Discriminative sparsity graph embedding based on histogram of rotated princial orientation gradients

Ying Tong; Yue-Hong Shen; Yi-Min Wei

doi:10.7498/aps.68.20190224

Journals >Acta Physica Sinica >Volume 68 >Issue 19 >Page 194202-1 > Article

Acta Physica Sinica
Vol. 68, Issue 19, 194202-1 (2019)

Discriminative sparsity graph embedding based on histogram of rotated princial orientation gradients

Ying Tong^1、2、*, Yue-Hong Shen¹, and Yi-Min Wei¹

Author Affiliations

¹College of Communication Engineering, The Army Engineering University of PLA, Nanjing 210007, China

²School of Information and Communication Engineering, Nanjing Institute of Technology, Nanjing 211167, China

show less

DOI: 10.7498/aps.68.20190224 Cite this Article

Ying Tong, Yue-Hong Shen, Yi-Min Wei. Discriminative sparsity graph embedding based on histogram of rotated princial orientation gradients[J]. Acta Physica Sinica, 2019, 68(19): 194202-1 Copy Citation Text

show less

Fig. 1. Flow chart of the proposed algorithm.本文算法的实现流程

Download full size | View in the Article

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

Download full size | View in the Article

Fig. 3. Rotated gradient convolution masks of 3-HRPOG feature descriptor.3-HRPOG算子的旋转梯度卷积模板

Download full size | View in the Article

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

Download full size | View in the Article

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

Download full size | View in the Article

Fig. 6. The sketch of Ms-HRPOG feature descriptor.Ms-HRPOG特征提取示意图

Download full size | View in the Article

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

Download full size | View in the Article

Fig. 8. Samples of one person in the AR database.AR数据库部分样本图像

Download full size | View in the Article

Fig. 9. Samples of one person in the Extended Yale B databaseExtended Yale B数据库部分样本图像

Download full size | View in the Article

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

Download full size | View in the Article

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

Download full size | View in the Article

Fig. 12. Recognition rates based on different initial matrix . 不同初始投影矩阵的识别率

Download full size | View in the Article

Fig. 13. Convergence curve of the objective function.目标函数收敛曲线

Download full size | View in the Article

Method	LPP^[22]	NPE^[23]	SPP^[33]	DSNPE^[37]	DP-NFL^[51]	SRC-DP^[40]	DSGE-pixels	DSGE-HRPOG
Method	LPP^[22]	NPE^[23]	SPP^[33]	DSNPE^[37]	DP-NFL^[51]	SRC-DP^[40]	DSGE-pixels	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
Method	LPP^[22]	NPE^[23]	SPP^[33]	DSNPE^[37]	GRSDA^[39]	RCDA^[52]	DSGE-pixels	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

Ying Tong, Yue-Hong Shen, Yi-Min Wei. Discriminative sparsity graph embedding based on histogram of rotated princial orientation gradients[J]. Acta Physica Sinica, 2019, 68(19): 194202-1

Download Citation

Tools

Save the article for my favorites

Paper Information