Please wait a minute...
浙江大学学报(工学版)
J4  2013, Vol. 47 Issue (4): 622-629    DOI: 10.3785/j.issn.1008-973X.2013.04.009
自动化技术、电信技术     
基于LBP和CCS-AdaBoost的多视角人脸检测
何智翔, 丁晓青, 方驰, 文迪
清华大学 智能技术与系统国家重点实验室,北京 100084
Multiview face detection based on LBP and CCS-AdaBoost
HE Zhi-xiang, DING Xiao-qing, FANG Chi, WEN Di
State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing 100084, China
 全文: PDF  HTML
摘要：

为了解决多视角人脸检测中多视角导致的人脸结构不同的问题和人脸与非人脸之间的误分类风险不同的问题,检测特征使用局部二值模式（LBP）及统计直方图,人脸非人脸分类器使用可控风险敏感AdaBoost（CCS-AdaBoost）.LBP及统计直方图能够描述多视角的人脸结构|CCS-AdaBoost能够在降低总体的误分类风险的同时最小化分类错误率.实验中,LBP特征的性能在正面人脸检测上比Haar-like特征更好.CCS-AdaBoost分类器在一定条件下也比普通AdaBoost分类器有更好的性能，并且弥补了风险敏感AdaBoost分类器（CS-AdaBoost）对靠近分类边界的样本分类不好的缺陷.最终的多视角人脸检测器在CMU-Profile测试集上获得了满意的结果.该算法实现了鲁棒的多视角人脸检测方法,在相同虚警率下获得比其他人脸检测方法更好的结果,能够有效地解决多视角人脸检测中的2个问题.
Abstract:

Detection features used local binary pattern (LBP) and its histogram in order to solve the problems in multi-view face detection of different face structure caused by multi-views and different misclassification cost between faces and non-faces. The face and non-face classifiers used controlled cost-sensitive AdaBoost (CCS-AdaBoost). LBP and its histogram can describe the multiview face structure|CCS-AdaBoost can minimize the total misclassification cost while minimizing the classification error rate. In the experiments, the LBP feature’s performance in frontal face detection is better than Haar-like features. CCS-AdaBoost also had a better performance than the original AdaBoost algorithm under certain conditions and overcame the cost-sensitive AdaBoost (CS-AdaBoost) algorithm’s drawbacks of classifying the samples near the classification boundary not well. The final multiview face detector had a satisfied detection result in CMU-Profile test set. The proposed method realized a robust multiview faces detection algorithm, and got better results than other face detection methods at the same false alarm rate. The method can effectively solve the foregoing two problems in multiview face detection.
出版日期: 2013-04-01
:  TP 391.4  
基金资助:

国家“863”高技术研究发展计划资助项目（2009AA11Z214）；国家自然科学基金资助项目（60972094,61071135）；教育部博士点基金资助项目（20090002110077）.
通讯作者: 丁晓青,女,教授.     E-mail: dxq@ocrserv.ee.tsinghua.edu.cn
作者简介: 何智翔(1984— ),男, 博士生, 从事目标检测的研究. E-mail：hezhixiang@ocrserv.ee.tsinghua.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

何智翔, 丁晓青, 方驰, 文迪. 基于LBP和CCS-AdaBoost的多视角人脸检测[J]. J4, 2013, 47(4): 622-629.

HE Zhi-xiang, DING Xiao-qing, FANG Chi, WEN Di. Multiview face detection based on LBP and CCS-AdaBoost. J4, 2013, 47(4): 622-629.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2013.04.009    或    http://www.zjujournals.com/eng/CN/Y2013/V47/I4/622

\
[1\] LIAO S C, ZHU X X, LEI Z, et al. Learning multi-scale block local binary patterns for face recognition ［C］∥ Proceedings of International Conference on Biometrics. Seoul: Springer, 2007: 828-837.

\
[2\] ZHANG L, CHU R F, XIANG S M, et al. Face detection based on multi-block LBP representation ［C］∥ Proceedings of International Conference on Biometrics. Seoul: Springer, 2007: 11-18.

\
[3\] HUANG C, AI H Z, LI Y, et al. Vector Boosting for rotation invariant multi-view face detection ［C］∥ Proceedings of 10th IEEE International Conference on Computer Vision. Beijing: IEEE, 2005: 446-453.

\
[4\] VIOLA P, JONES M J. Robust real-time face detection ［J］. International Journal of Computer Vision, 2004, 57(2): 137-154.

\
[5\] VIOLA P, JONES M J. Rapid object detection using a boosted cascade of simple features ［C］∥ Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kauai, Hawaii: IEEE, 2001: 12-14.

\
[6\] VIOLA P, JONES M J. Fast multi-view face detection ［R］. Cambridge: Mitsubishi Electric Research Laboratories, 2003.

\
[7\] MA Y, DING X Q. Robust multi-view face detection and pose estimation based on cost-sensitive AdaBoost ［C］∥ Proceedings of the 6th Asian Conference on Computer Vision. Jeju, Korea: Springer, 2004.

