JACIII Vol.27 No.3 pp. 474-480
doi: 10.20965/jaciii.2023.p0474

Research Paper:

Real-Time Wheat Unsound Kernel Classification Detection Based on Improved YOLOv5

Zhaohui Zhang*1,*2,†, Zengyang Zuo*2, Zhi Li*3, Yuguo Yin*4, Yan Chen*1, Tianyao Zhang*1, and Xiaoyan Zhao*1,*2 ORCID Icon

*1School of Automation and Electrical Engineering, University of Science and Technology Beijing
30 Xueyuan Road, Haidian District, Beijing 100083, China

*2Shunde Innovation School, University of Science and Technology Beijing
2 Zhihui Road, Daliang, Shunde District, Fo Shan, Guangdong 528399, China

*3College of Information Science and Engineering, Henan University of Technology
100 Lianhua Road, Zhengzhou High-Tech Development Zone, Zhengzhou, Henan 450001, China

*4Shandong Start Measurement and Control Equipment Co., Ltd.
600 Xinyi Road, Weifang Economic Development Zone, Weifang, Shandong 261101, China

Corresponding author

January 21, 2023
February 4, 2023
May 20, 2023
wheat classification, unsound kernels, YOLOv5, attention mechanism
Real-time unsound kernel detection

Real-time unsound kernel detection

China is one of the largest wheat production countries in the world. The wheat quality determines the price and many other aspects. The detection methods of wheat quality mainly depend on manual labor. It costs high amount of manpower and time, and the classification results are partly affected by different individuals. With the development of machine vision, an automatic classification system was presented in this study. A wheat unsound kernel identification method based on the improved YOLOv5 algorithm was designed by adding efficient channel attention (ECA). Compared with convolutional block attention module (CBAM) and squeeze-and-excitation network (SENet), the improved YOLOv5 algorithm was selected to fit the model better. The recognition results showed that YOLOv5 with the addition of the attention mechanism had a significant improvement in average accuracy over that without it. The most significant improvement was observed with the addition of ECA-YOLOv5, with an average accuracy of 96.24%, a 10% improvement over the other two models, and a 13% improvement over the original YOLOv5. This satisfied the application requirements for detection of wheat unsound kernel.

Cite this article as:
Z. Zhang, Z. Zuo, Z. Li, Y. Yin, Y. Chen, T. Zhang, and X. Zhao, “Real-Time Wheat Unsound Kernel Classification Detection Based on Improved YOLOv5,” J. Adv. Comput. Intell. Intell. Inform., Vol.27 No.3, pp. 474-480, 2023.
Data files:
  1. [1] H. Gao, T. Zhen, and Z. Li, “Detection of Wheat Unsound Kernels Based on Improved ResNet,” IEEE Access, Vol.10, pp. 20092-20101, 2022.
  2. [2] L. Jena, S. K. Behera, and P. K. Sethy, “Identification of Wheat Grain Using Geometrical Feature and Machine Learning,” 2021 2nd Int. Conf. for Emerging Technology (INCET), 2021.
  3. [3] S. Guan et al., “Ceramic Ring Defect Detection Based on Improved YOLOv5,” 2022 3rd Int. Conf. on Computer Vision, Image and Deep Learning & Int. Conf. on Computer Engineering and Applications (CVIDL & ICCEA), pp. 115-118, 2022.
  4. [4] F. Han and J. Li, “Wheat Heads Detection via YOLOv5 with Weighted Coordinate Attention,” 2022 7th Int. Conf. on Cloud Computing and Big Data Analytics (ICCCBDA), pp. 300-306, 2022.
  5. [5] C. H. R. Mendigoria et al., “Varietal Classification of Lactuca sativa Seeds Using an Adaptive Neuro-Fuzzy Inference System Based on Morphological Phenes,” J. Adv. Comput. Intell. Intell. Inform., Vol.25, No.5, pp. 618-624, 2021.
  6. [6] F. Cheng, F. N. Chen, and Y. B. Ying, “Image Recognition of Unsound Wheat Using Artificial Neural Network,” 2010 2nd WRI Global Congress on Intelligent Systems, pp. 172-175, 2010.
  7. [7] A. Sharma, T. Singh, and N. Garg, “Combining Near-Infrared Hyperspectral Imaging and ANN for Varietal Classification of Wheat Seeds,” 2022 3rd Int. Conf. on Intelligent Computing Instrumentation and Control Technologies (ICICICT), pp. 1103-1108, 2022.
  8. [8] V. K. Kolur and M. S. Padagatti, “Quality Identification and Grading of Wheat Grains Using Image Processing Techniques,” 2021 5th Int. Conf. on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT), pp. 497-500, 2021.
  9. [9] A. G. Singh, K. Singh, and S. A. Sampson, “Wheat Head Detection and Crop Health Classification System,” 2021 Innovations in Power and Advanced Computing Technologies (i-PACT), 2021.
  10. [10] X. Xia et al., “The Analysis of Wheat Appearance Quality Based on Digital Image Processing,” 2010 the 2nd Conf. on Environmental Science and Information Application Technology, pp. 231-234, 2010.
  11. [11] T. Georgieva, S. Penchev, and P. Daskalov, “Analysis of the Possibilities for Using Computer Vision and Spectral Analysis to Assess the Wheat Crops Condition,” 2022 8th Int. Conf. on Energy Efficiency and Agricultural Engineering (EE&AE), 2022.
  12. [12] X. Zhao et al., “Cross-View Gait Recognition Based on Dual-Stream Network,” J. Adv. Comput. Intell. Intell. Inform., Vol.25, No.5, pp. 671-678, 2021.
  13. [13] M. Genaev, S. Ekaterina, and D. Afonnikov, “Application of Neural Networks to Image Recognition of Wheat Rust Diseases,” 2020 Cognitive Sciences, Genomics and Bioinformatics (CSGB), pp. 40-42, 2020.
  14. [14] J. Redmon et al., “You Only Look Once: Unified, Real-Time Object Detection,” 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 779-788, 2016.
  15. [15] R. Fan and Z. Qiu, “Improved YOLOv5 Algorithm Based on CBAM Attention Mechanism,” 2022 Int. Conf. on Frontiers of Artificial Intelligence and Machine Learning (FAIML), pp. 229-233, 2022.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Jun. 07, 2023