Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{181074,
        author = {Pragati Mahale and Sumedh Chavan and Shashwat Kale and Aditya Shiledar},
        title = {Plants Species Identification for Medicinal Plants Using Convolutional Neural Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {6301-6310},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181074},
        abstract = {Accurate identification of medicinal plant species is crucial in medicine, botany, pharmacology, and conservation biology. Identification through conventional methods largely relies on human judgment and visual inspection, which are time-consuming, labor-intensive, and prone to human error, especially when determining between morphologically similar species. To circumvent such limitations, the present research proposes a fast and automatic system for plant species identification based on Convolutional Neural Networks (CNNs). The model leverages the power of deep learning to extract distinctive features of plant leaf images with respect to shape, texture, and vein pattern for proper classification. A comprehensive dataset of high-resolution images of medicinal plants was used, with multiple light conditions and environmental changes to improve model generalization. Data augmentation techniques such as flipping, rotation, and color shifting were used to improve dataset robustness. Transfer learning and ensemble learning were utilized to reinforce the model further to improve accuracy and avoid overfitting. Attention mechanisms were also utilized to allow the network to focus on the informative regions of each image. The proposed CNN-based model yielded better classification performance, and performance metrics such as accuracy, precision, recall, and F1-score confirmed its applicability in practical situations. The model's performance was also compared to existing algorithms such as Faster R-CNN, SSD, and hybrid CNN-Random Forest models. The results affirm the applicability of the model in real-time applications, which include mobile plant identification apps and biodiversity monitoring. The research helps improve the classification of medicinal plants, promotes conservation, and streamlines the cultivation of sustainable herbal medicine systems.},
        keywords = {Medicinal Plant Identification, Convolutional Neural Networks (CNN), Deep Learning, Image Classification, Plant Leaf Recognition, Data Augmentation, Transfer Learning.},
        month = {September},
        }