全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

一种融合LBP纹理特征的多姿态人脸跟踪方法

DOI: 10.11830/ISSN.1000-5013.2010.03.0282

Keywords: 多姿态人脸, 连续AdaBoost算法, 特征查找表, 局部二值模式

Full-Text   Cite this paper   Add to My Lib

Abstract:

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.

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.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133