Laser & Optoelectronics Progress, Volume. 58, Issue 4, 0404001(2021)

X-Ray Image Controlled Knife Detection and Recognition Based on Improved SSD

Ruihong Guo*, Li Zhang, Ying Yang, Yang Cao, and Junxi Meng
Author Affiliations
  • College of Electronics and Information, Xi'an Polytechnic University, Shaanxi, Xi'an 710048, China
  • show less
    Figures & Tables(13)
    Sample photos of the dataset
    Residual network structure module
    Feature connection and fusion mode
    Improved network model diagram
    Jumping connection feature fusion pattern diagram
    Experimental results
    • Table 1. Results of each network performance test

      View table

      Table 1. Results of each network performance test

      NetworkSpeed /(frame·s-1)AccuracyMode size /MFLOPS /109
      DenseNet12111474.3321.9
      VGG1618371.753715.3
      MobileNetv223172.0140.52
      ShuffleNet30370.8210.524
      ResNet3440273.1873.6
    • Table 2. Experimental environment configuration

      View table

      Table 2. Experimental environment configuration

      HardwareSoftware
      CPU: Intel i7-9750H CPUOperating system
      GTX 1660Ti-8GUbuntu16.04
      GPU: NVIDIA RTX2080tiFrame: Tensorflow
      RAM: 11G×4Language: Python
    • Table 3. mAP of each algorithm on SDCK dataset unit: %

      View table

      Table 3. mAP of each algorithm on SDCK dataset unit: %

      MethodSSDDSSDMFDSSDOur method
      mAP89.891.390.592.6
    • Table 4. mAP of SSD algorithm on SDCK controlled tool dataset unit: %

      View table

      Table 4. mAP of SSD algorithm on SDCK controlled tool dataset unit: %

      MethodSSDKitchen knifeFruit knifeHacking knifeDaggerScissorSpannerLittle knife
      mAP89.891.088.993.089.287.891.387.5
    • Table 5. mAP of each algorithm on VOC2007+2012 dataset

      View table

      Table 5. mAP of each algorithm on VOC2007+2012 dataset

      MethodTrainTestInput sizemAP /%
      SSD2007+20122007300×30078.8
      DSSD2007+20122007321×32180.3
      MFDSSD2007+20122007300×30080.0
      Our method2007+20122007512×51280.5
    • Table 6. Detection speed of each algorithm on SDCK datasetunit: frame·s-1

      View table

      Table 6. Detection speed of each algorithm on SDCK datasetunit: frame·s-1

      MethodSSDDSSDMFDSSDOur method
      Speed18.39.613.516.7
    • Table 7. Improved algorithm testmAP step by step

      View table

      Table 7. Improved algorithm testmAP step by step

      Base netFunction modulemAP /%
      VGG1689.8
      ResNet3490.8
      VGG1690.5
      ResNet3492.6
    Tools

    Get Citation

    Copy Citation Text

    Ruihong Guo, Li Zhang, Ying Yang, Yang Cao, Junxi Meng. X-Ray Image Controlled Knife Detection and Recognition Based on Improved SSD[J]. Laser & Optoelectronics Progress, 2021, 58(4): 0404001

    Download Citation

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

    Category: Detectors

    Received: Sep. 10, 2020

    Accepted: Nov. 5, 2020

    Published Online: Feb. 22, 2021

    The Author Email: Guo Ruihong (rhguoo@qq.com)

    DOI:10.3788/LOP202158.0404001

    Topics