High-Resolution Eggplant Leaf Image Dataset for Plant Disease Classification and Detection

The "EggplantLeaf-ImageDataset" is a high-resolution image dataset of eggplant (Solanum melongena) leaves collected to support machine learning and computer vision research in plant disease detection. The dataset contains 1338 original images captured using a Canon EOS 1300D DSLR camera under consistent natural daylight conditions. Image resolution is preserved at 4000 × 6000 pixels (width × height), ensuring high visual quality uncommon in most publicly available plant leaf datasets.

Images were collected over a 5-day period between April 12 and June 27, 2025, in Changao, Savar, Dhaka (23°53′2″N, 90°19′28″E), and Rayerdia, Kaliganj, Gazipur (23°88′2″N, 90°47′1″E), Bangladesh. Each image is labeled with one of six leaf condition classes:

1. Healthy 267 images
2. Insect Pest 189 images
3. Leaf Spot 232 images
4. Mosaic Virus 189 images
5. Small Leaf 225 images
6. Wilt 236 images

All images are original field samples. Class labels were reviewed and validated by agricultural experts. Only image-level annotations (i.e., class labels) are provided.

Files included:
EggplantLeaf-ImageDataset/ — Root directory containing six subfolders named Healthy, Insect Pest, Leaf Spot, Mosaic Virus, Small Leaf, and Wilt; each folder holds the original JPG images for that class.
EggplantLeaf-ImageDataset/Readme.md — Markdown file describing dataset structure, collection protocol, naming conventions, and usage guidelines.
EggplantLeaf-ImageDataset/metadata.csv — CSV file with two columns, filename (for example, Leaf Spot/Leaf Spot 17.jpg) and class (for example, Leaf Spot), mapping each image to its class label.