IDEAS home Printed from https://ideas.repec.org/a/gam/jagris/v13y2022i1p11-d1009738.html
   My bibliography  Save this article

Identification of Maize Seed Varieties Using MobileNetV2 with Improved Attention Mechanism CBAM

Author

Listed:
  • Rui Ma

    (College of Animation and Communication, Qingdao Agricultural University, Qingdao 266109, China)

  • Jia Wang

    (College of Animation and Communication, Qingdao Agricultural University, Qingdao 266109, China)

  • Wei Zhao

    (College of Animation and Communication, Qingdao Agricultural University, Qingdao 266109, China)

  • Hongjie Guo

    (College of Animation and Communication, Qingdao Agricultural University, Qingdao 266109, China)

  • Dongnan Dai

    (College of Animation and Communication, Qingdao Agricultural University, Qingdao 266109, China)

  • Yuliang Yun

    (College of Mechanical and Electrical Engineering, Qingdao Agricultural University, Qingdao 266109, China)

  • Li Li

    (Key Laboratory of Agricultural Information Acquisition Technology, Ministry of Agriculture and Rural Affairs, China Agricultural University, Beijing 100083, China)

  • Fengqi Hao

    (Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, China)

  • Jinqiang Bai

    (Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, China)

  • Dexin Ma

    (College of Animation and Communication, Qingdao Agricultural University, Qingdao 266109, China
    Intelligent Agriculture Institute, Qingdao Agricultural University, Qingdao 266109, China)

Abstract

Seeds are the most fundamental and significant production tool in agriculture. They play a critical role in boosting the output and revenue of agriculture. To achieve rapid identification and protection of maize seeds, 3938 images of 11 different types of maize seeds were collected for the experiment, along with a combination of germ and non-germ surface datasets. The training set, validation set, and test set were randomly divided by a ratio of 7:2:1. The experiment introduced the CBAM (Convolutional Block Attention Module) attention mechanism into MobileNetV2, improving the CBAM by replacing the cascade connection with a parallel connection, thus building an advanced mixed attention module, I_CBAM, and establishing a new model, I_CBAM_MobileNetV2. The proposed I_CBAM_MobileNetV2 achieved an accuracy of 98.21%, which was 4.88% higher than that of MobileNetV2. Compared to Xception, MobileNetV3, DenseNet121, E-AlexNet, and ResNet50, the accuracy was increased by 9.24%, 6.42%, 3.85%, 3.59%, and 2.57%, respectively. Gradient-Weighted Class Activation Mapping (Grad-CAM) network visualization demonstrates that I_CBAM_MobileNetV2 focuses more on distinguishing features in maize seed images, thereby boosting the accuracy of the model. Furthermore, the model is only 25.1 MB, making it suitable for portable deployment on mobile terminals. This study provides effective strategies and experimental methods for identifying maize seed varieties using deep learning technology. This research provides technical assistance for the non-destructive detection and automatic identification of maize seed varieties.

