Table 6 Skin detection scores obtained using different methods for the ECU data set
| Â | Acceptance threshold | Acceptance threshold | ||||||
|---|---|---|---|---|---|---|---|---|
Method | set to maximize F-measure | set to minimize | ||||||
| Â | F-measure | prec | rec |
|
| rec | δ fp |
|
Global Bayesian classifier [16] | 0.7772 | 73.15% | 82.89% | 9.13% | 12.13% | 89.27% | 13.52% | 13.52% |
Global model in ESS [14] | 0.7434 | 68.07% | 81.88% | 11.79% | 14.13% | 87.76% | 16.03% | 16.03% |
Chen’s global model [15] | 0.6896 | 55.30% | 9 1.6 1 % | 23.11% | 15.75% | 91.61% | 23.11% | 23.11% |
Wavelet-based hybrid detector [61] | 0.7894 | 76.34% | 81.73% | 9.01% | 12.28% | 88.74% | 13.31% | 13.78% |
Face-based adaptation in ESS [40] | 0.7672 | 69.67% | 85.35% | - | 13.95% | 89.85% | 17.74% | - |
Spatial analysis using RP [59] | 0.8177 | 75.79% | 88.78% | 8.45% | 9.87% | 92.32% | 12.06% | 1 0.3 2 % |
Spatial analysis using DSPFs [9] | 0.8303 | 78.09% | 88.65% | 9.06% | 7.68% | 93.28% | 8.64% | 12.08% |
Face-based adaptive seeds [11] | 0.8 6 6 1 | 8 2.7 0 % | 90.92% | - | 7.1 7 % | 94.06% | 8.3 9 % | - |
Proposed method (RP-based) | 0.8348 | 81.07% | 86.04% | 8.4 0 % | 9.20% | 90.85% | 9.25% | 10.44% |
Proposed method (DSPF-based) | 0.8411 | 79.10% | 89.79% | 12.67% | 7.22% | 9 4.1 4 % | 8.57% | 16.57% |