IDEAS home Printed from https://ideas.repec.org/a/gam/jagris/v15y2025i8p848-d1634520.html
   My bibliography  Save this article

The Development of a Lightweight DE-YOLO Model for Detecting Impurities and Broken Rice Grains

Author

Listed:
  • Zhenwei Liang

    (School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China)

  • Xingyue Xu

    (School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China)

  • Deyong Yang

    (School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China)

  • Yanbin Liu

    (School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China)

Abstract

A rice impurity detection algorithm model, DE-YOLO, based on YOLOX-s improvement is proposed to address the issues of small crop target recognition and the similarity of impurities in rice impurity detection. This model achieves correct recognition, classification, and detection of rice target crops with similar colors in complex environments. Firstly, changing the CBS module to the DBS module in the entire network model and replacing the standard convolution with Depthwise Separable Convolution (DSConv) can effectively reduce the number of parameters and the computational complexity, making the model lightweight. The ECANet module is introduced into the backbone feature extraction network, utilizing the weighted selection feature to cluster the network in the region of interest, enhancing attention to rice impurities and broken grains, and compensating for the reduced accuracy caused by model light weighting. The loss problem of class imbalance is optimized using the Focal Loss function. The experimental results demonstrate that the DE-YOLO model has an average accuracy (mAP) of 97.55% for detecting rice impurity crushing targets, which is 2.9% higher than the average accuracy of the original YOLOX algorithm. The recall rate (R) is 94.46%, the F1 value is 0.96, the parameter count is reduced by 48.89%, and the GFLOPS is reduced by 46.33%. This lightweight model can effectively detect rice impurity/broken targets and provide technical support for monitoring the rice impurity/ broken rate.

Suggested Citation

  • Zhenwei Liang & Xingyue Xu & Deyong Yang & Yanbin Liu, 2025. "The Development of a Lightweight DE-YOLO Model for Detecting Impurities and Broken Rice Grains," Agriculture, MDPI, vol. 15(8), pages 1-17, April.
  • Handle: RePEc:gam:jagris:v:15:y:2025:i:8:p:848-:d:1634520
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2077-0472/15/8/848/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2077-0472/15/8/848/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Kexin Que & Zhong Tang & Ting Wang & Zhan Su & Zhao Ding, 2024. "Effects of Unbalanced Incentives on Threshing Drum Stability during Rice Threshing," Agriculture, MDPI, vol. 14(5), pages 1-17, May.
    2. Wei Ji & Yu Pan & Bo Xu & Juncheng Wang, 2022. "A Real-Time Apple Targets Detection Method for Picking Robot Based on ShufflenetV2-YOLOX," Agriculture, MDPI, vol. 12(6), pages 1-18, June.
    3. Fawad Ali & Abdulqader Jighly & Reem Joukhadar & Nabeel Khan Niazi & Fahad Al-Misned, 2023. "Current Status and Future Prospects of Head Rice Yield," Agriculture, MDPI, vol. 13(3), pages 1-21, March.
    4. Yun Liu & Peichen Xin & Jinyan Sun & Decong Zheng, 2024. "Oat Threshing Damage and Its Effect on Nutritional Components," Agriculture, MDPI, vol. 14(6), pages 1-13, May.
    5. Tao Zhang & Yaoming Li & Guoliang You, 2023. "Experimental Study on the Cleaning Performance of Hot Air Flow Cleaning Device," Agriculture, MDPI, vol. 13(9), pages 1-17, September.
    Full references (including those not matched with items on IDEAS)

    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. Shujin Qiu & Ben Pan & Zeze Wang & Shige Fang & Jiangfan Hu & Shubo Yang & Wei Wang & Qingliang Cui & Xiangyang Yuan, 2024. "Research on the Tensile and Impact Mechanical Properties of Millet Ear Petals," Agriculture, MDPI, vol. 14(11), pages 1-16, October.
    2. Zhenwei Liang & Yongqi Qin & Zhan Su, 2024. "Establishment of a Feeding Rate Prediction Model for Combine Harvesters," Agriculture, MDPI, vol. 14(4), pages 1-15, April.
    3. Jinglian Tian & Yongzhong Tian & Wenhao Wan & Chenxi Yuan & Kangning Liu & Yang Wang, 2024. "Research on the Temporal and Spatial Changes and Driving Forces of Rice Fields Based on the NDVI Difference Method," Agriculture, MDPI, vol. 14(7), pages 1-22, July.
    4. Zhenwei Liang & Jia Liu & Deyong Yang & Kangcheng Ouyang, 2024. "Modeling and Simulation of Reel Motion in a Foxtail Millet Combine Harvester," Agriculture, MDPI, vol. 15(1), pages 1-16, December.
    5. Bangzhui Wang & Kexin Que & Zhong Tang & Meiyan Sun & Yi Lian & Haoyang Wang, 2024. "Multivariate Structural Vibration Coupling Response of the Self-Propelled Straw Pickup Baler Under Time-Varying Loads," Agriculture, MDPI, vol. 14(11), pages 1-28, November.
    6. Dongxuan Cao & Wei Luo & Ruiyin Tang & Yuyan Liu & Jiasen Zhao & Xuqing Li & Lihua Yuan, 2025. "Research on Apple Detection and Tracking Count in Complex Scenes Based on the Improved YOLOv7-Tiny-PDE," Agriculture, MDPI, vol. 15(5), pages 1-26, February.
    7. Pengfei Qian & Qi He & Zhong Tang & Tingwei Gu, 2025. "Biomimetic Structural Design for Reducing the Adhesion Between Wet Rice Leaves and Metal Surfaces," Agriculture, MDPI, vol. 15(9), pages 1-24, April.
    8. Kexin Que & Xiaobo Zhuang & Yanyun Shi & Zhexuan Ding & Zhong Tang & Tiantian Jing & Yunlong Cao & Bangzhui Wang & Yao Yu, 2024. "Winding Characteristics and Signal Characterization of Roller During Threshing of Mature Rice," Agriculture, MDPI, vol. 14(12), pages 1-22, December.
    9. Huawei Yang & Yinzeng Liu & Shaowei Wang & Huixing Qu & Ning Li & Jie Wu & Yinfa Yan & Hongjian Zhang & Jinxing Wang & Jianfeng Qiu, 2023. "Improved Apple Fruit Target Recognition Method Based on YOLOv7 Model," Agriculture, MDPI, vol. 13(7), pages 1-21, June.
    10. Guangyu Hou & Haihua Chen & Mingkun Jiang & Runxin Niu, 2023. "An Overview of the Application of Machine Vision in Recognition and Localization of Fruit and Vegetable Harvesting Robots," Agriculture, MDPI, vol. 13(9), pages 1-31, September.

    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:15:y:2025:i:8:p:848-:d:1634520. 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.