BDMediLeaves: A leaf images dataset for Bangladeshi medicinal plants identification

• Published in: Data in brief Vol. 50; p. 109488
• Main Authors: Islam, Saiful, Ahmed, Md. Rayhan, Islam, Siful, Rishad, Md Mahfuzul Alam, Ahmed, Sayem, Utshow, Toyabur Rahman, Siam, Minhajul Islam
• Format: Journal Article
• Language: English
• Published: Elsevier 01.10.2023
• Subjects: Computer vision; Data; Deep learning; Image processing; Medicinal leaf classification
• DOI: 10.1016/j.dib.2023.109488
• ISSN: 2352-3409

This paper introduces a newly curated dataset named “BDMediLeaves” that includes a diverse collection of leaf images of ten distinct medicinal plants from various regions in Dhaka, Bangladesh. The ten distinct categories are Phyllanthus emblica, Terminalia arjuna, Kalanchoe pinnata, Centella asiatica, Justicia adhatoda, Mikania micrantha, Azadirachta indica, Hibiscus rosa-sinensis, Ocimum tenuiflorum, and Calotropis gigantea. The dataset contains a total of 2,029 original leaf images, along with an additional 38,606 augmented images. Each original image was meticulously captured under natural lighting conditions with an appropriate background. Experts provided accurate labeling for each image, ensuring its seamless integration into various machine learning (ML) and deep learning (DL) models. This comprehensive dataset holds immense potential for researchers in utilizing various ML and DL methods to make significant advancements in the healthcare and pharmaceutical sectors. It serves as a valuable resource for future investigations, laying the foundation for crucial developments in these domains.