Identification of Different Medicinal Plants/Raw Materials Through Image Processing Using Machine Learning Algorithms

References

[1] P. K. Sekharamantry, Dr. 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.

[2] M. A. Kiflie, D. P. Sharma, and M. A. Haile, “Deep learning for Ethiopian indigenous medicinal plant species identification and classification,” Journal of Ayurveda and Integrative Medicine, vol. 15, no. 6, p. 100987,2024.[Online].Available: https://doi.org/10.1016/j.jaim.2024.100987

[3] V. Swu, I. Kharir, and D. Bora, “Identification of Different Plants through Image Processing Using Different Machine Learning Algorithms” Sambodhi, vol. 43, pp. 172-179, 2020.

[4] P. S. Kanda, K. Xia, and O. H. Sanusi, “A deep learning-based recognition technique for plant leaf classification”, IEEE Access, vol. 9, pp. 162590-162613, 2021.

[5] M. S. I. Musyaffa, N. Yudistira, M. A. Rahman, A. H. Basori, A. B. F. Mansur, and J. Batoro, “IndoHerb: Indonesia medicinal plants recognition using transfer learning and deep learning”, Heliyon, vol. 10, no. 23, 2024.

[6] S. Kavitha, T. Satish Kumar, E. Naresh, V. H. Kalmani, K. D. Bamane, and P. K. Pareek, “Medicinal plant identification in real-time using deep learning model” SN Comput. Sci., vol. 5, no. 73, 2024. doi: 10.1007/s42979-023-02398-5.

[7] G. K. Kumar, A. Rama, D. Sri Charan Reddy, and R. Vinayak, “Medicinal plants identification through image processing and machine learning,” 2025.

[8] S. Deshmukh, P. M. Mudhaliar, and S. Thorat,”Ayurvedic plant identification using image processing and artificial intelligence” Int. J. Sci. Res. Comput. Sci. Eng. Inf. Technol., vol. 7, pp. 212-218, 2021.

[9] B. Dey, J. Ferdous, R. Ahmed, and J. Hossain, “Assessing deep convolutional neural network models and their comparative performance for automated medicinal plant identification from leaf images,” Heliyon, vol. 10, no. 1, e23655, 2024. [Online].Available: https://doi.org/10.1016/j.heliyon.2023.e23655

[10] L. Li, Z. M. Li, and Y. Z. Wang, “A method of two-dimensional correlation spectroscopy combined with residual neural network for comparison and differentiation of medicinal plants raw materials superior to traditional machine learning: a case study on Eucommia ulmoides leaves” Plant Methods, vol. 18, no. 1, p. 102,.

[11] uv}~€Œ��¢£º»ÎÏÐÝ" # $ % & . óæÜÎÁÜÎÁܶ®¢®¢—‰€thhYKhh^~ h˜gCJOJQJaJh^~ CJOJQJaJhÚ4¡h^~ 6�OJQJhÚ4¡6�OJQJhh^~ h^~ OJQJhhh^~ hhhÚ4¡h^~ CJ(KH0aJ(hÚ4¡hÚ4¡CJ(KH0aJ(vÐ# $ % & IJWXKL®óÞÉ´¢¢””„wwww$dð¤a$gdÚ4¡$ &Fdë¤a$gd˜g [Some characters in this reference could not be displayed correctly — please refer to the published PDF for the full reference.]

[12] „d¤`„gd¤d¤d[$\$gdÚ4¡ [Some characters in this reference could not be displayed correctly — please refer to the published PDF for the full reference.]

@article{1708523,
      author = {B Meenu, V Deekshitha, Gaddam Sai Likhitha, Aishwarya Vilas Patil, Prof. Afroz Pasha},
      title = {Identification of Different Medicinal Plants/Raw Materials Through Image Processing Using Machine Learning Algorithms},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {8},
      number = {11},
      pages = {888-893},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1708523.pdf},
      abstract = {In an era where nature?s pharmacy brims with untapped potential, swiftly and accurately identifying medicinal plants is a transformative leap for healthcare, biodiversity, and sustainable innovation. This project unveils a groundbreaking hybrid approach, melding image processing with cutting-edge machine learning?fusing Conditional Generative Adversarial Networks (CGANs), Wasserstein GANs (WGANs), Deep Convolutional GANs (DCGANs), and the formidable VGG16 model, topped with logistic regression?to revolutionize plant recognition. Picture an AI botanist with a creative twist, not just spotting plants from snapshots but conjuring synthetic images to sharpen its skills, built on a rich, curated dataset of medicinal wonders amplified by sophisticated augmentation to echo real-world diversity. Our method weaves through data loading, preprocessing, and feature extraction, birthing two stellar models: Model 1 (CGAN with Logistic Regression), scoring a robust AUC-ROC of 0.94, and Model 2 (WGAN and DCGAN with Logistic Regression), rocketing to an awe-inspiring 0.99, flaunting near-perfect classification across 40 species across 40 species. Encased in a sleek web application, this tech marvel bridges complex AI with everyday use, its success vividly etched in confusion matrices and precision-recall metrics, with Model 2 shining in stability and accuracy?a bold stride toward preserving herbal wisdom, fueling research, and championing Sustainable Development Goals, where pixels and plants collide to spark a blooming future of botanical brilliance.},
      month = {May},
  }