Indian Journal of Science and Technology
DOI: 10.17485/IJST/v16iSP2.2438
Year: 2023, Volume: 16, Issue: Special Issue 2, Pages: 1-5
Original Article
Arnav Jyoti Bharadwaj1, Chinmoy Thakuria1*, Jintu Moni Rabha1, Gariyash Kumar Das1, Kaushik Das1
1Department of Computer Science and Engineering, Dibrugarh University Institute of Engineering and Technology, Dibrugarh, 786004, Assam, India
*Corresponding Author
Email: [email protected]
Received Date:23 March 2023, Accepted Date:26 June 2023, Published Date:20 October 2023
Objective: To employ a Convolutional Neural Network (CNN) for plant species classification based on image data. Method: A dataset of 10,000 plant images was utilized, and the dataset was split into training, validation, and testing sets. The CNN model was trained on the training set and evaluated on the validation and testing sets. Class-wise accuracy and a confusion matrix were analyzed to assess the model's performance. Findings: The CNN model achieved an accuracy of 93%, outperforming traditional machine-learning approaches. High accuracies (>90%) were obtained for 40 out of 50 plant species. However, certain species showed lower accuracies, indicating the need for further investigation and improvement. Novelty: This study contributes to the field of plant species classification by demonstrating the effectiveness of CNNs in achieving high accuracy. The results highlight the potential of automated plant species identification systems and emphasize the importance of exploring advanced techniques, such as transfer learning and ensemble methods, to enhance the model's performance.
Keywords: Convolutional Neural network (CNN), Deep Learning, Confusion matrix, Transfer learning, Plant species classification
© 2023 Bharadwaj et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)
Subscribe now for latest articles and news.