Fig. 1. Pixel mean of image row and column. (a)(d) Original image; (b)(e) pixel mean in column; (c)(f) pixel mean in row
Fig. 2. Schematic of curvature
Fig. 3. Face false edge extraction. (a) Original image; (b) face edge; (c) edge of a Cartesian coordinate system; (d) false edge of largest connected domain and no symmetry
Fig. 4. Face false edge of small slope. (a) t=0; (b) t=0.1; (c) t=0.2; (d) t=0.3
Fig. 5. False edge with a small curvature and opposite direction of the light source
Fig. 6. Edge markup results need to be enhanced before and after improvement. (a) Original image; (b)-(f) improved edge markup results with m is 0.01、0.03、0.05、0.07、0.1, respectively; (g)-(k) corresponding edge markup results before improvement
Fig. 7. Process illumination compensation of proposed method
Fig. 8. Illumination angle is 0°. (a) Original image; (b) improved MSR; (c) PCNN; (d) adaptive Gamma correction; (e) proposed method
Fig. 9. Illumination angle is 15°. (a) Original image; (b) improved MSR; (c) PCNN; (d) adaptive Gamma correction; (e) proposed method
Fig. 10. Illumination angle is -20°. (a) Original image; (b) improved MSR; (c) PCNN; (d) adaptive Gamma correction; (e) proposed method
Fig. 11. Illumination angle is +65°. (a) Original image; (b) improved MSR; (c) PCNN; (d) adaptive Gamma correction; (e) proposed method
Fig. 12. Illumination angle is +90°. (a) Original image; (b) improved MSR; (c) PCNN; (d) adaptive Gamma correction; (e) proposed method
Fig. 13. Experiment of MCU PIE face database. (a) Original images; (b) improved MSR; (c) PCNN; (d) proposed method
Fig. 14. Face recognition rate of different subsets
Fig. 15. Face misjudgment rate of different subsets
No. | Algorithm | Mean | RMSD | LSD | CSFNRS |
---|
1 | Original | 73.21 | 58.69 | 65.13 | 7.15 | Improved MSR | 191.41 | 36.93 | 184.76 | 4.05 | PCNN | 166.55 | 47.74 | 155.52 | 7.46 | Adaptive Gamma correction | 119.18 | 72.05 | 102.240 | 9.84 | Proposed method | 195.32 | 37.66 | 189.45 | 8.13 | 2 | Original | 44.55 | 59.73 | 39.98 | 3.97 | Improved MSR | 157.79 | 49.49 | 150.01 | 5.44 | PCNN | 133.76 | 62.44 | 125.41 | 5.52 | Adaptive Gamma correction | 122.60 | 70.20 | 119.17 | 9.25 | Proposed method | 177.44 | 60.15 | 158.59 | 12.10 | 3 | Original | 42.91 | 61.48 | 38.75 | 5.90 | Improved MSR | 153.02 | 45.81 | 144.77 | 5.43 | PCNN | 130.61 | 62.17 | 122.16 | 5.62 | Adaptive Gamma correction | 130.40 | 70.72 | 121.07 | 9.2 | Proposed method | 162.15 | 52.70 | 143.02 | 12.81 | 4 | Original | 46.10 | 45.87 | 41.11 | 3.70 | Improved MSR | 164.01 | 49.48 | 155.58 | 5.15 | PCNN | 150.43 | 57.92 | 141.63 | 5.99 | Adaptive Gamma correction | 128.51 | 72.32 | 115.97 | 6.97 | Proposed method | 196.91 | 46.08 | 179.77 | 10.18 | 5 | Original | 19.32 | 35.94 | 23.27 | 5.57 | Improved MSR | 131.93 | 50.40 | 121.79 | 7.48 | PCNN | 102.17 | 50.81 | 91.78 | 8.14 | Adaptive Gamma correction | 132.82 | 70.30 | 119.25 | 9.41 | Proposed method | 144.64 | 50.81 | 130.32 | 9.97 |
|
Table 1. Evaluation values of test image