Multi-Pose Face Recognition Based on Facial Landmarks and Incremental Clustering

Xiaoping Wu; Yepeng Guan

doi:10.3788/LOP56.141002

Journals >Laser & Optoelectronics Progress >Volume 56 >Issue 14 >Page 141002 > Article

Laser & Optoelectronics Progress
Vol. 56, Issue 14, 141002 (2019)

Multi-Pose Face Recognition Based on Facial Landmarks and Incremental Clustering

Xiaoping Wu^1、* and Yepeng Guan^1、2

Author Affiliations

¹ School of Communication & Information Engineering, Shanghai University, Shanghai 200444, China;

² Key Laboratory of Advanced Display and System Applications, Ministry of Education, Shanghai University, Shanghai 200072, China

show less

DOI: 10.3788/LOP56.141002 Cite this Article Set citation alerts

Xiaoping Wu, Yepeng Guan. Multi-Pose Face Recognition Based on Facial Landmarks and Incremental Clustering[J]. Laser & Optoelectronics Progress, 2019, 56(14): 141002 Copy Citation Text

show less

Fig. 1. Framework of face landmark location based on LCCDN model

Download full size

Fig. 2. Structural diagram of LSTM global network

Download full size

Fig. 3. Descent curves of CNN loss functions in different face regions

Download full size

Fig. 4. Classification performance of multi-pose face recognition under different Smax. (a) TPR; (b) FPR

Download full size

Fig. 5. Examples of some clips in surveillance video dataset

Download full size

Fig. 6. Qualitative results of facial landmark location based on LCCDN with various poses

Download full size

Fig. 7. Accuracies of different face recognition methods with various poses

Download full size

Network layer	Type	Filter	Output sizes	Others
Input	Input	-	40×40	-
Convolution 1	Convolution	5×5×20	36×36×20	-
Maxpooling 1	Max-pooling	2×2	18×18×20	-
Convolution 2	Convolution	3×3×40	16×16×40	-
Maxpooling 2	Max-pooling	2×2	8×8×40	-
Convolution 3	Convolution	3×3×60	6×6×60	-
Maxpooling 3	Max-pooling	2×2	3×3×60	-
Unshared Conv	Convolution	2×2×80	2×2×80	-
Fully-connectedfc1	Fully-connected	-	120	-
Dropout1	Dropout	-	120	Keep_ratiois 0.6
Predicttion	Fully-connected	-	-	-

Table 1. Structure of shallow CNN

Method	Mean error /10^-2	Failure rate /%
ERT^[3]	7.96	13.06
AAM^[4]	7.58	12.56
CFCNN^[9]	6.31	10.20
TCDCN^[15]	4.60	6.59
LCCDN	4.06	5.26

Table 2. Experimental comparison of different facial landmark location methods

Facial orientationdescriptor	Accuracy /%
Facial orientationdescriptor	CASPEAL-R1^[12]	CFP^[13]	Multi-PIE^[14]
D-LGBPH^[16]	91.75	91.25	92.63
ASIFT^[17]	91.53	90.77	91.03
CFCNN^[9]	93.54	92.28	94.16
TCDCN^[15]	93.89	94.24	94.82
LCCDN	96.75	96.50	97.82

Table 3. Experimental comparison of multi-pose face recognition based on different face orientation descriptors

Clusteringmethod	Accuracy /%
Clusteringmethod	CASPEAL-R1^[12]	CFP^[13]	Multi-PIE^[14]
BART^[11]	93.85	94.13	95.28
FCM^[18]	90.47	91.28.	90.86
K-means^[19]	91.39	92.05	93.90
CBART	96.75	96.50	97.82

Table 4. Experimental comparison of multi-pose face recognition based on different clustering methods

Method	Accuracy /%
Method	CASPEAL-R1^[12]	CFP^[13]	Multi-PIE^[14]
HPN^[2]	90.15	89.17	89.39
VGGFace^[7]	93.20	92.89	92.78
TPCNN^[20]	90.89	90.53	91.39
DFLP^[21]	92.56	91.25	92.16
Proposed	96.75	96.50	97.82

Table 5. Experimental comparison of different face recognition methods

Xiaoping Wu, Yepeng Guan. Multi-Pose Face Recognition Based on Facial Landmarks and Incremental Clustering[J]. Laser & Optoelectronics Progress, 2019, 56(14): 141002

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information