Plant-Leaf Recognition Based on Sample Standardization and Transfer Learning

被引:0
|
作者
Li, Guoxin [1 ]
Zhang, Ruolei [1 ]
Qi, Dawei [1 ]
Ni, Haiming [1 ]
机构
[1] Northeast Forestry Univ, Coll Sci, Hexing Rd 26, Harbin 150040, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 18期
基金
中国国家自然科学基金;
关键词
plant-leaf recognition; minimum enclosing quadrate; standardization of datasets; convolutional neural network; transfer learning;
D O I
10.3390/app14188122
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
In recent years, deep-learning methods have significantly improved the classification results in the field of plant-leaf recognition. However, limited by the model input, the original image needs to be compressed to a certain size before it can be input into the convolutional neural network. This results in great changes in the shape and texture information of some samples, thus affecting the classification accuracy of the model to a certain extent. Therefore, a minimum enclosing quadrate (MEQ) method is proposed to standardize the sample datasets. First, the minimum enclosing rectangle (MER) of the leaf is obtained in the original image, and the target area is clipped. Then, the minimum enclosing quadrate of the leaf is obtained by extending the short side of the rectangle. Finally, the sample is compressed to fit the input requirements of the model. In addition, in order to further improve the classification accuracy of plant-leaf recognition, an EC-ResNet50 model based on transfer-learning strategy is proposed and further combined with the MEQ method. The Swedish leaf, Flavia leaf, and MEW2012 leaf datasets are used to test the performance of the proposed methods, respectively. The experimental results show that using the MEQ method to standardize datasets can significantly improve the classification accuracy of neural networks. The Grad-CAM visual analysis reveals that the convolutional neural network exhibits a higher degree of attention towards the leaf surface features and utilizes more comprehensive feature regions during recognition of the leaf samples processed by MEQ method. In addition, the proposed MEQ + EC-ResNet50 method also achieved the best classification results among all the compared methods. This experiment provides a widely applicable sample standardization method for leaf recognition research, which can avoid the problem of sample deformation caused by compression processing and reduce the interference of redundant information in the image to the classification results to a certain degree.
引用
收藏
页数:24
相关论文
共 50 条
  • [1] Identification of Plant-Leaf Diseases Using CNN and Transfer-Learning Approach
    Hassan, Sk Mahmudul
    Maji, Arnab Kumar
    Jasinski, Michal
    Leonowicz, Zbigniew
    Jasinska, Elzbieta
    [J]. ELECTRONICS, 2021, 10 (12)
  • [2] Leaf Classification for Plant Recognition with Deep Transfer Learning
    Beikmohammadi, Ali
    Faez, Karim
    [J]. 2018 4TH IRANIAN CONFERENCE ON SIGNAL PROCESSING AND INTELLIGENT SYSTEMS (ICSPIS), 2018, : 21 - 26
  • [3] Deep learning model for plant-leaf disease detection in precision agriculture
    Bajpai C.
    Sahu R.
    Naik K.J.
    [J]. International Journal of Intelligent Systems Technologies and Applications, 2023, 21 (01) : 72 - 91
  • [4] Prediction and Analysis of Plant-Leaf Disease in Agricultural by using Image Processing and Machine Learning Techniques
    Babu, T. R. Ganesh
    Priya, S.
    Chandru, J. Gopi
    Balamurugan, M.
    Gopika, J.
    Praveena, R.
    [J]. 2021 INTERNATIONAL CONFERENCE ON COMPUTATIONAL PERFORMANCE EVALUATION (COMPE-2021), 2021, : 540 - 544
  • [5] Plant Leaf Recognition Using Competitive Based Learning Algorithm
    Imah, E. M.
    Rahayu, Y. S.
    Wintarti, A.
    [J]. 2ND ANNUAL APPLIED SCIENCE AND ENGINEERING CONFERENCE (AASEC 2017), 2018, 288
  • [6] PLANT-LEAF CROSS-SECTION TREATED AS AN OPTICAL SYSTEM
    ALLEN, WA
    RICHARDS.AJ
    [J]. JOURNAL OF THE OPTICAL SOCIETY OF AMERICA, 1972, 62 (05) : 713 - &
  • [7] A Deep Learning-Based Recognition Technique for Plant Leaf Classification
    Kanda, Paul Shekonya
    Xia, Kewen
    Sanusi, Olanrewaju Hazzan
    [J]. IEEE ACCESS, 2021, 9 : 162590 - 162613
  • [8] Image recognition of cotton leaf diseases and pests based on transfer learning
    Zhao L.
    Hou F.
    Lyu Z.
    Zhu H.
    Ding X.
    [J]. Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering, 2020, 36 (07): : 184 - 191
  • [9] `A Small Sample Image Recognition Method Based on ResNet and Transfer Learning
    Han, XiaoZhen
    Jin, Ran
    [J]. 2020 5TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND APPLICATIONS (ICCIA 2020), 2020, : 76 - 81
  • [10] An Approach Toward Classifying Plant-Leaf Diseases and Comparisons With the Conventional Classification
    Shrotriya, Anita
    Sharma, Akhilesh Kumar
    Prabhu, Srikanth
    Bairwa, Amit Kumar
    [J]. IEEE ACCESS, 2024, 12 : 117379 - 117398