and Downy Mildew (Class 5). Each image is resized to 224 × 224 pixels to ensure compatibility with standard deep learning models. The primary objective of this dataset collection is to provide a benchmark resource for researchers working on early-stage plant disease classification, detection and segmentation. This dataset is unique as it is one of the first publicly available Indian okra leaf disease datasets captured in real-world conditions, incorporating natural variations in lighting, leaf positioning, and environmental factors. It serves as a valuable resource for future young researchers in the field of smart agriculture, enabling advancements in machine learning-based disease diagnosis, smart farming applications, and precision agriculture. Future enhancements will focus on expanding the dataset with more images, including different growth stages and environmental conditions, to improve model generalization and real-world applicability.
Authors
Keywords
No keywords available for this article.
