Deep learning for mango leaf disease identification: A vision transformer perspective

被引:0
|
作者
Hossain, Md. Arban [1 ]
Sakib, Saadman [1 ]
Abdullah, Hasan Muhammad [2 ]
Arman, Shifat E. [1 ]
机构
[1] Univ Dhaka, Dept Robot & Mechatron Engn, Dhaka 1000, Bangladesh
[2] Bangabandhu Sheikh Mujibur Rahman Agr Univ, Dept Agroforestry & Environm, GIS & Remote Sensing Lab, Gazipur 1706, Bangladesh
关键词
Vision transformer; Plant disease; Deep learning; Smart agriculture;
D O I
10.1016/j.heliyon.2024.e36361
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Over the last decade, the use of machine learning in smart agriculture has surged in popularity. Deep learning, particularly Convolutional Neural Networks (CNNs), has been useful in identifying diseases in plants at an early stage. Recently, Vision Transformers (ViTs) have proven to be effective in image classification tasks. These architectures often outperform most state-of-the-art CNN models. However, the adoption of vision transformers in agriculture is still in its infancy. In this paper, we evaluated the performance of vision transformers in identification of mango leaf diseases and compare them with popular CNNs. We proposed an optimized model based on a pretrained Data-efficient Image Transformer (DeiT) architecture that achieves 99.75% accuracy, better than many popular CNNs including SqueezeNet, ShuffleNet, EfficientNet, DenseNet121, and MobileNet. We also demonstrated that vision transformers can have a shorter training time than CNNs, as they require fewer epochs to achieve optimal results. We also proposed a mobile app that uses the model as a backend to identify mango leaf diseases in real-time.
引用
收藏
页数:14
相关论文
共 50 条
  • [1] Early betel leaf disease detection using vision transformer and deep learning algorithms
    Kusuma S.
    Jothi K.R.
    [J]. International Journal of Information Technology, 2024, 16 (1) : 169 - 180
  • [2] Identification of Cotton Leaf Curl Disease Using CNN and Vision Transformer
    Biju, Goel
    Khan, Asiya
    Walker, David
    Qadri, Salman
    Hssan, Qaim
    Mahmood, Khalid
    Hanan, Abdul
    [J]. INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 2, INTELLISYS 2023, 2024, 823 : 670 - 688
  • [3] Deep transfer learning driven model for mango leaf disease detection
    Singh, Yogendra Pratap
    Chaurasia, Brijesh Kumar
    Shukla, Man Mohan
    [J]. INTERNATIONAL JOURNAL OF SYSTEM ASSURANCE ENGINEERING AND MANAGEMENT, 2024, 15 (10) : 4779 - 4805
  • [4] Deep-Learning-Based Diagnosis of Cassava Leaf Diseases Using Vision Transformer
    Zhuang, Lipeng
    [J]. AICCC 2021: 2021 4TH ARTIFICIAL INTELLIGENCE AND CLOUD COMPUTING CONFERENCE, 2021, : 74 - 79
  • [5] Peanut leaf disease identification with deep learning algorithms
    Laixiang Xu
    Bingxu Cao
    Shiyuan Ning
    Wenbo Zhang
    Fengjie Zhao
    [J]. Molecular Breeding, 2023, 43
  • [6] Peanut leaf disease identification with deep learning algorithms
    Xu, Laixiang
    Cao, Bingxu
    Ning, Shiyuan
    Zhang, Wenbo
    Zhao, Fengjie
    [J]. MOLECULAR BREEDING, 2023, 43 (04)
  • [7] Mango Leaf Stress Identification Using Deep Neural Network
    Gautam, Vinay
    Rani, Jyoti
    [J]. INTELLIGENT AUTOMATION AND SOFT COMPUTING, 2022, 34 (02): : 849 - 864
  • [8] Wheat leaf disease identification based on deep learning algorithms
    Xu, Laixiang
    Cao, Bingxu
    Zhao, Fengjie
    Ning, Shiyuan
    Xu, Peng
    Zhang, Wenbo
    Hou, Xiangguan
    [J]. PHYSIOLOGICAL AND MOLECULAR PLANT PATHOLOGY, 2023, 123
  • [9] Crop Leaf Disease Identification Using Deep Transfer Learning
    Zhou, Changjian
    Zhang, Yutong
    Zhao, Wenzhong
    [J]. JOURNAL OF INFORMATION PROCESSING SYSTEMS, 2024, 20 (02): : 149 - 158
  • [10] Leaf disease identification and classification using optimized deep learning
    Abd Algani, Yousef Methkal
    Marquez Caro, Orlando Juan
    Robladillo Bravo, Liz Maribel
    Kaur, Chamandeep
    Al Ansari, Mohammed Saleh
    Kiran Bala, B.
    [J]. Measurement: Sensors, 2023, 25