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{179443,
        author = {Saurabh Verma and Swati Singh and Akash Kumar Patel and Dr. Devesh Katiyar},
        title = {Crop Disease Detection Using Deep Learning techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {7890-7892},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179443},
        abstract = {The increasing threat of plant diseases severely impacts agricultural productivity and farmer livelihoods. With the advancement of artificial intelligence, deep learning offers a promising solution to detect crop diseases early and accurately. This paper investigates the classification of diseases in three essential crops—rice, wheat, and tomato—using a dataset of 3000 images collected from Indian farms. Three CNN architectures—ResNet50, DenseNet121, and Xception—were trained and evaluated. Among them, Xception achieved the highest accuracy of 94%, followed by DenseNet at 88% and ResNet at 87%. The models were assessed using precision, recall, F1-score, specificity, and confusion matrix. The results demonstrate the significant potential of CNNs in automating crop disease identification.},
        keywords = {[Crop Disease Detection, CNN, Xception, DenseNet, ResNet, Deep Learning, Tomato, Rice, Wheat, Indian Dataset, Precision, Accuracy].},
        month = {May},
        }