2008, Volume 10, Issue 7
Strategic Study of CAE >> 2008, Volume 10, Issue 7
A fast face detection algorithm using enhanced AdaBoostbased on walsh features
1. School of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing 210094, China ;
2. School of Information Engineer, Yangzhou University, Yangzhou, Jiangsu 225009, China
Next Previous
Abstract
A fast face detection algorithm using enhanced AdaBoost based on Walsh features is proposed in this paper, and its training process is fast and works well under fewer non-face training samples.Firstly,the utility of Walsh features, instead of Harr-Like features can reduce the redundancy among features largely. Then, an enhanced double threshold AdaBoost algorithm is developed, where double threshold makes training process faster ; and in the process of training cascaded detector, the next classifier can be guided by the former classifier,which enhances the performance of the cascaded detector ;moreover,the adjustment to the threshold of each classifier can separate the training result of face and on-face as far as possible. Finally, the trained detector is tested on MIT + CMU test set, and experimental results show that its training speed, precision and detection time exceeds the corresponding method.
Keywords
Walsh features ; enhanced AdaBoost ; cascaded detector ; face detection
Figures
图1
图2
图3
图4
图5
图6
图7
图8
图9
图10
图11
图12
References
[ 1 ] Brunelli R , Poggio T . Face recognition : Features versus templates [J] . IEEE Trans . on Pattern Analysis and Machine Intelligence , 1993 , 15 (10) : 1042 - 1052 link1
[ 2 ] Yang G Z , Huang T S . Human face detection in a complex background [J] . Pattern Recognition , 1994 , 27 (1) : 53 - 63 link1
[ 3 ] Jeng S H , Liao H Y . An efficient approach for facial feature detection using geometrical face model [ A ] . Proc of 13th International Conference on Pattern Recognition [ C ] . Vienna , Austria : IEEE Computer Society Press , 1996 : 426 - 430 link1
[ 4 ] Jain R . Difference and accumulative difference pictures in dynamic scene analysis [J] . Image and Vision Computing , 1984 , 2(2) : 99 - 108 link1
[ 5 ] Kass M , Witkin A , Terzopoulous D . Snakes : Active contour models [A] . Proc of the 1st International Conference on Computer Vision [C] . London , UK : IEEE Computer Society Press ,1987 :259 - 268 link1
[ 6 ] Yuille A , Hallinan P , Cohen D . Feature extraction from faces using deformable templates [ A ] . Proc of IEEE Computer Society Conference on CVPR ’89 [C] . San Diego , California , USA , IEEE Computer Society Press , 1989 : 104 - 109 link1
[ 7 ] Jones M J ,Rehg J M .Statistical color models with application to skin detection [ R] . Technical report , Cambridge Res Lab , Compaq Computer Corp , 1998
[ 8 ] Martinkauppi B . Face colour under varying illumination-analysis and applications [D] . PhD Thesis , University of Oulu , 2002
[ 9 ] Moghaddam B , Pentlan A . Beyond linear eigenspaces : Bayesian matching for face recognition [A] . Face Recognition : from Theory to Application [M] . Springer-Verlag , 1998 : 230 - 243
[10] Rowley H A . Neural network-based human face detection [D] . PhD Thesis , Carnegie Mellon University , USA , May 1999
[11] Feraud R , Bernier O J , Viallet J E , et al . A fast and accurate face detector based on neural networks [ J] . IEEE Trans . on Pattern Analysis and Machine Intelligence , 2001 , 23(1) : 42 - 53 link1
[12] Osuna E , Freund R ,Girosi F . Training support vector machines : an application to face detection [A] . IEEE Conference on CVPR ’ 97 [C] . San Juan , Puerto Rico , USA , IEEE Computer Society Press , 1997 : 130 - 136 link1
[13] Liu C J .A bayesian discriminating features method for face detection [J] . IEEE Trans . on Pattern Analysis and Machine Intelligence , 2003 , 25(6) : 725 - 740 link1
[14] Violas P , Jones M .Rapid object detection using a boosted cascade of simple features [ A] . IEEE Conference on CVPR ’ 2001 [ C ] . Lihue , Kauai , Hawaii , USA , IEEE Computer Society Press , 2001 : 511 - 518 link1
京公网安备 11010502051620号
