Laser & Optoelectronics Progress, Volume. 58, Issue 24, 2410002(2021)

Image Aesthetics Retargeting Algorith Based on Multi-Level Attention Fusion

Ming Yu, Jijun Zhang, Yingchun Guo*, Meng Zhang, and Dan Wang
Author Affiliations
  • School of Artificial Intelligence, Hebei University of Technology, Tianjin 300401, China
  • show less
    Figures & Tables(9)
    Flowchart of image aesthetic retargeting based on attention fusion
    Fusion of importance maps. (a) Original images; (b) aesthetic feature maps; (c) Esal; (d) fusions of Egrad ; (e) importance maps
    Image retargeting process based on the energy transfer
    Seven retargeting results for different type of images. (a) With a single large subject; (b) with a complex background; (c) with multiple subjects; (d) with complex subject objects
    Results of ablation experiments. (a) Original images; (b) important map + gradient and straight-line map; (c) aesthetic feature map + important map + gradient and straight-line map
    • Table 1. Comparison of between proposed method and mainstream methods

      View table

      Table 1. Comparison of between proposed method and mainstream methods

      MethodSRCCPLCCAccuracy /%
      Ref. [19]--66.70
      Ref. [20]--71.42
      Ref. [31]--74.46
      Ref. [32]--75.76
      Ref. [33]--77.40
      Ref. [34]0.558-77.33
      Ref. [35]--81.70
      Ref. [30]0.6120.63681.51
      Ref. [22]0.7520.75581.61
      Ref. [22]0.7560.75781.72
      Proposed algorithm0.7550.75782.28
    • Table 2. Objective evaluation results of 4 images

      View table

      Table 2. Objective evaluation results of 4 images

      Retargeting algorithmFig. 4(a)Fig. 4(b)Fig. 4(c)Fig. 4(d)
      US0.590.600.680.60
      SC0.630.650.620.61
      SNS0.600.610.680.63
      BSC0.660.650.700.68
      InGAN0.400.610.490.62
      Cycle-IR0.600.680.660.70
      Proposed algorithm0.680.730.700.72
    • Table 3. Subjective evaluation statistics

      View table

      Table 3. Subjective evaluation statistics

      Retargeting algorithmSelect numberSelect rate /%
      US1162.90
      SC2125.30
      SNS40710.18
      BSC48912.22
      InGAN1323.30
      Cycle-IR55913.98
      W/o aesthetic feature map77319.33
      Proposed algorithm131232.80
    • Table 4. Objective evaluation statistics

      View table

      Table 4. Objective evaluation statistics

      Retargeting algorithmAverage score
      US0.60
      SC0.63
      SNS0.63
      BSC0.68
      InGAN0.59
      Cycle-IR0.68
      W/o aesthetic feature map0.68
      Proposed algorithm0.71
    Tools

    Get Citation

    Copy Citation Text

    Ming Yu, Jijun Zhang, Yingchun Guo, Meng Zhang, Dan Wang. Image Aesthetics Retargeting Algorith Based on Multi-Level Attention Fusion[J]. Laser & Optoelectronics Progress, 2021, 58(24): 2410002

    Download Citation

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

    Category: Image Processing

    Received: Dec. 17, 2020

    Accepted: Feb. 12, 2021

    Published Online: Nov. 24, 2021

    The Author Email: Yingchun Guo (gyc@scse.hebut.edu.cn)

    DOI:10.3788/LOP202158.2410002

    Topics