Laser & Optoelectronics Progress, Volume. 56, Issue 14, 141002(2019)
Multi-Pose Face Recognition Based on Facial Landmarks and Incremental Clustering
Figures & Tables(12)
Fig. 4. Classification performance of multi-pose face recognition under different Smax. (a) TPR; (b) FPR
Fig. 6. Qualitative results of facial landmark location based on LCCDN with various poses
Table 1. Structure of shallow CNN
View tableTable 1. Structure of shallow CNN
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-connected fc1 Fully- connected - 120 - Dropout1 Dropout - 120 Keep_ ratio is 0.6 Predicttion Fully-connected - - -
Table 2. Experimental comparison of different facial landmark location methods
View tableTable 2. Experimental comparison of different facial landmark location methods
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 3. Experimental comparison of multi-pose face recognition based on different face orientation descriptors
View tableTable 3. Experimental comparison of multi-pose face recognition based on different face orientation descriptors
Facial orientation descriptor Accuracy /% 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 4. Experimental comparison of multi-pose face recognition based on different clustering methods
View tableTable 4. Experimental comparison of multi-pose face recognition based on different clustering methods
Clustering method Accuracy /% 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 5. Experimental comparison of different face recognition methods
View tableTable 5. Experimental comparison of different face recognition methods
Method Accuracy /% 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
Tools
Get Citation
Copy Citation Text
Xiaoping Wu, Yepeng Guan. Multi-Pose Face Recognition Based on Facial Landmarks and Incremental Clustering[J]. Laser & Optoelectronics Progress, 2019, 56(14): 141002
Paper Information
Category: Image Processing
Received: Dec. 29, 2018
Accepted: Feb. 17, 2019
Published Online: Jul. 12, 2019
The Author Email: Wu Xiaoping (ypguan@shu.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20