Author Affiliations
1College of Communication Engineering, The Army Engineering University of PLA, Nanjing 210007, China2School of Information and Communication Engineering, Nanjing Institute of Technology, Nanjing 211167, Chinashow less
Fig. 1. Flow chart of the proposed algorithm.本文算法的实现流程
Fig. 2. Gradient convolution masks of 3-HRPOG feature descriptor: (a)
mask; (b)
mask.
3-HRPOG算子的梯度卷积模板示意图 (a)
模板; (b)
模板
Fig. 3. Rotated gradient convolution masks of 3-HRPOG feature descriptor.3-HRPOG算子的旋转梯度卷积模板
Fig. 4. Rotation invariance analysis: (a) Original binary image and gradient vectors of HOG and 3-HRPOG; (b) rotated
binary image and gradient vectors of HOG and 3-HRPOG.
旋转不变性分析 (a) 原图及HOG和3-HRPOG的梯度矢量值; (b) 旋转
图像及HOG和3-HRPOG的梯度矢量值
Fig. 5. Rotated dominant direction gradient masks of 5-HRPOG feature descriptor.5-HRPOG算子的旋转主方向梯度模板
Fig. 6. The sketch of Ms-HRPOG feature descriptor.Ms-HRPOG特征提取示意图
Fig. 7. Sparsity reconstruction weights of one sample with SPP algorithm on the LFW database.LFW数据库中某一图像的SPP稀疏重构权值
Fig. 8. Samples of one person in the AR database.AR数据库部分样本图像
Fig. 9. Samples of one person in the Extended Yale B databaseExtended Yale B数据库部分样本图像
Fig. 10. Occlusion samples of one person in the Extended Yale B database.Extended Yale B数据库部分遮挡样本图像
Fig. 11. Samples of one person: (a) LFW database; (b) PubFig database.部分样本图像 (a) LFW数据库部分样本; (b) PubFig数据库部分样本
Fig. 12. Recognition rates based on different initial matrix
.
不同初始投影矩阵
的识别率
Fig. 13. Convergence curve of the objective function.目标函数收敛曲线
Method | LPP[22] | NPE[23] | SPP[33] | DSNPE[37] | DP-NFL[51] | SRC-DP[40] | DSGE-pixels | DSGE-HRPOG | 3-HRPOG | 5-HRPOG | Ms-HRPOG | Recognition Rate/% | 67.14 | 68.69 | 68.21 | 76.07 | 71.8 | 75.2 | 76.79 | 88.45 | 88.21 | 88.81 | Dimension | 115 | 311 | 220 | 140 | 63 | 63 | 322 | 777 | 754 | 774 |
|
Table 1. Experimental results on the AR database with the interference factors of expression, illumination and time.
AR数据库在表情、光照和时间干扰因素下的实验结果
| Experiment 1/% | Experiment 2/% | Experiment 3/% | LPP[22] | 71.39 | 68.68 | 69.46 | NPE[23] | 72.64 | 71.81 | 71.08 | SPP[33] | 75.90 | 72.92 | 74.07 | DSNPE[37] | 80.28 | 78.26 | 78.14 | SRC-DP[40] | 78.35 | 76.50 | 77.80 | SRC-FDC[42] | 80.90 | 79.90 | 80.30 | DSGE-pixels | 79.03 | 78.75 | 82.65 | DSGE-HRPOG
(3-HRPOG)
| 88.54 | 89.51 | 90.53 | DSGE-HRPOG
(5-HRPOG)
| 89.31 | 89.58 | 90.98 | DSGE-HRPOG
(Ms-HRPOG)
| 89.31 | 90.00 | 91.06 |
|
Table 2. Experimental results of AR database with the occlusion interference.
AR数据库在遮挡干扰因素下的实验结果
| Mean/% | Std/% | Dimension | LPP[22] | 95.90 | 0.38 | 141 | NPE[23] | 95.87 | 0.55 | 311 | SPP[33] | 90.39 | 0.90 | 151 | DSNPE[37] | 98.02 | 0.33 | 200 | Wang[54] | 97.85 | 0.93 | — | Gao[53] | 98.59 | 0.53 | — | DSGE-pixels | 98.45 | 0.27 | 202 | DSGE-HRPOG
(3-HRPOG)
| 99.45 | 0.17 | 1350 | DSGE-HRPOG
(5-HRPOG)
| 99.37 | 0.12 | 1297 | DSGE-HRPOG
(Ms-HRPOG)
| 99.55 | 0.13 | 1385 |
|
Table 3. Experimental results on the AR database with the mix interference factors.
AR数据库在混合干扰因素下的实验结果
Method | LPP[22] | NPE[23] | SPP[33] | DSNPE[37] | GRSDA[39] | RCDA[52] | DSGE-pixels | DSGE-HRPOG | 3-HRPOG | 5-HRPOG | Ms-HRPOG | Recognition Rate/% | 87.86 | 89.31 | 85.79 | 85.74 | 82.7 | 92 | 86.03 | 91.35 | 89.77 | 92.48 | Dimension | 65 | 160 | 95 | 85 | 266 | — | 83 | 355 | 345 | 351 |
|
Table 4. Experimental results of Extended Yale B database with the illumination interference.
Extended Yale B数据库在光照干扰因素下的实验结果
| Experiment 1/% | Experiment 2/% | LPP[22] | 95.51 ± 0.40 | 96.78 ± 0.72 | NPE[23] | 96.43 ± 0.23 | 97.85 ± 0.31 | SPP[33] | 92.57 ± 0.84 | 93.05 ± 0.77 | DSNPE[37] | 94.18 ± 0.48 | 95.29 ± 0.54 | Gao[53] | 86.91 ± 1.07 | 88.23 ± 0.91 | DSGE-pixels | 95.83 ± 0.66 | 96.21 ± 0.21 | DSGE-HRPOG(3-HRPOG) | 97.30 ± 0.20 | 97.73 ± 0.35 | DSGE-HRPOG (5-HRPOG) | 96.85 ± 0.38 | 96.93 ± 0.60 | DSGE-HRPOG G(Ms-HRPOG) | 97.98 ± 0.50 | 98.10 ± 0.31 |
|
Table 5. Experimental results of Extended Yale B database with the occlusion interference.
Extended Yale B数据库在遮挡干扰因素下的实验结果
| LFW/% | PubFig/% | LPP[22] | 35.32 | 24.00 | NPE[23] | 35.19 | 25.00 | SPP[33] | 31.52 | 29.00 | DSNPE[37] | 44.05 | 30.90 | WGSC[58] | 47.60 | 37.50 | RSRC[3] | 42.80 | 47.00 | RRC[57] | 53.20 | 42.20 | IRGSC[41] | 56.30 | 48.50 | DSGE-pixels | 51.52 | 38.60 | DSGE-HOG | 69.62 | 49.00 | DSGE-HRPOG(3-HRPOG) | 76.71 | 54.20 | DSGE-HRPOG (5-HRPOG) | 76.58 | 53.30 | DSGE-HRPOG (Ms-HRPOG) | 73.80 | 53.70 |
|
Table 6. Experimental results on the LFW database and PubFig database.
LFW和PubFig数据库的实验结果
| DSGE-HRPOG | 3-HRPOG | 5-HRPOG | Ms-HRPOG | with joint optimization | 54.20 (630) | 53.30 (473) | 53.70 (514) | without joint optimization | 53.50 (514) | 50.90 (423) | 53.20 (514) |
|
Table 7. Experimental results with joint optimization and without joint optimization on the PubFig database.
PubFig数据库上有联合优化和无联合优化的实验结果