Authors : Sakthi Saranya S.; Dr. W. Rose Varuna

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/565jur3e

Scribd : https://tinyurl.com/mub2utja

DOI : https://doi.org/10.38124/ijisrt/26apr1643

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The automatic detection of medicinal plant species based on the leaf image is a challenging area of study owing to high inter-species similarity, morphological variations within a class, and noisy image acquisition processes. In this study, an algorithmic technique involving image processing and machine learning methods for recognising the type of medicinal plants based on their leaves. The proposed approach involves image acquisition, contrast improvement by CLAHE and median filtering, segmentation of the leaf image using k-means clustering, and feature extraction through GLCM textures and geometrical shapes. This study analyses five different types of ML classifiers: KNN, Naive Bayes, Decision Tree, Random Forest, and SVM. In this study, the experiments were conducted on the publicly available Medicinal Leaf dataset that contains 1800 images of 30 medicinal plant species. The experimental evaluation reveals that the Random Forest classifier model obtains a higher level of accuracy of 93.80% compared to other ML classifiers with a precision of 92.60%, recall of 93.10%, and F1-score of 92.85%.

Keywords : CLAHE, K-Means Segmentation, SVM, Random Forest, Naive Bayes, Decision Tree

References :

1. Mulugeta, A. K., Sharma, D. P., & Mesfin, A. H. (2024). Deep learning for medicinal plant species classification and recognition: a systematic review. Frontiers in Plant Science, 14, 1286088.
2. Hussain, S., et al. (2021). The Classification of Medicinal Plant Leaves Based on Multispectral and Texture Feature Using Machine Learning Approach. Agronomy, 11(2), 263.
3. Prabha, B., & Kavitha, K. (2025). Deep Learning Based Medicinal Plants Identification Using CNN Architecture. In: Proceedings of ICMMCS 2025. Lecture Notes in Networks and Systems, vol 1400. Springer, Cham.
4. Wang, B., et al. (2024). AI-Driven Pattern Recognition in Medicinal Plants: A Comprehensive Review. Computers, Materials & Continua, 81(2).
5. Kan, H. X., Jin, L., & Zhou, F. L. (2017). Classification of Medicinal Plant Leaf Image Based on Multi-feature Extraction. Pattern Recognition and Image Analysis, 27(3), 581–587.
6. Kaur, P. P., & Singh, S. (2021). Classification of Herbal Plant and Comparative Analysis of SVM and KNN Classifier Models on the Leaf Features Using Machine Learning. In: Soft Computing for Intelligent Systems. Springer, Singapore.
7. Kaur, P. P., Singh, S., et al. (2022). Random Forest Classifier Used for Modelling and Classification of Herbal Plants. In: Mobile Radio Communications and 5G Networks. Springer, Singapore.
8. Bhatt, D., et al. (2022). Deep ensemble learning for automatic medicinal leaf identification. International Journal of Information Technology, 14(6), 3089–3097.
9. Karnan, A., & Ragupathy, R. (2024). A Comprehensive Study on Plant Classification Using Machine Learning Models. In: ICT: Smart Systems and Technologies. ICTCS 2023. Springer, Singapore.
10. Roopashree, S. (2020). Medicinal Leaf Dataset. Mendeley Data.
11. Jebadass, J. R., & Balasubramaniam, P. (2023). Preprocessing of leaf images using brightness preserving dynamic fuzzy histogram equalization technique. International Journal of Artificial Intelligence, 12(3), 1149–1157.
12. Sheth, V., et al. (2022). A Comparative Analysis of Machine Learning Algorithms. Procedia Computer Science, 215, 422–431.