CitrusLeafVision: A Diverse Dataset for Lemon Leaf Disease Detection

The Lemon Leaf Disease Dataset is a comprehensive collection of 1,238 high-quality images of lemon tree leaves, systematically gathered from Munshi Bazar in Kamalganj Upazila, Moulvibazar District, Bangladesh, between July 3 and July 7, 2025. This dataset consists of eight distinct classes: Bacterial_Canker (216 images), Bacterial_Spot (241 images), Citrus_Leafminer (42 images), Curl_Virus (128 images), Deficiency_Leaf (100 images), Dry_Leaf (129 images), Healthy_Leaf (267 images), and Leaf_Spot (115 images), capturing various healthy and diseased conditions of lemon leaves. The images were captured using a Realme 6i smartphone in natural lighting conditions, ensuring high resolution and clarity. The original images, taken in JPG format at a resolution of 4000 × 3000 pixels, were later resized to 640 × 480 pixels at 72 dpi to standardize the dataset. Although the dataset does not include annotations, it serves as a valuable resource for researchers and machine learning practitioners working on plant disease detection and classification. This dataset is particularly relevant for applications in precision agriculture and automated plant pathology, where early diagnosis and leaf health monitoring can significantly improve crop management strategies.