• Laser & Optoelectronics Progress
  • Vol. 59, Issue 18, 1815007 (2022)
Chunjian Hua1、2、*, Zijun Zhang1、2, Yi Jiang1、2, Jianfeng Yu1、2, and Ying Chen3
Author Affiliations
  • 1School of Mechanical Engineering, Jiangnan University, Wuxi 214122, Jiangsu , China
  • 2Jiangsu Key Laboratory of Advanced Food Manufacturing Equipment & Technology, Wuxi 214122, Jiangsu , China
  • 3School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, Jiangsu , China
  • show less
    DOI: 10.3788/LOP202259.1815007 Cite this Article Set citation alerts
    Chunjian Hua, Zijun Zhang, Yi Jiang, Jianfeng Yu, Ying Chen. Improved Manifold Ranking Algorithm for Green Citrus Recognition[J]. Laser & Optoelectronics Progress, 2022, 59(18): 1815007 Copy Citation Text show less
    Flow chart of the proposed algorithm
    Fig. 1. Flow chart of the proposed algorithm
    Image brightness enhancement result. (a) Original image; (b) image after brightness enhancement
    Fig. 2. Image brightness enhancement result. (a) Original image; (b) image after brightness enhancement
    Superpixel segmentation result. (a) Brightness enhancement image; (b) super pixel segmentation image
    Fig. 3. Superpixel segmentation result. (a) Brightness enhancement image; (b) super pixel segmentation image
    Convex hull results of Harris corner detection
    Fig. 4. Convex hull results of Harris corner detection
    RTV structure extraction and LC feature images. (a) Brightness enhancement; (b) RTV de-texturing; (c) LC feature image; (d) after screening
    Fig. 5. RTV structure extraction and LC feature images. (a) Brightness enhancement; (b) RTV de-texturing; (c) LC feature image; (d) after screening
    Preliminary foreground extraction result. (a) Canny edge detection; (b) feature fusion; (c) preliminary foreground result
    Fig. 6. Preliminary foreground extraction result. (a) Canny edge detection; (b) feature fusion; (c) preliminary foreground result
    Improved background prior method. (a) After brightness enhancement; (b) GMR method; (c) proposed method
    Fig. 7. Improved background prior method. (a) After brightness enhancement; (b) GMR method; (c) proposed method
    Result comparison of different algorithms. (a) After brightness enhancement; (b) ITTi; (c) SR; (d) FT; (e) CA; (f) GMR; (g) proposed algorithm
    Fig. 8. Result comparison of different algorithms. (a) After brightness enhancement; (b) ITTi; (c) SR; (d) FT; (e) CA; (f) GMR; (g) proposed algorithm
    Comparison of segmentation results. (a) GMR; (b) proposed algorithm; (c) artificial segmentation
    Fig. 9. Comparison of segmentation results. (a) GMR; (b) proposed algorithm; (c) artificial segmentation
    Image numberGMR algorithmProposed algorithm
    SA /%FPR /%FNR /%SA /%FPR /%FNR /%
    Average65.1721.843.1494.223.191.64
    167.8319.880.3892.334.361.56
    271.665.868.2797.120.800.37
    354.7527.452.6395.962.051.41
    471.7123.970.1795.873.740.76
    580.0312.490.2296.561.181.35
    674.6521.910.0397.751.520.98
    754.1029.111.3291.366.970.31
    881.948.511.6592.183.131.49
    942.8025.5013.4490.053.363.11
    1050.4528.505.8997.390.681.52
    1169.9314.535.0792.542.782.32
    1293.433.600.7090.512.314.59
    1358.7833.982.3795.124.990.93
    1440.2750.471.8194.406.822.21
    Table 1. Evaluation of segmentation results
    Chunjian Hua, Zijun Zhang, Yi Jiang, Jianfeng Yu, Ying Chen. Improved Manifold Ranking Algorithm for Green Citrus Recognition[J]. Laser & Optoelectronics Progress, 2022, 59(18): 1815007
    Download Citation