A Deep Learning Framework for Automated Recognition of Traditional Indian Medicinal Flora

International Journal of Emerging Research in Science, Engineering, and Management
Vol. 2, Issue 3, pp. 351-357, March 2026.

https://doi.org/10.58482/ijersem.v2i3.45

This work is licensed under a Creative Commons Attribution 4.0 International License.

A Deep Learning Framework for Automated Recognition of Traditional Indian Medicinal Flora

N Babu

Erasappa Murali

E Bhanu Prakash

Obili Dhakshayani

Bakka Tejaswini

Thupakula Chandrakanth

Department of CSE, Siddharth Institute of Engineering & Technology, Puttur, AP, India.

Full Text PDF

Abstract: Recognizing therapeutic herbs accurately poses genuine difficulties for those without botanical training. This method focus on building a recognition framework targeting forty herb varieties native to the Indian subcontinent. The investigation tested three distinct neural architectures against leaf photographs. A standard convolutional model formed the starting point, reaching 80.13% correct classifications. Then employed MobileNet configured for transfer operations, which pushed results to 90.74%. The third approach merged MobileNet’s feature capabilities with recurrent sequence handling through LSTM modules. This combined strategy delivered 92.94% validation performance with strong consistency across herb categories. The leaf collection contained roughly 3,800 photographs spanning all forty varieties. Results point toward meaningful advantages when spatial pattern recognition works alongside temporal sequence modelling for botanical classification challenges.

Keywords: Herbal plant recognition, neural architectures, convolutional networks, lightweight models, sequence learning.

References: 

  1. G L. Y. T R and J. R, “A Comprehensive Survey on Deep Learning Applications in Plant Disease Detection and Classification,” 2025 3rd International Conference on Inventive Computing and Informatics (ICICI), Bangalore, India, 2025, pp. 758-765, doi: 10.1109/ICICI65870.2025.11069894.
  2. A. Arun, S. Sharma, B. Singh, and T. Hazra, “Identification of Plant Species Using Convolutional Neural Network with Transfer Learning,” Journal of Phytopathology, vol. 173, no. 1, Jan. 2025, doi: 10.1111/jph.70032.
  3. B. Nayak, S. Dash, A. Bisoyi, and D. P. Dash, “Plant disease diagnosis: A survey and comparative analysis of current techniques,” Next Research., vol. 8, p. 101596, Mar. 2026, doi: 10.1016/j.nexres.2026.101596.
  4. H. Bouakkaz, M. Bouakkaz, C. A. Kerrache, and S. Dhelim, “Enhanced classification of medicinal plants using deep learning and optimized CNN architectures,” Heliyon, vol. 11, no. 3, p. e42385, Jan. 2025, doi: 10.1016/j.heliyon.2025.e42385.
  5. Q. Guo, X.-J. Wu, J. Kittler, and Z. Feng, “Differentiable neural architecture learning for efficient neural networks,” Pattern Recognition, vol. 126, p. 108448, Jan. 2022, doi: 10.1016/j.patcog.2021.108448.
  6. A. Arun, S. Sharma, B. Singh, and T. Hazra, “Identification of Plant Species Using Convolutional Neural Network with Transfer Learning,” Journal of Phytopathology, vol. 173, no. 1, Jan. 2025, doi: 10.1111/jph.70032.
  7. B. R. Pushpa, S. Jyothsna, and S. Lasya, “HybNet: A hybrid deep models for medicinal plant species identification,” MethodsX, vol. 14, p. 103126, Dec. 2024, doi: 10.1016/j.mex.2024.103126.
  8. A. Abade, P. A. Ferreira, and F. De Barros Vidal, “Plant diseases recognition on images using convolutional neural networks: A systematic review,” Computers and Electronics in Agriculture, vol. 185, p. 106125, Apr. 2021, doi: 10.1016/j.compag.2021.106125.
  9. A. Jafar, N. Bibi, R. A. Naqvi, A. Sadeghi-Niaraki, and D. Jeong, “Revolutionizing agriculture with artificial intelligence: plant disease detection methods, applications, and their limitations,” Frontiers in Plant Science, vol. 15, p. 1356260, Mar. 2024, doi: 10.3389/fpls.2024.1356260.
  10. S. Joshi et al., “Neural 3D reconstruction and immersive VR visualization of row crops across phenological growth stages,” Smart Agricultural Technology, p. 102024, Mar. 2026, doi: 10.1016/j.atech.2026.102024.
  11. V. C. Gandhi, P. P. Gandhi, A. K. A. Raheem, Y. T. Alzubaidi, K. Khudaybergenov, and M. Khishe, “Advancing glaucoma diagnosis: Multi-modal deep learning with vision transformer architectures,” Intelligence-Based Medicine, vol. 13, p. 100355, Jan. 2026, doi: 10.1016/j.ibmed.2026.100355.
  12. R. Mahmood, S. Patel, and K. Elleithy, “EEViT: Efficient Enhanced Vision Transformer Architectures with Information Propagation and Improved Inductive Bias,” AI, vol. 6, no. 9, p. 233, Sep. 2025, doi: 10.3390/ai6090233.
Download PDF

This article is part of Volume 2, Issue 3 (March 2026)