Chinese Journal of Liquid Crystals and Displays, Volume. 38, Issue 2, 204(2023)

Fusion of NSCT infrared and visible images based on multi-judgment and WLS optimization

XIAN-tao WANG1,2 and JIN-yu ZHAO1、*
Author Affiliations
  • 1Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,Changchun 130033,China
  • 2University of Chinese Academy of Sciences,Beijing 100049,China
  • show less
    Figures & Tables(13)
    Frame diagram of NSCT decomposition
    NSCT two-channel NSPFB and NSDFB
    Fusion results of different subbands WLS and absolute value of large WLS
    Overall frame diagram of infrared and visible image fusion
    Objective evaluation results of the fusion method in this paper under different parameters α
    Principle of “low frequency of this article” is selected for low frequency,and the experimental results of “Camp” and “House” by different methods are selected for high frequency. The ordinate represents the numerical value,and the abscissa 1,2,3,4,5 represents the used method in order of high-frequency selection PC,SML,variance,threshold energy and the method of high-frequency multi-judgment in this paper.
    Processing results of “Camp” and “House” by different fusion algorithms
    Processing results of “Ship” and “Jeep” by different fusion algorithms
    Objective quality evaluation results of different algorithms for “Camp”,“House”,“Ship” and “Jeep”.
    • Table 1. Source image used for experimental verification 1

      View table
      View in Article

      Table 1. Source image used for experimental verification 1

      可见图像红外图像
      Camp
      House
    • Table 2. Experimental results of “Camp” and “House” using different methods for high-frequency selection and “maximum absolute value” principle and low-frequency selection

      View table
      View in Article

      Table 2. Experimental results of “Camp” and “House” using different methods for high-frequency selection and “maximum absolute value” principle and low-frequency selection

      图像评价指标平均阈值能量平方熵+SML
      CampAG2.878 82.935 32.935 32.942 0
      IE6.336 36.423 46.423 46.433 5
      SF6.423 26.782 36.782 26.802 9
      MI0.460 30.727 80.727 70.732 7
      HouseAG3.686 83.711 23.711 23.711 6
      IE12.887 912.921 612.921 412.922 3
      SF6.466 86.771 36.771 36.771 7
      MI1.023 71.154 81.154 81.154 9
    • Table 3. Objective evaluation results of “Camp” and “House” by different algorithms

      View table
      View in Article

      Table 3. Objective evaluation results of “Camp” and “House” by different algorithms

      图像评价指标DWT_avgDWT_WSMLNSCT_avgNSCT_WSMLNSCT_PC本文算法
      CampAG2.565 62.713 22.878 82.836 12.733 53.076 4
      IE6.27336.59606.423 26.752 16.746 76.809 9
      SF5.94346.38436.336 36.287 96.091 86.641 3
      MI0.48190.77240.460 30.733 00.716 90.718 1
      HouseAG3.479 43.547 23.686 83.691 33.415 93.762 3
      IE6.336 96.728 66.466 86.769 76.742 36.775 8
      SF12.331 212.516 812.887 912.910 912.685 712.953 2
      MI1.034 91.201 81.023 71.171 31.178 11.153 8
    • Table 4. Objective evaluation results of “Ship” and “Jeep” by different algorithms

      View table
      View in Article

      Table 4. Objective evaluation results of “Ship” and “Jeep” by different algorithms

      图像评价指标DWT_avgDWT_WSMLNSCT_avgNSCT_WSMLNSCT_PC本文算法
      ShipAG1.799 31.859 61.902 71.906 91.893 22.009 3
      IE4.989 05.874 45.131 25.908 45.914 55.937 3
      SF5.635 85.774 85.780 85.822 85.796 45.960 3
      MI0.531 90.917 50.536 21.012 61.040 31.006 6
      JeepAG2.725 93.165 23.026 63.071 82.987 23.222 4
      IE6.469 07.225 66.613 07.178 87.190 97.236 8
      SF7.530 38.540 68.163 38.505 88.352 08.692 4
      MI0.580 91.551 80.528 01.425 81.667 81.374 6
    Tools

    Get Citation

    Copy Citation Text

    XIAN-tao WANG, JIN-yu ZHAO. Fusion of NSCT infrared and visible images based on multi-judgment and WLS optimization[J]. Chinese Journal of Liquid Crystals and Displays, 2023, 38(2): 204

    Download Citation

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

    Category: Research Articles

    Received: May. 27, 2022

    Accepted: --

    Published Online: Feb. 20, 2023

    The Author Email: JIN-yu ZHAO (zhaojy@ciomp.ac.cn)

    DOI:10.37188/CJLCD.2022-0179

    Topics