[1]陈远,陈锻生.一种融合LBP纹理特征的多姿态人脸跟踪方法[J].华侨大学学报(自然科学版),2010,31(3):282-287.[doi:10.11830/ISSN.1000-5013.2010.03.0282]
　CHEN Yuan,CHEN Duan-sheng.A Multi-View Face Tracking Method Syncretized LBP Texture Feature[J].Journal of Huaqiao University(Natural Science),2010,31(3):282-287.[doi:10.11830/ISSN.1000-5013.2010.03.0282]
点击复制

一种融合LBP纹理特征的多姿态人脸跟踪方法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第31卷
期数:
2010年第3期
页码:
282-287
栏目:
出版日期:
2010-05-20

文章信息/Info

Title:
A Multi-View Face Tracking Method Syncretized LBP Texture Feature
文章编号:
1000-5013(2010)03-0282-06
作者:
陈远; 陈锻生
华侨大学计算机科学与技术学院
Author(s):
CHEN Yuan;  CHEN Duan-sheng
College of Computer Science and Technology, Huaqiao University, Quanzhou 362021, China
关键词:
多姿态人脸;  连续AdaBoost算法;  特征查找表;  局部二值模式
Keywords:
multi-view face;  real AdaBoost algorithm;  feature search table;  local binary patterns
分类号:
TP391.41
DOI:
10.11830/ISSN.1000-5013.2010.03.0282
文献标志码:
A
摘要:
提出一种改进的Camshift算法,它融合目标人脸的局部二值模式(LBP)纹理特征的T分量,以及肤色的HSV色彩空间的H分量的统计直方图来生成概率分布图像,实现纹理与肤色特征的有效融合; 然后,利用Kalman滤波器来预测目标人脸的运动信息,快速地跟踪到目标人脸.实验表明,在复杂的跟踪条件下,这种算法比原始的仅采用颜色直方图信息的Meanshift和Camshift算法,在跟踪速度和精度上有显著的提高.
Abstract:
We proposed a new improved Camshift algorithm,the hue in an HSV color space of skin color and the texture in the local binary patterns(LBP) texture future of target face is used to produce probability distribution image(PDI),to realize the fusion of the LBP and skin color information.And we also used Kalman filter to predict motion information of target face and find it fast.The experiments show that compare with the original Meanshift and Camshift algorithm using only the color histogram,this algorithm can great improve the tracking speed and precision in complicated tracking conditions.

参考文献/References:

[1] ROWLEY H, BALUJA S, KANADE T. Rotation invariant neural network-based face detection [A]. Washington, DC:IEEE Computer Society, 1998.38-44.
[2] FERAUD R, BERNIER O J, JEAN-EMMANUEL VIALLET. A fast and accurate face detector based on neural networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001(1):42-53.
[3] SCHNEIDERMAN H, KANADE T. A statistical method for 3D object detection applied to faces and cars [A]. [s.n.], 2000.746-751.
[4] LI Yong-min, GONG Shao-gang, LIDDELL H. Support vector regression and classification based multi-view facedetection and recognition [A]. [s.n.], 2000.300-305.
[5] LI S Z, ZHU L, ZHANG Z Q. Statistical learning of multi-view face detection [A]. Lodon:Springer-Verlag, 2002.67-81.
[6] LI S Z, ZHU L, ZHANG Z Q. Learning to detect multi-view faces in real-time [A]. IEEE Computer Society, 2002.172.
[7] SCHAPIRE R E, SINGER Y. Improved boosting algorithms using confidence-rated predictions [J]. Machine Learning, 1999(3):297-336.
[8] 武勃, 黄畅, 艾海舟. 基于连续Adaboost算法的多视角人脸检测 [J]. 计算机研究与发展, 2005(9):1612-1621.

备注/Memo

备注/Memo:
福建省科技计划重点项目(2008I0021)
更新日期/Last Update: 2014-03-23