LeafIQ: A Hybrid Deep Learning Framework for Medicinal Leaf Classification Using EfficientNet-B1 and GLCM Texture Feature

Article Sidebar

PDF
Published: 2026-06-09
DOI: https://doi.org/10.70102/3sgtrm65
Keywords:
Medicinal leaf classification, Deep learning, EfficientNet-B1, , GLCM (Gray Level Co-occurrence Matrix), Grad-CAM (Gradient-weighted Class Activation Mapping), Attention fusion, Transfer learning and Data Augmentation

Main Article Content

Dr. R. Jayamala
Department of Computer Science and Engineering University College of Engineering, BIT Campus, Anna University, Trichy, India
Jemuna U
Department of Information Technology University College of Engineering, BIT Campus, Anna University, Trichy, India
Aishwarya K S
Department of Information Technology University College of Engineering, BIT Campus, Anna University, Trichy, India

Abstract

Traditional health care systems such as Ayurveda, Siddha, and Unani need the identification of medicinal leaves. However, manual recognition is challenging due to similarity between species. Most existing work depends on traditional Convolution Neural Network (CNNs) and handcrafted features which perform poor on noised image and similar leaves. In this paper, a hybrid deep learning model called LeafIQ (Leaf Intelligence Quotient) using EfficientNet-B1 and advanced Gray Level Co-occurrence Matrix (GLCM). EfficientNet-B1 model is used for image classification and feature extraction. GLCM is the texture feature extraction technique for accurate extraction of texture. The deep feature vector and the texture feature vector is fused for accurate classification. Gradient-weighted Class Activation Mapping (Grad-CAM) is an Explainable Artificial Intelligence (XAI) used for visually represent the important part of the leaf image. By analysing the images of 30 different plant species, the results show that combined deep features and texture features helps to identify the leaves better. As a result, this framework gives accuracy of 99.82% and reliable classification. LeafIQ is deployed as a Flask web application with a professional chat-style interface supporting Gemini AI integration, YouTube plant search, Tamil–English bilingual output, and Grad-CAM visual explanations.

Article Details

Issue

Vol. 6 No. 2 (2026): Volume 6, Issue 2, 2026 (July-December)

Section

Articles

How to Cite

LeafIQ: A Hybrid Deep Learning Framework for Medicinal Leaf Classification Using EfficientNet-B1 and GLCM Texture Feature (R. Jayamala, J. U, & A. K S, Trans.). (2026). International Journal of Aquatic Research and Environmental Studies, 6(2), 35-48. https://doi.org/10.70102/3sgtrm65

References

1. V. Gautam, G. Kaur, G. S. P. Ghantasala, P. Vidyullatha, S. Allabun, M. Othman, and A. Zheleznyak, “A lightweight deep learning method for medicinal leaf image classification using feature fusion,” Scientific Reports, vol. 15, Art. No. 34417, Jan. 2025, doi: 10.1038/s41598-025-17436-w.

2. 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, Art. No. E42385, Feb. 2025, doi: 10.1016/j.heliyon.2025.e42385.

3. P. Dalvi, D. R. Kalbande, S. S. Rathod, H. Dalvi, and A. Agarwal, “Multiattribute deep CNN-based approach for detecting medicinal plants and their use for skin diseases,” IEEE Transactions on Artificial Intelligence, vol. 6, no. 3, pp. 710–724, Mar. 2025, doi: 10.1109/TAI.2024.3491938.

4. D. Chetia, S. Kr. Kalita, P. P. Baruah, D. Dutta, and T. Akhter, “Identification of traditional medicinal plant leaves using an effective deep learning model and self-curated dataset,” arxiv preprint, arxiv:2501.09363v1, Jan. 2025.

5. T. M. Garang Ok, M. Sibiya, Z. Wang, and M. Nkandla, “Investigation of deep learning techniques used in medicinal plants identification and classification,” IEEE Access, Aug. 2025, doi: 10.1109/ACCESS.2025.3598636.

A. S. Karnik, N. Nair, Y. Sagili, and P. B. Shanthi, “Multi-scale venation pattern analysis for medicinal plant species recognition,” IEEE Access, vol. 13, pp. 125526–125536, Jul. 2025, doi: 10.1109/ACCESS.2025.3589278.

6. M. T. Islam, M. W. Rahman, M. S. Hossain, K. Roksana, I. D. Azpiroz, R. M. Diaz, I. Ashraf, and M. A. Samad, “Medicinal plant classification using particle swarm optimized cascaded network,” IEEE Access, vol. 12, pp. 42465–42478, Mar. 2024, doi: 10.1109/ACCESS.2024.3378262.

7. S. Salsabila, A. Suharso, and P. Purwantoro, “Comparison of deep learning architectures in identifying types of medicinal plant leaf images,” Journal of Artificial Intelligence and Control, vol. 8, no. 1, pp. 39–46, Jul. 2024, doi: 10.30871/jaic.v8i1.6289.

8. R. Swarnalatha and S. Salunkhe, “EEG-centered Parkinson’s disease prediction system using deep learning techniques,” Medical Research Archives, vol. 11, no. 5, May 2023, doi: 10.18103/mra.v11i5.3699.

9. S. Roopashree and J. Anitha, “deepherb: A vision-based system for medicinal plants using Xception features,” IEEE Access, vol. 9, pp. 135927–135941, Sep. 2021, doi: 10.1109/ACCESS.2021.3116207.

10. R. Akter and M. I. Hosen, “CNN-based leaf image classification for Bangladeshi medicinal plant recognition,” in Proc. ETCCE, Dhaka, Bangladesh, 2020, pp. 1–6, doi: 10.1109/ETCCE51779.2020.9350900.

