• Laser & Optoelectronics Progress
  • Vol. 55, Issue 11, 111006 (2018)
Fangjie Chen*, Jun Han, Zuwu Wang, Guoqiang Zhang, and Jianlian Cheng
Author Affiliations
  • School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China
  • show less
    DOI: 10.3788/LOP55.111006 Cite this Article Set citation alerts
    Fangjie Chen, Jun Han, Zuwu Wang, Guoqiang Zhang, Jianlian Cheng. Image Registration Algorithm Based on Improved GMS and Weighted Projection Transformation[J]. Laser & Optoelectronics Progress, 2018, 55(11): 111006 Copy Citation Text show less
    Distribution characteristics of correct matching and error matching
    Fig. 1. Distribution characteristics of correct matching and error matching
    Correct matching and error matching feature for neighborhood score distributions
    Fig. 2. Correct matching and error matching feature for neighborhood score distributions
    Nine lattice grids (purple) and five lattice grids (yellow) in a neighborhood sequence
    Fig. 3. Nine lattice grids (purple) and five lattice grids (yellow) in a neighborhood sequence
    Schematics of five lattice grid rotation. (a) Five lattice grids of the grid neighborhood; (b) rotate clockwise once; (c) rotate clockwise twice; (d) rotate clockwise thrice
    Fig. 4. Schematics of five lattice grid rotation. (a) Five lattice grids of the grid neighborhood; (b) rotate clockwise once; (c) rotate clockwise twice; (d) rotate clockwise thrice
    Four groups of test images. (a) APAP trail images; (b) DHW temple images; (c) SPHP garden images; (d) proposed algorithm fan-sculpture images
    Fig. 5. Four groups of test images. (a) APAP trail images; (b) DHW temple images; (c) SPHP garden images; (d) proposed algorithm fan-sculpture images
    Four groups of image stitching for comparison. (a) APAP trail image stitching; (b) DHW temple image stitching; (c) SPHP garden image stitching; (d) proposed stitching algorithm
    Fig. 6. Four groups of image stitching for comparison. (a) APAP trail image stitching; (b) DHW temple image stitching; (c) SPHP garden image stitching; (d) proposed stitching algorithm
    ImagesAlgorithmRough match pairsRefined match pairsTime /s
    Fig. 6(a)GMS1000026850.065
    Proposed1000027050.039
    Fig. 6(b)GMS988933380.058
    Proposed988934200.034
    Fig. 6(c)GMS100008500.071
    Proposed100008970.042
    Fig. 6(d)GMS1000023.580.045
    Proposed1000027760.029
    Table 1. Refined match pairs and running time
    AlgorithmImages
    Fig. 6(a)Fig. 6(b)Fig. 6(c)Fig. 6(d)
    SIFT+RANSAC97.3298.7497.6596.51
    SURF+RANSAC95.6296.6896.1395.71
    BRISK+RANSAC93.5495.1394.8193.90
    ORB+RANSAC94.7895.4793.1894.87
    AKAZE+RANSAC95.1397.6995.8995.23
    Proposed97.5798.6198.1496.56
    Table 2. Matching correct rate
    AlgorithmImages
    Fig. 6(a)Fig. 6(b)Fig. 6(c)Fig. 6(d)
    SIFT+RANSAC0.51890.39530.45710.4134
    SURF+RANSAC0.58540.44120.49250.4335
    BRISK+RANSAC0.70250.56330.62320.6069
    ORB+RANSAC0.66870.49510.58340.5488
    AKAZE+RANSAC0.60650.42380.52180.5047
    Proposed0.45270.35570.40790.3713
    Table 3. Root mean square errorpixel
    Fangjie Chen, Jun Han, Zuwu Wang, Guoqiang Zhang, Jianlian Cheng. Image Registration Algorithm Based on Improved GMS and Weighted Projection Transformation[J]. Laser & Optoelectronics Progress, 2018, 55(11): 111006
    Download Citation