Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security, IACIDS 2023, 23-25 November 2023, Lavasa, Pune, India

Research Article

Deep Learning Based Paddy Disease Classification Using Resnet-50

Download87 downloads
  • @INPROCEEDINGS{10.4108/eai.23-11-2023.2343203,
        author={Thamarai selvi S B and Thirumurugan  S and Kanish  P and Surya  M},
        title={  Deep Learning Based Paddy Disease Classification Using Resnet-50},
        proceedings={Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security, IACIDS 2023, 23-25 November 2023, Lavasa, Pune, India},
        publisher={EAI},
        proceedings_a={IACIDS},
        year={2024},
        month={3},
        keywords={deep learning convolutional neural network paddy disease detection agriculture},
        doi={10.4108/eai.23-11-2023.2343203}
    }
    
  • Thamarai selvi S B
    Thirumurugan S
    Kanish P
    Surya M
    Year: 2024
    Deep Learning Based Paddy Disease Classification Using Resnet-50
    IACIDS
    EAI
    DOI: 10.4108/eai.23-11-2023.2343203
Thamarai selvi S B1,*, Thirumurugan S2, Kanish P2, Surya M2
  • 1: Assistant Professor of Computer Science and Engineering, K S Rangasamy College of Technology, Tiruchengode, India
  • 2: Student of Computer Science and Engineering, K S Rangasamy College of Technology, Tiruchengode, India
*Contact email: thamaraiselvi@ksrct.ac.in

Abstract

In this research, a Convolutional Neural Network (CNN) utilizing the ResNet- 50 architecture is presented, demonstrating a noteworthy accuracy level of 97% in the classification of paddy diseases. By curating an extensive dataset of paddy disease images, employing data augmentation techniques, and tailoring the model, a practical tool for efficient disease detection and management in agriculture has been developed. The model's performance is further enhanced through a fine-tuning process that involves adjusting the learning rates of specific layers. This research not only underscores the potential of deep learning within the realm of agriculture but also contributes a valuable resource for farmers and agronomists. It provides them with a timely and precise means of paddy disease identification, ultimately leading to improved crop yields and the mitigation of losses.