\
[8\] WU B, AI H Z, HUANG C, et al. Fast rotation invariant multi-view face detection based on real Adaboost ［C］∥ Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition. Seoul: IEEE, 2004: 79-84.

\
[9\] SCHNEIDERMAN H, KANADE T. A statistical method for 3D object detection applied to faces and cars ［C］∥ Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Hilton Head Island: IEEE, 2000: 746-751.

\
[10\] FERAUD R, BERNIER O J. A fast and accurate face detector based on neural networks ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(1): 42-53.

\
[11\] FERAUD R, BERNIER O J. Ensemble and modular approaches for face detection: a comparison ［C］∥ Advances in Neural Information Processing Systems. USA: MIT, 1997: 472-478.

\
[12\] CHEN S G, MA X H, ZHANG S K. AdaBoost face detection based on Haar-like intensity features and multi-threshold features ［C］∥ Proceedings of the International Conference on Multimedia and Signal Processing (CMSP). Guilin: ［s. n.］, 2011: 251-255.

\
[13\] LIU C, SHUM H Y. Kullback-Leibler Boosting ［C］∥ Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Wisconsin: IEEE, 2003: 587-594.

\
[14\] 丁晓宇. 改进的AdaBoost算法及其在人脸检测中的应用［D］. 广州: 中山大学, 2007.

DING Xiao-yu. Improved AdaBoost algorithm used in face detection ［D］. Guangzhou: Zhongshan University, 2007.

\
[15\] KARAKOULAS G, TAYLOR J. Optimizing classifiers for imbalanced training sets ［C］∥ Advances in Neural Information Processing Systems. USA: MIT, 1998: 253-259.

\
[16\] TING K. A comparative study of cost-sensitive Boosting algorithms ［C］∥ Proceedings of the International Conference on Machine Learning (ICML-2000). Stanford: IMLS, 2000: 983-990.

\
[17\] LESKOVEC J, TAYLOR J. Linear programming Boosting for uneven datasets ［C］∥ Proceedings of the International Conference on Machine Learning (ICML-2003). Washington. DC: ［s. n.］, 2003: 456-463.

\
[18\] FLEURET F, GEMAN D. Fast face detection with precise pose estimation ［C］∥ Proceedings of the 16th International Conference on Pattern Recognition. Quebec: IEEE, 2002: 235-238.

\
[19\] LI S Z, ZHU L, ZHANG Z Q, et al. Statistical learning of multi-view face detection ［C］∥ Proceedings of the European Conference on Computer Vision. Copenhagen:［s. n.］, 2002: 67-81.
[1] 徐嵩,孙秀霞,何衍. 利用直线段成像特性的摄像机畸变迭代标定方法[J]. J4, 2014, 48(3): 404-413.
[2] 谢天, 解利军, 宋广华, 郑耀. 基于平面颜色分布的增强现实自然特征注册算法[J]. J4, 2013, 47(12): 2243-2252.
[3] 杨帮华, 何美燕, 刘丽, 陆文宇. 脑机接口中基于BISVM的EEG分类[J]. J4, 2013, 47(8): 1431-1436.
[4] 杨冰, 许端清, 杨鑫, 赵磊, 唐大伟. 基于艺术风格相似性规则的绘画图像分类[J]. J4, 2013, 47(8): 1486-1492.
[5] 楼晓俊, 孙雨轩, 刘海涛. 聚类边界过采样不平衡数据分类方法[J]. J4, 2013, 47(6): 944-950.
[6] 孟子博, 姜虹, 陈婧, 袁波, 王立强. 基于特征剪裁的AdaBoost算法及在人脸检测中的应用[J]. J4, 2013, 47(5): 906-911.
[7] 刘晓芳,叶修梓,张三元,张引. 并行磁共振图像的非二次正则化保边性重建[J]. J4, 2012, 46(11): 2035-2043.
[8] 张远辉,韦巍. 在线角速度估计的乒乓球机器人视觉测量方法[J]. J4, 2012, 46(7): 1320-1326.
[9] 施锦河, 沈继忠, 王攀. 四类运动想象脑电信号特征提取与分类算法[J]. J4, 2012, 46(2): 338-344.
[10] 张大尉, 朱善安. 基于核邻域保持判别嵌入的人脸识别[J]. J4, 2011, 45(10): 1842-1847.
[11] 舒振宇, 汪国昭. 基于张量投票的快速网格分割算法[J]. J4, 2011, 45(6): 999-1005.
[12] 徐舒畅, 张三元, 张引. 基于彩色图像的皮肤色素浓度提取算法[J]. J4, 2011, 45(2): 253-258.
[13] 佘青山, 孟明, 罗志增, 马玉良. 基于多核学习的下肢肌电信号动作识别[J]. J4, 2010, 44(7): 1292-1297.
[14] 薛凌云, 段会龙, 向学勤, 范影乐. 基于FitzHughNaguno神经元随机共振机制的图像复原[J]. J4, 2010, 44(6): 1103-1107.
[15] 张远辉, 韦巍, 虞旦. 基于实时图像的乒乓机器人Kalman跟踪算法[J]. J4, 2009, 43(09): 1580-1584.