Deep CNN-Based Planthopper Classification Using a High-Density Image Dataset

被引:3
作者
Ibrahim, Mohd Firdaus [1 ,2 ]
Khairunniza-Bejo, Siti [1 ,3 ,4 ]
Hanafi, Marsyita [5 ]
Jahari, Mahirah [1 ,3 ]
Ahmad Saad, Fathinul Syahir [6 ]
Mhd Bookeri, Mohammad Aufa [7 ]
机构
[1] Univ Putra Malaysia, Fac Engn, Dept Biol & Agr Engn, Serdang 43400, Malaysia
[2] Univ Malaysia Perlis, Fac Mech Engn & Technol, Arau 02600, Malaysia
[3] Univ Putra Malaysia, Smart Farming Technol Res Ctr, Serdang 43400, Malaysia
[4] Univ Putra Malaysia, Inst Plantat Studies, Serdang 43400, Malaysia
[5] Univ Putra Malaysia, Fac Engn, Dept Comp & Commun Syst Engn, Serdang 43400, Malaysia
[6] Univ Malaysia Perlis, Fac Elect Engn & Technol, Arau 02600, Malaysia
[7] Malaysian Agr Res & Dev Inst, Engn Res Ctr, Seberang Perai 13200, Malaysia
来源
AGRICULTURE-BASEL | 2023年 / 13卷 / 06期
关键词
planthoppers; convolutional neural network; machine vision; paddy cultivation; PESTS; IDENTIFICATION; LOCALIZATION; RECOGNITION; SYSTEM;
D O I
10.3390/agriculture13061155
中图分类号
S3 [农学(农艺学)];
学科分类号
0901 ;
摘要
Rice serves as the primary food source for nearly half of the global population, with Asia accounting for approximately 90% of rice production worldwide. However, rice farming faces significant losses due to pest attacks. To prevent pest infestations, it is crucial to apply appropriate pesticides specific to the type of pest in the field. Traditionally, pest identification and counting have been performed manually using sticky light traps, but this process is time-consuming. In this study, a machine vision system was developed using a dataset of 7328 high-density images (1229 pixels per centimetre) of planthoppers collected in the field using sticky light traps. The dataset included four planthopper classes: brown planthopper (BPH), green leafhopper (GLH), white-backed planthopper (WBPH), and zigzag leafhopper (ZIGZAG). Five deep CNN models-ResNet-50, ResNet-101, ResNet-152, VGG-16, and VGG-19-were applied and tuned to classify the planthopper species. The experimental results indicated that the ResNet-50 model performed the best overall, achieving average values of 97.28% for accuracy, 92.05% for precision, 94.47% for recall, and 93.07% for the F1-score. In conclusion, this study successfully classified planthopper classes with excellent performance by utilising deep CNN architectures on a high-density image dataset. This capability has the potential to serve as a tool for classifying and counting planthopper samples collected using light traps.
引用
收藏
页数:17
相关论文
共 36 条
[1]   Deep CNN-based damage classification of milled rice grains using a high-magnification image dataset [J].
Bhupendra ;
Moses, Kriz ;
Miglani, Ankur ;
Kankar, Pavan Kumar .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2022, 195
[2]  
Bookeri M.A.M., 2021, Adv. Agric. Food Res. J, V3, pa0000187, DOI [10.36877/aafrj.a0000187, DOI 10.36877/AAFRJ.A0000187]
[3]  
Bray F., 2014, AAG REV BOOKS, V2, P127, DOI [10.1080/2325548X.2014.954196, DOI 10.1080/2325548X.2014.954196]
[4]   SMOTE: Synthetic minority over-sampling technique [J].
Chawla, Nitesh V. ;
Bowyer, Kevin W. ;
Hall, Lawrence O. ;
Kegelmeyer, W. Philip .
2002, American Association for Artificial Intelligence (16)
[5]   Automatic moth detection from trap images for pest management [J].
Ding, Weiguang ;
Taylor, Graham .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2016, 123 :17-28
[6]  
Ghaffar M. B. A., 2016, Journal of Tropical Agriculture and Food Science, V44, P49
[7]   Intelligent detection of citrus fruit pests using machine vision system and convolutional neural network through transfer learning technique [J].
Hadipour-Rokni, Ramazan ;
Asli-Ardeh, Ezzatollah Askari ;
Jahanbakhshi, Ahmad ;
Paeen-Afrakoti, Iman Esmaili ;
Sabzi, Sajad .
COMPUTERS IN BIOLOGY AND MEDICINE, 2023, 155
[8]   EvoDCNN: An evolutionary deep convolutional neural network for image classification [J].
Hassanzadeh, Tahereh ;
Essam, Daryl ;
Sarker, Ruhul .
NEUROCOMPUTING, 2022, 488 :271-283
[9]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[10]   Application of transfer learning and image augmentation technology for tomato pest identification [J].
Huang, Mei-Ling ;
Chuang, Tzu-Chin ;
Liao, Yu-Chieh .
SUSTAINABLE COMPUTING-INFORMATICS & SYSTEMS, 2022, 33