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...

改进的人脸检测训练方法

DOI: 10.13190/jbupt.200804.73.031, PP. 73-76

Keywords: 人脸检测,自适应提升算法,neighbor-eliminated,boosting算法,双表链接结构,Neyman-Pearson决策规则

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对AdaBoost存在的诸如分类器的级联结构会导致系统拒真率与认假率的失衡,单调性前提的不成立容易直接造成训练过程的失败等缺陷,对人脸检测训练方法进行研究,提出了一种改进算法——neighbor-eliminatedboosting(NEB)算法。此算法通过构建一种新的基于双表链接结构的特征描述子存储结构,引入特征相关信息,简化了训练过程。实验结果表明,以NEB算法为基础实现的人脸检测系统,在训练速度上具有明显的优越性。

References

[1]  Lee B, Boyd E, Daeson E, et al. Secure key issuing in ID-based cryptography[C]// Proceedings of the Second Australian Information Security Workshop-AISW 2004. Dunedin: Australian Computer Society, Inc, 2004:69-74.
[2]  Viola P, Jones M. Rapid object detection using a boosted cascade of simple features[J]. IEEE CVPR, 2001, 1(2): 511-518.
[3]  Schapire R E, Singer Y. Improved boosting algorithms using confidence-rated predictions[J]. Machine Learning, 37(3): 297-336.
[4]  Desmedt Y, Frankel Y. Threshold cryptosystem[C]// Advances in Cryptology-Crypto 89. Berlin: Spring- Verlag, 1989:231-236.
[5]  Friedman J, Hastie T, Tibshirani R. Additive logistic regression: a statistical view of boosting[J]. The Annals of Statistics, 2000, 28(2): 337-374 .
[6]  Schapire R E, Freund Y, Bartlett P, Lee W S. Boosting the margin: a new explanation for the effectiveness of voting methods[J]. The Annals of Statistics, 1998, 26 (5): 1651-1686.
[7]  李闯,丁晓青,吴佑寿. 一种改进的AdaBoost算法?——AD AdaBoost[J]. 计算机学报, 2007, 30 (1): 103-109.
[8]  Li Chuang, Ding Xiaoqing, Wu Youshou. A revised AdaBoost algorithm- AD AdaBoost[J]. Chinese Journal of Computers, 2007, 30 (1): 103-109.
[9]  Li Stan, Zhu Lang, Zhang Zhenqiu,et al. Statistical learning of multi-view face detection[J]. A theory of the learnable. Communications of ACM, 1984, 27 (11): 1134-1142.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133