Full Text PDF
ESTD Year: 2017 | Impact Factor: 6.9
DOI Prefix: 10.47001/IRJIET
ESTD Year: 2017 | Impact Factor: 6.9
DOI Prefix: 10.47001/IRJIET
Vol 10 No 7 (2026): Volume 10, Issue 7, July 2026 | Pages: 137-143
International Research Journal of Innovations in Engineering and Technology
OPEN ACCESS | Research Article | Published Date: 31-07-2026
Medicinal plants have long been recognized as an important source of natural remedies and play a crucial role in traditional and modern healthcare systems. Accurate identification of medicinal plants is essential to ensure their proper use in herbal medicine, agriculture, and pharmaceutical research. However, manual identification of plant species based on leaf characteristics requires specialized botanical knowledge and can be difficult for non-experts due to the similarities in leaf shape, texture, and vein structures among different species. With the rapid advancement of technologies in Artificial Intelligence and Deep Learning, automated plant recognition systems have become an effective solution for addressing this challenge.
This research proposes an automated medicinal leaf identification system based on deep learning techniques for accurate classification of plant species. The system utilizes the MobileNetV2 model, which is designed for efficient image classification with reduced computational complexity. The dataset used in this study consists of labeled images of medicinal plant leaves collected from various sources. Prior to training, image preprocessing techniques such as resizing, normalization, and data augmentation are applied to improve model performance and reduce overfitting. Transfer learning is employed to leverage pretrained weights and enhance feature extraction capabilities.
The proposed model automatically learns distinguishing visual features including leaf shape, edge patterns, venation structure, and texture. After training, the system demonstrates high classification accuracy in identifying multiple medicinal plant species. To improve accessibility and practical usability, the trained model is integrated into a web-based interface developed using Streamlit, allowing users to upload leaf images and obtain real-time predictions. The results indicate that the proposed system can serve as an efficient and reliable tool for medicinal plant identification. This approach has potential applications in agriculture, botanical research, environmental monitoring, and digital herbal knowledge systems.
CNN, MobileNet, Deep Learning, Image Classification, Medicinal Leaves.
Minakshee Chandankhede, Pratik Gawande, Lokeshwar Kawle, Ridhi Sharma, Rishikant Kardate, & Rujul Kindarle. (2026). Real-Time Medicinal Leaf Classification Using Lightweight Deep Learning Models. International Research Journal of Innovations in Engineering and Technology - IRJIET, 10(7), 137-143. Article DOI https://doi.org/10.47001/IRJIET/2026.107015
This work is licensed under Creative common Attribution Non Commercial 4.0 Internation Licence
M. Deshmukh, “Deep Learning for the Classification and Recognition of Medicinal Plant Species,” Indian J. Sci. Technol., vol. 17, no. 11, 2024.
R. Subramanian, “Mobile Based Ayurvedic Leaf Detection using Deep Learning and NLP,” Int. J. Intell. Syst. Appl. Eng., vol. 12, 2024.
H. Tiwari et al., “Identification of Medicinal Plant Leaves Based on Spectral Characteristics,” J. Adv. Zool., vol. 44, 2024.
P. K. Sharma, “Medicinal Plant Identification by Leaf Structure Using Ensemble Methods,” IJIES, vol. 5, no. 9, 2024.
P. K. Sharma, “Medicinal Plant Identification by Leaf Structure Using Ensemble Methods on Deep Learning Algorithms,” International Journal of Recent Advances in Multidisciplinary Topics, vol. 5, no. 9, pp. 51–53, Sep. 2024.
P. K. Sekharamantry, M. S. Rao, Y. Srinivas, and A. Uriti, “PSR-LeafNet: A Deep Learning Framework for Identifying Medicinal Plant Leaves Using Support Vector Machines,” Big Data and Cognitive Computing, vol. 8, no. 12, p. 176, 2024, doi: 10.3390/bdcc8120176.
R. Subramanian, “Mobile Based Ayurvedic Leaf Detection and Retrieving Its Medicinal Properties Using Deep Learning and NLP,” International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 3, pp. 3561–3565, 2024.
M. Deshmukh, “Deep Learning for the Classification and Recognition of Medicinal Plant Species,” Indian Journal of Science and Technology, vol. 17, no. 11, pp. 1070–1077, 2024, doi: 10.17485/IJST/v17i11.3099.
S. Salsabila, A. Suharso, and P. Purwantoro, “Comparison of Deep Learning Architectures in Identifying Types of Medicinal Plant Leaf Images,” Journal of Applied Informatics and Computing, vol. 8, no. 1, pp. 39–46, 2024, doi: 10.30871/jaic.v8i1.6289.
V. Sharma, K. Chaurasia, and A. Bansal, “Optimizing Species Recognition in Medicinal Plants: A Comprehensive Evaluation of Deep Learning Models,” in Proc. 14th Int. Conf. Cloud Computing, Data Science & Engineering (Confluence), 2024, doi: 10.1109/Conflu-ence60223.2024.10463198.
X. Li et al., “MTJNet: Multi-task Joint Learning Network for Advancing Medicinal Plant and Leaf Classification,” Knowledge-Based Systems, vol. 299, p. 112147, 2024, doi: 10.1016/j.knosys.2024.112147.
D. Awasthi, A. K. Shukla, and A. Gupta, “An Advanced Review of Machine Learning Methods for Identifying Medicinal Plant Leaf Diseases,” African Journal of Biomedical Research, vol. 28, no. 1S, pp. 2378–2385, 2025, doi: 10.53555/AJBR.v28i1S.6700.
V. Subitha, S. M. Asha Jelbhin, and A. P. Antony, “Enhancing Medicinal Plant Classification and Supply Chain Integrity Using CNN and LSTM Networks,” Journal of Computer Science Engineering and Software Testing, vol. 11, no. 2, pp. 24–31, 2025, doi: 10.5755/j01.itc.53.1.34345.
D. Chetia et al., “Identification of Traditional Medicinal Plant Leaves Using an Effective Deep Learning Model and Self-Curated Dataset,” arXiv preprint, 2025, doi: 10.48550/arXiv.2501.09363.