Robust Facial Alignment for Face Recognition

被引:4
作者
Chou, Kuan-Pen [1 ]
Li, Dong-Lin [4 ]
Prasad, Mukesh [2 ]
Pratama, Mahardhika [3 ]
Su, Sheng-Yao [4 ]
Lu, Haiyan [2 ]
Lin, Chin-Teng [2 ]
Lin, Wen-Chieh [1 ]
机构
[1] Natl Chiao Tung Univ, Dept Comp Sci, Hsinchu, Taiwan
[2] Univ Technol Sydney, FEIT, Sch Software, Ctr Artificial Intelligence, Sydney, NSW, Australia
[3] Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore, Singapore
[4] Natl Chiao Tung Univ, Dept Elect Engn, Hsinchu, Taiwan
来源
NEURAL INFORMATION PROCESSING (ICONIP 2017), PT III | 2017年 / 10636卷
关键词
Face recognition; Face alignment; Facial feature localization and sparse representation classifier; POSE; FRAMEWORK;
D O I
10.1007/978-3-319-70090-8_51
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper proposes a robust real-time face recognition system that utilizes regression tree based method to locate the facial feature points. The proposed system finds the face region which is suitable to perform the recognition task by geometrically analyses of the facial expression of the target face image. In real-world facial recognition systems, the face is often cropped based on the face detection techniques. The misalignment is inevitably occurred due to facial pose, noise, occlusion, and so on. However misalignment affects the recognition rate due to sensitive nature of the face classifier. The performance of the proposed approach is evaluated with four benchmark databases. The experiment results show the robustness of the proposed approach with significant improvement in the facial recognition system on the various size and resolution of given face images.
引用
收藏
页码:497 / 504
页数:8
相关论文
共 21 条
[1]  
[Anonymous], 2003, Mitsubishi Electric Research Lab TR-20003-96
[2]   From Pixels to Response Maps: Discriminative Image Filtering for Face Alignment in the Wild [J].
Asthana, Akshay ;
Zafeiriou, Stefanos ;
Tzimiropoulos, Georgios ;
Cheng, Shiyang ;
Pantic, Maja .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2015, 37 (06) :1312-1320
[3]  
Balasubramanian VN, 2007, PROC CVPR IEEE, P2377
[4]   Line-based face recognition under varying pose [J].
de Vel, O ;
Aeberhard, S .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1999, 21 (10) :1081-1088
[5]   Computing 3-D head orientation from a monocular image sequence [J].
Horprasert, T ;
Yacoob, Y ;
Davis, LS .
PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, 1996, :242-247
[6]  
Huang J, 1998, INT C PATT RECOG, P154, DOI 10.1109/ICPR.1998.711102
[7]   One Millisecond Face Alignment with an Ensemble of Regression Trees [J].
Kazemi, Vahid ;
Sullivan, Josephine .
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, :1867-1874
[8]   Support vector machine based multi-view face detection and recognition [J].
Li, YM ;
Gong, SG ;
Sherrah, J ;
Liddell, H .
IMAGE AND VISION COMPUTING, 2004, 22 (05) :413-427
[9]   Dual Sparse Constrained Cascade Regression for Robust Face Alignment [J].
Liu, Qingshan ;
Deng, Jiankang ;
Tao, Dacheng .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 25 (02) :700-712
[10]  
Moon H, 2004, IEEE IMAGE PROC, P75