The week's pick
Random Articles
Reseach Article
A Deep Learning-based Framework for Detection and Classification of Ayurvedic Medicinal Plant Leaves
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 110 |
| Year of Publication: 2026 |
| Authors: Bhagyajyothi K.L., Jothimani K. |
10.5120/ijca9718e87d976e
|
Bhagyajyothi K.L., Jothimani K. . A Deep Learning-based Framework for Detection and Classification of Ayurvedic Medicinal Plant Leaves. International Journal of Computer Applications. 187, 110 ( May 2026), 20-25. DOI=10.5120/ijca9718e87d976e
Abstract
Medicinal plants have long been recognized as essential sources of therapeutic compounds in both traditional and modern healthcare systems. However, accurately identifying specific plant parts with medicinal value remains a challenging task prior to laboratory-based extraction and analysis of bioactive components. This study presents a deep learning-based approach for the classification of medicinal plant parts using a Convolutional Neural Network (CNN) with a sigmoid activation function in the final layer for multi-label classification. The proposed method follows a supervised learning paradigm, where annotated image data establishes reliable ground truth for model training.The dataset primarily comprises high-resolution images of plant leaves, which are further utilized to infer and classify multiple plant components. To enhance performance and reduce training time, transfer learning is employed by fine-tuning pre-trained CNN models originally trained on ImageNet. The experimental implementation, including training and evaluation, was carried out using the Google Colab platform.Among the evaluated architectures, MobileNet demonstrated superior performance, achieving an accuracy of 99% on the training set and 98% on the testing set, along with an F1-score of 94%, indicating robust classification capability. Notably, the model maintained a high accuracy of 97% even without batch normalization in the fully connected layer. MobileNet also exhibited the fastest training time due to its efficient use of depthwise separable convolutions, which significantly reduce computational complexity. Furthermore, comparative analysis reveals that the inclusion of batch normalization enhances classification efficiency and model stability. Overall, the findings suggest that MobileNet is a highly effective and computationally efficient model for the classification of medicinal plant parts, offering significant potential for supporting automated plant-based medicinal research and applications.
References
- A. Sabu, et al., “Literature Review of Image Features and Classifiers Used in Leaf-Based Plant Recognition Through Image Analysis Approach,” International Journal of Computer Applications, 2017. .
- E. Sandeep Kumar, et al., “Leaf Features Based Approach for Automated Identification of Medicinal Plants,” International Journal of Engineering & Technology, vol. 7, 2018
- A. Gopal, R. Janani, et al., “Identification of Selected Medicinal Plant Leaves Using Image Features and ANN,” International Journal of Pure and Applied Mathematics, 2018
- A. G. Divya Sree, et al., “Ayurvedic Leaf Identification Using Deep Learning Model,” International Journal for Research in Applied Science & Engineering Technology (IJRASET), vol. 7, 2019
- A. M. Raghukumar, et al., “Comparison of Machine Learning Algorithms for Detection of Medicinal Plants,” in Proceedings of the 4th International Conference on Computing Methodologies and Communication (ICCMC), IEEE 2020.
- J. Ruby, et al., “Ayurvedic Leaf Classification Using Machine Learning Algorithm,” International Journal of Creative Research Thoughts (IJCRT), vol. 9, 2021,.
- R. Upendar Rao, et al., “Identification of Medicinal Plants Using Deep Learning,” International Journal for Research in Applied Science & Engineering Technology (IJRASET), vol. 10, 2022.
- S. Sameer A, et al., “A Novel Approach to Classification of Ayurvedic Medicinal Plants Using Neural Networks,” International Journal of Engineering Research & Technology (IJERT), vol. 11, 2022).
Index Terms
Keywords