This paper proposes a sample augmentation method to solve the problem of small samples in the inspection of surface defects of filters, the method can generate large-scale samples while ensuring diversity and authenticity, making deep network training feasible. And an improved YOLOv7 defect detection algorithm is proposed by modifying the network structure and adding attention mechanisms, using Wise-IoU to replace the original loss function to increase the accuracy and maintain the speed of detecting surface defects on filters. The results showed that the improved model achieved an average precision of 97.55%, an improvement of 5.76% over the original YOLOv7 algorithm, with a frame rate of 46.5 frames/s.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Surface Defect Detection Algorithm for Air Filters Based on Improved YOLOv7


    Contributors:
    Liu, Yinxiao (author) / Wei, Xiaojuan (author) / Liu, Zhenan (author) / Ma, Yi (author) / Zhang, Maoyuan (author) / Guo, Yunfeng (author) / Bao, Zhikang (author) / Chen, Jixuan (author) / Zhang, Hongbo (author)


    Publication date :

    2023-10-11


    Size :

    3910097 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Improved YOLOv7 Target Detection Algorithm Based on UAV Aerial Photography

    Zhen Bai / Xinbiao Pei / Zheng Qiao et al. | DOAJ | 2024

    Free access

    Bird Detection Algorithm for Transmission Line Based on Improved YOLOv7

    Zheng, Yong Kang / Lin Liu, Jia / Wang, Chao et al. | IEEE | 2023


    Freeway vehicle detection on improved YOLOv7

    Gong, Shaojie / Mao, Kun / Yuan, Haifeng et al. | SPIE | 2023