2026-10-09T21:48:02Z https://data.mendeley.com/oai

oai:data.mendeley.com/nft66vt53x.1 2026-10-02T06:18:28Z

Islam, Md Hasibul Brinjal Leaf Disease and Fruit Condition Image Dataset: A Field-Collected Dataset from Bangladesh Mendeley Data This dataset is a field-collected image resource for researchers and practitioners working in agriculture, machine learning, and computer vision. It contains images of brinjal (Solanum melongena) leaves and fruits collected under field conditions in Bangladesh. The dataset covers different disease symptoms, pest infestation, nutritional deficiency, and healthy leaf and fruit conditions. The dataset contains two main versions: the "RawDataset" and the "AugmentedDataset". The RawDataset contains 2,206 original images distributed across 11 classes. The AugmentedDataset contains 8,800 images, with 800 images per class, providing a balanced version of the dataset for machine learning and deep learning applications. The 11 classes are: Aphids, Cercospora Leaf Spot, Defect Fruit, Early Blight, Healthy Fruit, Healthy Leaf, Magnesium Deficiency, Mosaic Virus, Phomopsis Blight, Phytophthora Blight, and Powdery Mildew. The images were collected from field locations in Bangladesh using multiple smartphone devices. The images were manually labeled and organized into class-specific folders. All released images are standardized to 300 × 300 pixels and provided in image format. ### Folder Structure The dataset is organized under the parent folder **BrinjalDataset**, which contains two subfolders: RawDataset Number of images: 2,206 Number of classes: 11 Data format: .jpg AugmentedDataset Number of images: 8,800 Number of classes: 11 Images per class: 800 Data format: .jpg Both `RawDataset` and `AugmentedDataset` contain the same 11 class folders. The original dataset preserves the natural class imbalance, while the augmented dataset provides a balanced distribution with 800 images per class. The dataset can be used for brinjal image classification, plant disease and symptom recognition, pest and nutritional disorder recognition, fruit condition classification, computer vision, deep learning, and agricultural image analysis. It is intended to support the development and evaluation of machine learning methods for automated brinjal condition recognition. Agricultural Science Computer Science Plant Disease Development Deep Learning Shuvo, Rabioul Hasan Islam, Nazmul Nur, Fernaz Dataset doi:10.17632/nft66vt53x.1 oai:data.mendeley.com/nft66vt53x.1 Creative Commons Attribution 4.0 International http://creativecommons.org/licenses/by/4.0 https://data.mendeley.com/datasets/nft66vt53x 2026-10-02T06:18:28Z