Suggested Citation

  • Rui Ma & Jia Wang & Wei Zhao & Hongjie Guo & Dongnan Dai & Yuliang Yun & Li Li & Fengqi Hao & Jinqiang Bai & Dexin Ma, 2022. "Identification of Maize Seed Varieties Using MobileNetV2 with Improved Attention Mechanism CBAM," Agriculture, MDPI, vol. 13(1), pages 1-16, December.
    • Handle: RePEc:gam:jagris:v:13:y:2022:i:1:p:11-:d:1009738
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2077-0472/13/1/11/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2077-0472/13/1/11/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Khalied Albarrak & Yonis Gulzar & Yasir Hamid & Abid Mehmood & Arjumand Bano Soomro, 2022. "A Deep Learning-Based Model for Date Fruit Classification," Sustainability, MDPI, vol. 14(10), pages 1-16, May.
    2. Christian Janiesch & Patrick Zschech & Kai Heinrich, 2021. "Machine learning and deep learning," Electronic Markets, Springer;IIM University of St. Gallen, vol. 31(3), pages 685-695, September.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Hongling Li & Xiaolong Liu & Hua Zhang & Hui Li & Shangyun Jia & Wei Sun & Guanping Wang & Quan Feng & Sen Yang & Wei Xing, 2024. "Research and Experiment on Miss-Seeding Detection of Potato Planter Based on Improved YOLOv5s," Agriculture, MDPI, vol. 14(11), pages 1-18, October.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Shanxin Zhang & Hao Feng & Shaoyu Han & Zhengkai Shi & Haoran Xu & Yang Liu & Haikuan Feng & Chengquan Zhou & Jibo Yue, 2022. "Monitoring of Soybean Maturity Using UAV Remote Sensing and Deep Learning," Agriculture, MDPI, vol. 13(1), pages 1-21, December.
    2. Jen-Yu Lee & Tien-Thinh Nguyen & Hong-Giang Nguyen & Jen-Yao Lee, 2022. "Towards Predictive Crude Oil Purchase: A Case Study in the USA and Europe," Energies, MDPI, vol. 15(11), pages 1-15, May.
    3. Nasser Al-Habsi, 2025. "Date Palm ( Phoenix dactylifera L.) Fruit: Strategic Crop for Food Security, Nutritional Benefits, Postharvest Quality, and Valorization into Emerging Functional Products," Sustainability, MDPI, vol. 17(16), pages 1-42, August.
    4. Mostafa Bigdeli & Mahsa Akbari, 2024. "Machine-learning-based Classification of Customers’ Behavioural Model in Instagram," Paradigm, , vol. 28(2), pages 223-240, December.
    5. Yang Chen & Xiaoyulong Chen & Jianwu Lin & Renyong Pan & Tengbao Cao & Jitong Cai & Dianzhi Yu & Tomislav Cernava & Xin Zhang, 2022. "DFCANet: A Novel Lightweight Convolutional Neural Network Model for Corn Disease Identification," Agriculture, MDPI, vol. 12(12), pages 1-22, November.
    6. Eduard Hartwich & Alexander Rieger & Johannes Sedlmeir & Dominik Jurek & Gilbert Fridgen, 2023. "Machine economies," Electronic Markets, Springer;IIM University of St. Gallen, vol. 33(1), pages 1-13, December.
    7. Rainer Alt, 2021. "Electronic Markets on robotics," Electronic Markets, Springer;IIM University of St. Gallen, vol. 31(3), pages 465-471, September.
    8. Ayala, Néstor Fabián & Rodrigues da Silva, Jassen & Cannarozzo Tinoco, Maria Auxiliadora & Saccani, Nicola & Frank, Alejandro G., 2025. "Artificial Intelligence capabilities in Digital Servitization: Identifying digital opportunities for different service types," International Journal of Production Economics, Elsevier, vol. 284(C).
    9. Najla Alharbi & Bashayer Alkalifah & Ghaida Alqarawi & Murad A. Rassam, 2024. "Countering Social Media Cybercrime Using Deep Learning: Instagram Fake Accounts Detection," Future Internet, MDPI, vol. 16(10), pages 1-22, October.
    10. Chenyuan Liu & Heng Li & Kexin Li & Yue Wu & Baogang Lv, 2025. "Deep Learning for State of Health Estimation of Lithium-Ion Batteries in Electric Vehicles: A Systematic Review," Energies, MDPI, vol. 18(6), pages 1-20, March.
    11. Abdulwahhab, Ali H. & Abdulaal, Alaa Hussein & Thary Al-Ghrairi, Assad H. & Mohammed, Ali Abdulwahhab & Valizadeh, Morteza, 2024. "Detection of epileptic seizure using EEG signals analysis based on deep learning techniques," Chaos, Solitons & Fractals, Elsevier, vol. 181(C).
    12. Abhirup Khanna & Bhawna Yadav Lamba & Sapna Jain & Vadim Bolshev & Dmitry Budnikov & Vladimir Panchenko & Alexandr Smirnov, 2023. "Biodiesel Production from Jatropha: A Computational Approach by Means of Artificial Intelligence and Genetic Algorithm," Sustainability, MDPI, vol. 15(12), pages 1-33, June.
    13. Roberto Cascante-Yarlequé & Purificación Galindo-Villardón & Fabricio Guevara-Viejó & José Luis Vicente-Villardón & Purificación Vicente-Galindo, 2025. "HJ-BIPLOT : A Theoretical and Empirical Systematic Review of Its 38 Years of History, Using Text Mining and LLMs," Mathematics, MDPI, vol. 13(12), pages 1-35, June.
    14. Leonardo Banh & Gero Strobel, 2023. "Generative artificial intelligence," Electronic Markets, Springer;IIM University of St. Gallen, vol. 33(1), pages 1-17, December.
    15. Dylan Norbert Gono & Herlina Napitupulu & Firdaniza, 2023. "Silver Price Forecasting Using Extreme Gradient Boosting (XGBoost) Method," Mathematics, MDPI, vol. 11(18), pages 1-15, September.
    16. Cheng Yang & Fuhao Sun & Yujie Zou & Zhipeng Lv & Liang Xue & Chao Jiang & Shuangyu Liu & Bochao Zhao & Haoyang Cui, 2024. "A Survey of Photovoltaic Panel Overlay and Fault Detection Methods," Energies, MDPI, vol. 17(4), pages 1-37, February.
    17. Lu Lu & Wei Liu & Wenbo Yang & Manyu Zhao & Tinghao Jiang, 2022. "Lightweight Corn Seed Disease Identification Method Based on Improved ShuffleNetV2," Agriculture, MDPI, vol. 12(11), pages 1-18, November.
    18. Hong, Jichao & Li, Kerui & Liang, Fengwei & Yang, Haixu & Zhang, Chi & Yang, Qianqian & Wang, Jiegang, 2024. "A novel state of health prediction method for battery system in real-world vehicles based on gated recurrent unit neural networks," Energy, Elsevier, vol. 289(C).
    19. Shuai Sang & Lu Li, 2024. "A Novel Variant of LSTM Stock Prediction Method Incorporating Attention Mechanism," Mathematics, MDPI, vol. 12(7), pages 1-20, March.
    20. Yuanhe Du & Tianhang Liu & Wei Shang & Jia Li, 2025. "Research on the Impact of Artificial Intelligence on Urban Green Energy Efficiency: An Empirical Test Based on Neural Network Models," Sustainability, MDPI, vol. 17(16), pages 1-47, August.

    More about this item

    Keywords

    ;
    ;
    ;
    ;

    JEL classification:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jagris:v:13:y:2022:i:1:p:11-:d:1009738. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.