MedicinalLeafBD v1.0: A Leakage-Safe Medicinal Plant Leaf Dataset from Bangladesh
Fuente:
Zenodo
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Recurso digital |
| Lenguaje: | inglés |
| Publicado: |
Zenodo
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866901881150767104 |
|---|---|
| author | Sarker, Ovi |
| author_facet | Sarker, Ovi |
| contents | <p>MedicinalLeafBD v1.0 is a curated and leakage-safe medicinal plant leaf dataset developed by Ovi Sarker to support deep learning research in plant recognition and medicinal botany. </p> <p>The dataset contains 5,454 high-quality images from 16 medicinal plant species commonly found in Bangladesh. Each image was standardized to 224×224 pixels and organized using a leakage-safe split strategy (80% training, 10% validation, 10% testing) to prevent data leakage between sets. Duplicate and near-duplicate images were removed using perceptual hashing (pHash).</p> <p>Classes include: Ashok, Basil, Cannonball Tree, Cordia, Debdaru, Heaven Lotus, Jarul, Mastwood, Minjiri, Nageshor, Neem, Punnag, Royna, Telakucha, Thankuni, and Vasaka.</p> <p>All images were collected from publicly available open-access online resources (educational archives, botanical repositories, and Google Images). Data was then restructured, relabeled, and verified manually by the author.</p> <p>This dataset aims to assist researchers and students working in AI-based medicinal plant classification, transfer learning, and explainable AI (Grad-CAM) visualizations.</p> <p>**Key Features:**<br>- 5,454 leaf images across 16 plant species<br>- Leakage-safe 80/10/10 data split<br>- Duplicate removal via perceptual hashing<br>- Ready for TensorFlow/Keras transfer learning<br>- Model metadata file (`model_meta.json`) included</p> <p>**Citation:**<br>O. Sarker, "MedicinalLeafBD v1.0: A Leakage-Safe Medicinal Plant Leaf Dataset from Bangladesh," Zenodo, 2025. DOI: 10.5281/zenodo.17389084.</p> <p>**License:** Creative Commons Attribution 4.0 International (CC BY 4.0)<br>**Contact:** ovisk20@gmail.com</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17389084 |
| institution | Zenodo |
| language | eng |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | MedicinalLeafBD v1.0: A Leakage-Safe Medicinal Plant Leaf Dataset from Bangladesh Sarker, Ovi Medicinal plants Bangladesh Deep learning Image classification EfficientNet TensorFlow Dataset AI research Botany <p>MedicinalLeafBD v1.0 is a curated and leakage-safe medicinal plant leaf dataset developed by Ovi Sarker to support deep learning research in plant recognition and medicinal botany. </p> <p>The dataset contains 5,454 high-quality images from 16 medicinal plant species commonly found in Bangladesh. Each image was standardized to 224×224 pixels and organized using a leakage-safe split strategy (80% training, 10% validation, 10% testing) to prevent data leakage between sets. Duplicate and near-duplicate images were removed using perceptual hashing (pHash).</p> <p>Classes include: Ashok, Basil, Cannonball Tree, Cordia, Debdaru, Heaven Lotus, Jarul, Mastwood, Minjiri, Nageshor, Neem, Punnag, Royna, Telakucha, Thankuni, and Vasaka.</p> <p>All images were collected from publicly available open-access online resources (educational archives, botanical repositories, and Google Images). Data was then restructured, relabeled, and verified manually by the author.</p> <p>This dataset aims to assist researchers and students working in AI-based medicinal plant classification, transfer learning, and explainable AI (Grad-CAM) visualizations.</p> <p>**Key Features:**<br>- 5,454 leaf images across 16 plant species<br>- Leakage-safe 80/10/10 data split<br>- Duplicate removal via perceptual hashing<br>- Ready for TensorFlow/Keras transfer learning<br>- Model metadata file (`model_meta.json`) included</p> <p>**Citation:**<br>O. Sarker, "MedicinalLeafBD v1.0: A Leakage-Safe Medicinal Plant Leaf Dataset from Bangladesh," Zenodo, 2025. DOI: 10.5281/zenodo.17389084.</p> <p>**License:** Creative Commons Attribution 4.0 International (CC BY 4.0)<br>**Contact:** ovisk20@gmail.com</p> |
| title | MedicinalLeafBD v1.0: A Leakage-Safe Medicinal Plant Leaf Dataset from Bangladesh |
| topic | Medicinal plants Bangladesh Deep learning Image classification EfficientNet TensorFlow Dataset AI research Botany |
| url | https://doi.org/10.5281/zenodo.17389084 |