• Laser & Optoelectronics Progress
  • Vol. 59, Issue 4, 0410002 (2022)
Chengmin Liu, Wujian Ye*, and Yijun Liu
Author Affiliations
  • School of Information Engineering, Guangdong University of Technology, Guangzhou , Guangdong 510006, China
  • show less
    DOI: 10.3788/LOP202259.0410002 Cite this Article Set citation alerts
    Chengmin Liu, Wujian Ye, Yijun Liu. Automatic Background Blurring Algorithm Based on Image Perception and Segmentation[J]. Laser & Optoelectronics Progress, 2022, 59(4): 0410002 Copy Citation Text show less
    System framework diagram
    Fig. 1. System framework diagram
    Auxiliary image outputs. (a) Original image; (b) focus image; (c) depth of field image; (d) Mask corresponding to vehicle on left; (e) Mask corresponding to vehicle on right
    Fig. 2. Auxiliary image outputs. (a) Original image; (b) focus image; (c) depth of field image; (d) Mask corresponding to vehicle on left; (e) Mask corresponding to vehicle on right
    Diagram of ResNet-18 network structure
    Fig. 3. Diagram of ResNet-18 network structure
    Filter out Mask that is too small. (a) Original image; (b) (c) Masks before filtering; (d) Mask after filtering
    Fig. 4. Filter out Mask that is too small. (a) Original image; (b) (c) Masks before filtering; (d) Mask after filtering
    Filter out overlapping Masks. (a) Original image; (b)‒(e) Masks before filtering; (f) (g) Masks after filtering
    Fig. 5. Filter out overlapping Masks. (a) Original image; (b)‒(e) Masks before filtering; (f) (g) Masks after filtering
    Background blur images. (a) Background blur image after simple fusion; (b) background blur image after edge optimization
    Fig. 6. Background blur images. (a) Background blur image after simple fusion; (b) background blur image after edge optimization
    Comparison of results of experiment 1. (a1)(a2) Original image; (b1)(b2) Mask R-CNN; (c1)(c2) YOLACT
    Fig. 7. Comparison of results of experiment 1. (a1)(a2) Original image; (b1)(b2) Mask R-CNN; (c1)(c2) YOLACT
    Comparison of results of experiment 2. (a1)(a2) No edge optimization; (b1) (b2) Poisson fusion edge optimization; (c1)(c2) mean filter edge optimization
    Fig. 8. Comparison of results of experiment 2. (a1)(a2) No edge optimization; (b1) (b2) Poisson fusion edge optimization; (c1)(c2) mean filter edge optimization
    Comparison of results of experiment 3. (a1) (a2) Original images; (b1)(b2) small filter cores; (c1)(c2) moderate filter cores; (d1) (d2) large filter cores
    Fig. 9. Comparison of results of experiment 3. (a1) (a2) Original images; (b1)(b2) small filter cores; (c1)(c2) moderate filter cores; (d1) (d2) large filter cores
    Comparison of results of experiment 3. (a) Depth of field image; (b1)(b2) original images; (c1) without sense of hierarchy (auto focus); (c2) without sense of hierarchy (independent selection); (d1) with sense of hierarchy (auto focus); (d2) with sense of hierarchy (independent selection)
    Fig. 10. Comparison of results of experiment 3. (a) Depth of field image; (b1)(b2) original images; (c1) without sense of hierarchy (auto focus); (c2) without sense of hierarchy (independent selection); (d1) with sense of hierarchy (auto focus); (d2) with sense of hierarchy (independent selection)
    Comparison of results of experiment 5. (a) Original image; (b) autofocus mode of our method; (c) independent selection mode of our method; (d) Huawei P20; (e) iPhone XR
    Fig. 11. Comparison of results of experiment 5. (a) Original image; (b) autofocus mode of our method; (c) independent selection mode of our method; (d) Huawei P20; (e) iPhone XR
    Comparison of results of experiment 6. (a) Original image; (b) our method; (c) method proposed by Yang et al.; (d) method proposed by Xiong et al.; (e) method proposed by Purohit et al.; (f) method proposed by Dutta et al.; (g) method proposed by Zheng et al.
    Fig. 12. Comparison of results of experiment 6. (a) Original image; (b) our method; (c) method proposed by Yang et al.; (d) method proposed by Xiong et al.; (e) method proposed by Purohit et al.; (f) method proposed by Dutta et al.; (g) method proposed by Zheng et al.
    AlgorithmNo edge tuningPoisson fusion edge tuningFiltering edge tuning
    PSNR22.7522.4322.80
    Table 1. Comparison of PSNR
    AlgorithmYang et al.Xiong et al.Purohit et al.Dutta et al.Zheng et al.Our paper
    Score6.945.286.786.086.437.27
    Table 2. Comparison of subjective evaluation of blur effects of several algorithms
    Chengmin Liu, Wujian Ye, Yijun Liu. Automatic Background Blurring Algorithm Based on Image Perception and Segmentation[J]. Laser & Optoelectronics Progress, 2022, 59(4): 0410002
    Download Citation