Buckwheat Disease Recognition Based on Convolution Neural Network

被引:6
|
作者
Liu, Xiaojuan [1 ]
Zhou, Shangbo [1 ]
Chen, Shanxiong [2 ]
Yi, Zelin [3 ]
Pan, Hongyu [2 ]
Yao, Rui [2 ]
机构
[1] Chongqing Univ, Coll Comp Sci, Chongqing 400044, Peoples R China
[2] Southwest Univ, Coll Comp & Informat Sci, Chongqing 400715, Peoples R China
[3] Southwest Univ, Coll Agron & Biotechnol, Chongqing 400715, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 09期
关键词
buckwheat disease; convolutional neural network; image detection; deep learning; recognition; CROP; IDENTIFICATION; CLASSIFICATION; PESTS;
D O I
10.3390/app12094795
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Buckwheat is an important cereal crop with high nutritional and health value. Buckwheat disease greatly affects the quality and yield of buckwheat. The real-time monitoring of disease is an essential part of ensuring the development of the buckwheat industry. In this research work, we proposed an automated way to identify buckwheat diseases. It was achieved by integrating a convolutional neural network (CNN) with the image processing technology. Firstly, the proposed approach would detect the buckwheat disease area accurately. Then, to improve the accuracy of classification, a two-level inception structure was added to the traditional convolutional neural network for accurate feature extraction. It also helps to handle low-quality image problems, which includes complex imaging environment and leaf crossing in sampling buckwheat image, etc. At the same time, instead of the traditional convolution, the convolution based on cosine similarity was adopted to reduce the influence of uneven illumination during the imaging. The experiment proved that the revised convolution enabled better feature extraction within samples with uneven illumination. Finally, the experiment results showed that the accuracy, recall, and F1-measure of the disease detection reached 97.54, 96.38, and 97.82%, respectively. For identifying disease categories, the mean values of precision, recall, and F1-measure were 84.86, 85.78, and 85.4%. Our method has provided important technical support for realizing the automatic recognition of buckwheat diseases.
引用
收藏
页数:22
相关论文
共 50 条
  • [21] Recognition of Radar-Based Deaf Sign Language Using Convolution Neural Network
    Malik, M. D. H. Dol
    Mansor, W.
    Rashid, N. E. Abdul
    Rahman, M. Z. U.
    INTERNATIONAL JOURNAL OF INTEGRATED ENGINEERING, 2023, 15 (03): : 124 - 130
  • [22] Design of Chinese Character Recognition Based on AlexNet Convolution Neural Network
    Xie, Songhua
    Yang, Hailiang
    Nie, Hui
    AIPR 2020: 2020 3RD INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND PATTERN RECOGNITION, 2020, : 68 - 73
  • [23] Banknote Image Defect Recognition Method Based on Convolution Neural Network
    Wang Ke
    Wang Huiqin
    Shu Yue
    Mao Li
    Qiu Fengyan
    INTERNATIONAL JOURNAL OF SECURITY AND ITS APPLICATIONS, 2016, 10 (06): : 269 - 279
  • [24] Deep convolution neural network for image recognition
    Traore, Boukaye Boubacar
    Kamsu-Foguem, Bernard
    Tangara, Fana
    ECOLOGICAL INFORMATICS, 2018, 48 : 257 - 268
  • [25] A Convolution Neural Network Engine for Sclera Recognition
    Maheshan, M. S.
    Harish, B. S.
    Nagadarshan, N.
    INTERNATIONAL JOURNAL OF INTERACTIVE MULTIMEDIA AND ARTIFICIAL INTELLIGENCE, 2020, 6 (01): : 78 - 83
  • [26] Individual Cow Recognition Based on Convolution Neural Network and Transfer Learning
    Xing Yongxin
    Wu Biqiao
    Wu Songping
    Wang Tianyi
    LASER & OPTOELECTRONICS PROGRESS, 2021, 58 (16)
  • [27] Study on SAR Target Recognition Performance Based on Convolution Neural Network
    Zhang Ye
    Zhu Weigang
    Fan Xinyan
    PROCEEDINGS OF 2017 3RD IEEE INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATIONS (ICCC), 2017, : 1687 - 1692
  • [28] Seedlings Supplement Device and Seedling Recognition Based on Convolution Neural Network
    Zhang, Yong
    TRAITEMENT DU SIGNAL, 2022, 39 (05) : 1567 - 1575
  • [29] Korean Sign Language Recognition Based on Image and Convolution Neural Network
    Shin, Hyojoo
    Kim, Woo Je
    Jang, Kyoung-ae
    ICIGP 2019: PROCEEDINGS OF THE 2ND INTERNATIONAL CONFERENCE ON IMAGE AND GRAPHICS PROCESSING / 2019 5TH INTERNATIONAL CONFERENCE ON VIRTUAL REALITY, 2019, : 52 - 55
  • [30] Neural network based on convolution and self-attention fusion mechanism for plant leaves disease recognition
    Zhao, Yun
    Li, Yang
    Wu, Na
    Xu, Xing
    CROP PROTECTION, 2024, 180