11. M. J. Hasan, S. Mazumdar, and S. Momen, “Deployable deep learning for cross-domain plant leaf disease detection via ensemble learning, knowledge distillation, and quantization,” IEEE Access, vol. 13, Aug. 2025, doi: 10.1109/ACCESS.2025.3595390.

12. S. O. Oppong, F. Twum, J. Ben Hayfron-Acquah, and Y. M. Missah, “A novel computer vision model for medicinal plant identification using log-Gabor filters and deep learning algorithms,” Computational Intelligence and Neuroscience, vol. 2022, Article ID 1189509, Apr. 2022, doi: 10.1155/2022/1189509.

13. M. Tan and Q. V. Le, “efficientnet: Rethinking model scaling for convolutional neural networks,” in Proc. ICML, 2020, arxiv:1905.11946v5.

14. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. CVPR, 2015, pp. 1–12, arxiv:1512.03385v1.

15. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” in ICLR, 2015, arxiv:1409.1556v6.

A. Krizhevsky, I. Sutskever, and G. E. Hinton, “imagenet classification with deep convolutional neural networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–90, 2017, doi: 10.1145/3065386.

B. Szegedy, W. Liu, Y. Jia, S. Reed, D. Erhan, and A. Rabinovich, “Going deeper with convolutions,” in Proc. CVPR, 2015, pp. 1–9, doi: 10.1109/CVPR.2015.7298594.

16. G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proc. CVPR, 2017, pp. 2261–2269, doi: 10.1109/CVPR.2017.243.

17. J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in Proc. CVPR, 2018, pp. 7132–7141, doi: 10.1109/CVPR.2018.00745.

18. R. M. Haralick, K. Shanmugam, and I. Dinstein, “Textural features for image classification,” IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-3, no. 6, pp. 610–621, 1973, doi: 10.1109/TSMC.1973.4309314.

19. R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-CAM: Visual explanations from deep networks via gradient-based localization,” in Proc. ICCV, 2017, pp. 618–626, arxiv:1610.02391v4.

20. S. P. Mohanty, D. P. Hughes, and M. Salathe, “Using deep learning for image-based plant disease detection,” Frontiers in Plant Science, vol. 7, Art. 1419, 2016, doi: 10.3389/fpls.2016.01419.

21. J. Zhang, Z. Lin, J. Brandt, X. Shen, and S. Sclaroff, “Top-down neural attention by excitation backprop,” International Journal of Computer Vision, vol. 126, no. 10, pp. 1084–1102, 2016, arxiv:1608.00507v1.

22. P. Barré, B. C. Stöver, K. F. Müller, and V. Steinhage, “leafnet: A computer vision system for automatic plant species identification,” Ecological Informatics, vol. 40, pp. 50–56, 2017, doi: 10.1016/j.ecoinf.2017.05.005.

23. D. P. Hughes and M. Salathe, “An open access repository of images on plant health,” arxiv, 2015, arxiv:1511.08060.

24. J. Deng, W. Dong, R. Socher, L. J. Li, K. Li, and L. Fei-Fei, “imagenet: A large-scale hierarchical image database,” in Proc. CVPR, 2009, pp. 248–255, doi: 10.1109/CVPR.2009.5206848.

25. F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” in Proc. CVPR, 2017, pp. 1800–1807, doi: 10.1109/CVPR.2017.195.

26. C. Shorten and T. M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” Journal of Big Data, vol. 6, no. 1, p. 60, 2019, doi: 10.1186/s40537-019-0197-0.

27. B. Lim, S. Son, H. Kim, S. Nah, and K. M. Lee, “Enhanced deep residual networks for single image super-resolution,” in Proc. CVPR Workshops, 2017, pp. 136–144, doi: 10.1109/CVPRW.2017.151.

28. N. Kumar, P. N. Belhumeur, A. Biswas, D. W. Jacobs, W. J. Kress, I. C. Lopez, and J. V. B. Soares, “Leafsnap: A computer vision system for automatic plant species identification,” in Proc. ECCV, 2012, pp. 502–516, doi: 10.1007/978-3-642-33709-3_36.

29. T. Munisami, M. Ramsurn, S. Kishnah, and S. Pudaruth, “Plant leaf recognition using shape features and colour histogram with K-nearest neighbour classifiers,” Procedia Computer Science, vol. 58, pp. 740–747, 2015, doi: 10.1016/j.procs.2015.08.095.

30. J. Waldchen and P. Mader, “Plant species identification using computer vision techniques: A systematic literature review,” Archives of Computational Methods in Engineering, vol. 25, no. 2, pp. 507–543, 2018, doi: 10.1007/s11831-016-9206-z.

31. S. Ioffe and C. Szegedy, “Batch normalization,” in Proc. ICML, 2015, pp. 448–456, arxiv:1502.03167v3.

32. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” Journal of Machine Learning Research, vol. 15, pp. 1929–1958, 2014.

33. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” ICLR, 2017, arxiv:1412.6980v9.

A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, and G. Chanan, “pytorch: An imperative style, high-performance deep learning library,” in neurips, 2019, arxiv:1912.01703v1.

34. G. Van Rossum and F. L. Drake, Python 3 Reference Manual, createspace, 2009.

35. S. Roopashree and J. Anitha, "Medicinal Leaf Dataset," Mendeley Data, vol. 1, 2020,

36. Doi: 10.17632/nnytj2v3n5.1.

37. Google, "Gemini API Documentation," Google AI for Developers. [Online]. Available:

38. Https://ai.google.dev/docs. [Accessed: 06-Jun-2026].