Research Article Open Access

Dataset of Selected Medicinal Plant Species of the Genus Brachylaena: A Comparative Application of Deep Learning Models for Plant Leaf Recognition

Avuya Deyi1, Arnaud Nguembang Fadja2, Eleonora Deborah Goosen3, Xavier Siwe Noundou4 and Marcellin Atemkeng1
  • 1 Department of Mathematics, Rhodes University, 6139 Makhanda, South Africa
  • 2 Department of Engineering, University of Ferrara, Via Saragat 1, 44122 Ferrara, Italy
  • 3 Department of Pharmacy, Faculty of Pharmacy, Rhodes University, Makhanda 6139, South Africa
  • 4 Department Pharmaceutical Sciences, School of Pharmacy, Sefako Makgatho Health Sciences University, Pretotia, 0204, South Africa

Abstract

Since several active pharmaceutical ingredients are sourced from medicinal plants, identifying and classifying these plants are generally a valuable and essential task during the drug manufacturing process. For many years, identifying and classifying those plants have been exclusively done by experts in the domain, such as botanists and herbarium curators. Recently, powerful computer vision technologies, using deep learning or deep artificial neural networks, have been developed for classifying or identifying objects using images. A convolutional neural network is a deep learning architecture that outperforms previous state-of-the-art approaches in image classification and object detection based on its efficient feature extraction of images. This study investigated several pre-trained convolutional neural networks for identifying and classifying leaves of three species of the genus Brachylaena. The three species considered were Brachylaena discolor, Brachylaena ilicifolia, and Brachylaena elliptica. All three species are used medicinally by people in South Africa. We trained and evaluated different deep convolutional neural networks from 1259 labeled images of those plant species (at least 400 for each species) split into training, evaluation, and test sets. The best model provided a 98.26% accuracy using cross-validation with a confidence interval of ±2.16%.

Journal of Computer Science
Volume 19 No. 11, 2023, 1387-1397

DOI: https://doi.org/10.3844/jcssp.2023.1387.1397

Submitted On: 27 February 2023 Published On: 17 October 2023

How to Cite: Deyi, A., Fadja, A. N., Goosen, E. D., Noundou, X. S. & Atemkeng, M. (2023). Dataset of Selected Medicinal Plant Species of the Genus Brachylaena: A Comparative Application of Deep Learning Models for Plant Leaf Recognition. Journal of Computer Science, 19(11), 1387-1397. https://doi.org/10.3844/jcssp.2023.1387.1397

  • 1,556 Views
  • 1,055 Downloads
  • 0 Citations

Download

Keywords

  • Deep Learning
  • Medicinal Plants Classification
  • Brachylaena Discolor
  • Brachylaena Ilicifolia
  • Brachylaena
  • Transfer Learning