Laser & Optoelectronics Progress, Volume. 56, Issue 21, 211501(2019)

Classroom Face Detection Algorithm Based on Convolutional Neural Network

Meng Wang, Hansong Su, Gaohua Liu*, and Shen Li
Author Affiliations
  • College of Electrical Automation and Information Engineering, Tianjin University, Tianjin, 300072, China
  • show less
    Figures & Tables(6)
    Structure of residual module
    Overall network structure of classroom face detection algorithm
    Reducing inner distance based on center feature loss function
    Examples of classroom face detection. (a) Different backgrounds; (b) different perspectives; (c) different lighting
    Results on verification set of Wider Face. (a) Easy; (b) medium; (c) hard
    • Table 1. Parameters of feature extraction network

      View table

      Table 1. Parameters of feature extraction network

      BlockConv1Conv2_xConv3_xConv4_xConv5_x
      Parameter7×7,64,stride 23×3 max pool, stride 21×1,643×3,641×1,256×31×1,1283×3,1281×1,512×41×1,2563×3,2561×1,1024×61×1,5123×3,5121×1,2048×3
    Tools

    Get Citation

    Copy Citation Text

    Meng Wang, Hansong Su, Gaohua Liu, Shen Li. Classroom Face Detection Algorithm Based on Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2019, 56(21): 211501

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Machine Vision

    Received: Mar. 28, 2019

    Accepted: Apr. 26, 2019

    Published Online: Nov. 2, 2019

    The Author Email: Gaohua Liu (suppig@126.com)

    DOI:10.3788/LOP56.211501

    Topics