• Laser & Optoelectronics Progress
  • Vol. 58, Issue 22, 2210005 (2021)
Jiansi Liu, Liju Yin*, Jinfeng Pan, Yumin Cui, and Xiangyu Tang
Author Affiliations
  • College of Electrical and Electronic Engineering, Shandong University of Technology, Zibo, Shandong 255000, China
  • show less
    DOI: 10.3788/LOP202158.2210005 Cite this Article Set citation alerts
    Jiansi Liu, Liju Yin, Jinfeng Pan, Yumin Cui, Xiangyu Tang. Edge Detection Algorithm for Unevenly Illuminated Images Based on Parameterized Logarithmic Image Processing Model[J]. Laser & Optoelectronics Progress, 2021, 58(22): 2210005 Copy Citation Text show less
    Processing of transmitted images under LIP model
    Fig. 1. Processing of transmitted images under LIP model
    Under the LIP model, two images are added together
    Fig. 2. Under the LIP model, two images are added together
    Processing process of φ function
    Fig. 3. Processing process of φ function
    Processing process of φ-1 function
    Fig. 4. Processing process of φ-1 function
    Four-direction Sobel operator templates. (a) x-axis direction template; (b) y-axis direction template; (c) 45° direction template; (d) 135° direction template
    Fig. 5. Four-direction Sobel operator templates. (a) x-axis direction template; (b) y-axis direction template; (c) 45° direction template; (d) 135° direction template
    3 pixel×3 pixel area
    Fig. 6. 3 pixel×3 pixel area
    Gradient image comparison results. (a) Test image; (b) gradient image of proposed algorithm; (c) gradient image of Ref. [14] algorithm; (d) traditional Sobel algorithm gradient image
    Fig. 7. Gradient image comparison results. (a) Test image; (b) gradient image of proposed algorithm; (c) gradient image of Ref. [14] algorithm; (d) traditional Sobel algorithm gradient image
    Image of real experimental platform
    Fig. 8. Image of real experimental platform
    Internal structure of the experimental platform
    Fig. 9. Internal structure of the experimental platform
    Principle block diagram of experimental platform
    Fig. 10. Principle block diagram of experimental platform
    Image of measured target. (a) Car image; (b) triangle base image; (c) triangle base and number plate combination image
    Fig. 11. Image of measured target. (a) Car image; (b) triangle base image; (c) triangle base and number plate combination image
    Results of algorithm flow. (a) Original image; (b) filtered image; (c) gradient image; (d) final result image
    Fig. 12. Results of algorithm flow. (a) Original image; (b) filtered image; (c) gradient image; (d) final result image
    Comparison of edge detection results. (a) Original image; (b) traditional Canny algorithm; (c) Sobel algorithm; (d) Ref. [14] algorithm; (e) proposed algorithm
    Fig. 13. Comparison of edge detection results. (a) Original image; (b) traditional Canny algorithm; (c) Sobel algorithm; (d) Ref. [14] algorithm; (e) proposed algorithm
    Picture nameAlgorithm
    Traditional CannySobelRef. [14]Proposed algorithm
    Car1.1480.4381.8342.683
    Triangle base0.8760.3341.4232.376
    Base and number plate0.8520.3391.3722.215
    Table 1. Comparison of calculation time unit: s
    AlgorithmLe1-N1-FMe
    Traditional Canny0.8450.6940.8340.781
    Sobel0.7160.7410.7230.728
    Ref. [14] algorithm0.8940.8720.8860.883
    Proposed algorithm0.9320.9050.9120.915
    Table 2. Evaluation of algorithm’s performance
    Jiansi Liu, Liju Yin, Jinfeng Pan, Yumin Cui, Xiangyu Tang. Edge Detection Algorithm for Unevenly Illuminated Images Based on Parameterized Logarithmic Image Processing Model[J]. Laser & Optoelectronics Progress, 2021, 58(22): 2210005
    Download Citation