Table 2 Overall results of the proposed methods for all possible combinations of the stages that are shown in Fig. 4 have been computed
From: A procedure to locate the eyelid position in noisy videokeratoscopic images
Rank | Filtering | Model | Fitting | Mean ± STD |
|---|---|---|---|---|
1 | GDV | Rice | LAD | 3.54 ± 1.44 |
2 | GDV | Rice | Bisquare | 3.68 ± 1.49 |
3 | GDV | Parabola | LAD | 4.32 ± 2.07 |
4 | GDV | Cubic | Bisquare | 4.34 ± 1.51 |
5 | GDV | Cubic | LAD | 4.42 ± 1.72 |
6 | GDV | Parabola | Bisquare | 4.51 ± 2.64 |
7 | GDV | Rational | LAD | 4.64 ± 1.91 |
8 | GDV | Fourier | LAD | 4.69 ± 2.10 |
9 | GDV | Fourth-order | LAD | 4.75 ± 2.11 |
10 | GDV | Fourier | Bisquare | 4.80 ± 1.99 |
11 | GDV | Dagum | LAD | 4.84 ± 1.54 |
13 | GDV | Skew-normal | Bisquare | 4.86 ± 2.42 |
17 | GDV | Weibull | LAD | 5.11 ± 2.09 |
42 | GDV | Log-logistic | LAD | 5.71 ± 2.86 |
71 | Wavelet | Fréchet | Bisquare | 6.10 ± 3.36 |
78 | Wavelet | Parabola | Hough | 6.13 ± 4.42 |
184 | No filtering | Gamma | Bisquare | 7.17 ± 1.41 |