Deep Learning-Based Plant Disease Detection Using Computer Vision

  • Unique Paper ID: 211187
  • Volume: 13
  • Issue: 6
  • PageNo: 3609-3617
  • Abstract:
  • Plant diseases are a major challenge in agriculture, as they can affect crop quality and reduce agricultural productivity. Early identification of plant diseases is important for supporting effective crop management. This research presents a computer vision-based approach for automated plant disease classification using the EfficientNet-B0 architecture. The PlantVillage dataset, consisting of 54,305 RGB images from 14 crop species and 38 classification categories, is used for the experiment. The images are preprocessed through resizing, normalization, and data augmentation techniques to improve the consistency and diversity of training samples. A modified classification layer with dropout is used to produce predictions for the 38 categories. The dataset is divided into training, validation, and testing sets using stratified sampling. The recorded experimental evaluation on 8,146 test images reports an accuracy of 96.94%, a macro F1-score of 95.87%, and a weighted F1-score of 96.97%. These results indicate the potential of image-based deep learning approaches for plant disease classification. However, further evaluation using real-field images is required to assess the system's performance under practical agricultural conditions.

Copyright & License

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.

BibTeX

@article{211187,
        author = {Harish K and Aarti Pimpalkar and Mayuresh Gulame and Ashwini Shahapurkar},
        title = {Deep Learning-Based Plant Disease Detection Using Computer Vision},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {6},
        pages = {3609-3617},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=211187},
        abstract = {Plant diseases are a major challenge in agriculture, as they can affect crop quality and reduce agricultural productivity. Early identification of plant diseases is important for supporting effective crop management. This research presents a computer vision-based approach for automated plant disease classification using the EfficientNet-B0 architecture. The PlantVillage dataset, consisting of 54,305 RGB images from 14 crop species and 38 classification categories, is used for the experiment. The images are preprocessed through resizing, normalization, and data augmentation techniques to improve the consistency and diversity of training samples. A modified classification layer with dropout is used to produce predictions for the 38 categories. The dataset is divided into training, validation, and testing sets using stratified sampling. The recorded experimental evaluation on 8,146 test images reports an accuracy of 96.94%, a macro F1-score of 95.87%, and a weighted F1-score of 96.97%. These results indicate the potential of image-based deep learning approaches for plant disease classification. However, further evaluation using real-field images is required to assess the system's performance under practical agricultural conditions.},
        keywords = {computer vision, convolutional neural network, deep learning, EfficientNet-B0, image classification, Plant disease detection, PlantVillage dataset.},
        month = {November},
        }

Cite This Article

K, H., & Pimpalkar, A., & Gulame, M., & Shahapurkar, A. (2026). Deep Learning-Based Plant Disease Detection Using Computer Vision. International Journal of Innovative Research in Technology (IJIRT), 13(6), 3609–3617.

Related Articles