Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM65304
Volume:
10 |
6 |
Jun 2026
Pages:
1-3
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Department of Computer Science
Jspm Narhe Technical Campus Pune
Department of Computer Science
Jspm Narhe Technical Campus Pune
Department of Computer Science
Jspm Narhe Technical Campus Pune
Department of Computer Science
Jspm Narhe Technical Campus Pune
Department of Computer Science
Jspm Narhe Technical Campus Pune
- In the domain of traditional medicine and Ayurveda, accurate identification of medicinal herbs demands substantial botanical expertise and is not scalable to the general population. This paper proposes HerbSenseAI, a deep learning-based system for automated recognition of medicinal herbs from leaf images. A Convolutional Neural Network (CNN) trained on a curated dataset of herb leaf images is deployed via a Python-Tkinter GUI. Users register, log in, upload a leaf image, and receive herb predictions along with detailed medicinal benefits retrieved from a SQLite database. Preprocessing is performed with OpenCV; training with TensorFlow and Keras. The proposed system achieves a test accuracy of 94.7%, demonstrating reliability as a real-time herb identification tool for students, pharmacists, and Ayurvedic practitioners.
KEYWORDS
This paper presented HerbSenseAI, a deep learning system for automated medicinal herb identification from leaf images. The CNN trained with TensorFlow and Keras achieves 94.7% test accuracy. Integration of OpenCV for preprocessing, SQLite for herb benefit storage, Tkinter for GUI, and Matplotlib for performance visualization makes the system comprehensive, accessible, and deployable. Future enhancements include: expanding the dataset to cover rare/endangered species; integrating MobileNetV2/EfficientNet for improved accuracy with lower compute; cloud-based model serving for mobile deployment; multi-label classification for mixed herb images.
[1] J. W. Lee and Y. C. Yoon, "Identifying good-quality plants using a wide learning model," in Proc. Int. Conf. Technol. Platforms Services (PlatCon), Jan. 2019, pp. 1–5. [2] M. Arsenovic, M. Karanovic, S. Sladojevic, A. Anderla, and D. Stefanovic, "Addressing current limitations of deep learning methods for plant disease diagnosis," Symmetry, vol. 11, no. 7, p. 939, 2019. [3] A. Rich, U. S. Keceli, C. Catal, H. Y. Yalic, H. Temucin, and B. Tekinerdogan, "A transmission analysis study of plant taxa based on a deep neural network," Comput. Electron. Agric., vol. 158, pp. 20–29, 2019. [4] I. Z. Mukti and D. Biswas, "Transfer learning-based plant leaf disease detection using ResNet50," in Proc. Int. Conf. ECCE, Dec. 2019, pp. 1–6. [5] S. Deshmukh, T. Holkar, M. Jagtap, and A. Ghadge, "Prediction of herbs with its benefits using deep learning techniques," KJ College of Engineering, Pune, India, 2022. [6] V. Bodhwani, D. P. Acharjya, and U. Alone, "Deep crop identification network for agricultural applications," Procedia Computer Science, vol. 152, pp. 186–194, 2019. [7] H. S. Abdullahi, R. E. Sheriff, and F. Mahieddine, "Convolutional neural networks in precision agriculture for image recognition and crop classification," in Proc. Int. Conf. INTECH, Aug. 2017. [8] L. C. De, "Biodiversity and conservation of aromatic plants," Adv. Agric. Crop Res., vol. 5, no. 4, p. 00186, 2016. [9] F. Chollet, Deep Learning with Python, Manning Publications, Shelter Island, NY, 2018. [10] A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd ed., O'Reilly Media, 2019.
Publication Date
6/22/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...