[1]陈春燕,章品正,罗立民.基于粒特征和连续Adaboost的人脸检测[J].智能系统学报,2009,4(5):446-452.[doi:10.3969/j.issn.1673-4785.2009.05.010]
CHEN Chun-yan,ZHANG Pin-zheng,LUO Li-min.Face detection using real Adaboost on granular features[J].CAAI Transactions on Intelligent Systems,2009,4(5):446-452.[doi:10.3969/j.issn.1673-4785.2009.05.010]
点击复制
CHEN Chun-yan,ZHANG Pin-zheng,LUO Li-min.Face detection using real Adaboost on granular features[J].CAAI Transactions on Intelligent Systems,2009,4(5):446-452.[doi:10.3969/j.issn.1673-4785.2009.05.010]
基于粒特征和连续Adaboost的人脸检测
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
4
期数:
2009年第5期
页码:
446-452
栏目:
学术论文—机器感知与模式识别
出版日期:
2009-10-25
- Title:
- Face detection using real Adaboost on granular features
- 文章编号:
- 1673-4785(2009)05-0446-07
- 关键词:
- 粒特征; 贝叶斯决策; 连续Adaboost; Boosting级联; 人脸检测
- 分类号:
- TP391.41
- 文献标志码:
- A
- 摘要:
- 提出了一种基于粒特征和连续Adaboost算法的人脸检测方法.它使用粒特征并扩展贝叶斯决策弱分类器，设计具有连续置信度输出的查找表型弱分类器形式，构造出弱分类空间，使用大规模的训练集和验证集，采用连续Adaboost算法学习得到Boosting动态级联型的人脸检测器.在CMUMIT正面人脸测试集上，误报20个时，检测率为90%以上.在一台Pentium Dual 1.2 GHz的PC上，处理一幅大小为320×240像素大小的图片平均需100 ms.实验结果表明该方法取得了比较好的精度和速度.
- Abstract:
- A face detection method based on sparse granular features and the real adaptive boosting (Adaboost) meta-algorithm was proposed. A sparse granular feature set was introduced into the Adaboost learning framework. A weak look-up-table (LUT) type classifier with real confidence output was designed by extending the Bayesian stump. Then, the space of the weak classifier was constructed. The Adaboost cascade face detector was taught by using a large training set and an evaluation set. Experiments were performed on the CMU-MIT dataset, a standard public data set for benchmarking frontal face detection systems. The detection rate reached over 90% when false alarms were 20. The average processing time on a Pentium Dual1.2GHz PC was about 100 ms for a 320×240pixel image. This shows the proposed method provides good precision and speed.
- 参考文献/References:
-
［1］ROWLEY H, BALUJA S, KANADE T. Rotation invariant neural network-based face detection［C］//Proc of IEEE Conf on Computer Vision and Pattern Recognition. Santa Barbara, USA, 1998: 38-44.
［2］SCHNEIDERMAN H. Learning a restricted Bayesian network for object detection［C］//Proc of IEEE Conf on Computer Vision and Pattern Recognition. Washington DC, USA, 2004: 639-646.
［3］OSUNA E, FREUND R， GIROSI F. Training support vector machines: an application to face detection［C］//Proc of IEEE Conf on Computer Vision and Pattern Recognition. San Juan, Puerto Rico, 1997: 130-136.
［4］HEISELE B, SERRE T, PRENTICE S, et al. Hierarchical classification and feature reduction for fast face detection with support vector machines［J］. Pattern Recognition, 2003, 36(9): 2007-2017.
［5］VIOLA P, JONES M. Rapid object detection using a boosted cascade of simple features［C］//Proc of IEEE Conf on Computer Vision and Pattern Recognition. Kauai Marriott， USA, 2001: 511-518.
［6］LEVI K, WEISS Y. Learning object detection from a small number of examples: the importance of good features［C］//Proc of IEEE Conf on Computer Vision and Pattern Recognition. Washington DC, USA, 2004: 53-60.
［7］LIENHART R, MAYDT J. An extended set of Haarlike features for rapid object detection［C］//Proc of IEEE Conf on Image Processing. New York, USA, 2002: 900-903.
［8］HUANG Chang, AI Haizhou, LI Yuan, et al. High-performance rotation invariant multiview face detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(4): 671-686.
［9］ABRAMSON Y, STEUX B. YEF real-time object detection［C］//Proc of International Workshop Automatic Learning and Real-Time. Siegen, Germany, 2005: 5-13.
［10］XIAO Rong, ZHU Long, ZHANG Hongjiang. Boosting chain learning for object detection［C］//Proc of IEEE Conf on Computer Vision. Nice， France, 2003: 709-715.
［11］LI S Z, ZHANG Z Q. FloatBoost learning and statistical face detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1112-1123.
［12］BOURDEV L, BRANDT J. Robust object detection via soft cascade［C］//Proc of IEEE Conf on Computer Vision and Pattern Recognition. San Diego, USA, 2005: 236-243.
［13］HUANG Chang, AI Haizhou, WU Bo, et al. Boosting nested cascade detector for multi-view face detection［C］//Proceedings of International Conference on Pattern Recognition. Cambridge, UK, 2004: 415-418.
［14］武?? 勃,黄?? 畅,艾海舟,等. 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, 42(9): 1612-1621.
WU Bo, HUANG Chang, AI Haizhou, et al. A multiview face detection based on real Adaboost algorithm［J］. Journal of Computer Research and Development, 2005, 42(9): 1612-1621.
［15］XIAO Rong, ZHU Huaiyi, SUN He, et al. Dynamic cascade for face detection［C］//IEEE Intenational Conference on Computer Vision. Rio de Janeiro, Brazil, 2007: 1-8.
［16］HUANG Chang, AI Haizhou, LI Yuan, et al. Learning sparse features in granular space for multi-view face detection［C］//Proc of 7th International Conf on Automatic Face and Gesture Recognition. Southampton, UK, 2006: 401-406.
［17］NILLSON N J. Artifical Intelligence: a new Synthesis［M］. San Francisco, USA: Morgan Kaufmann, 1998: 140-161.
［18］SUNG K, POGGIO T. Example-based learning for viewbased face detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(1): 39-51.
［19］ROWLEY H, BALUJA S, KANADE T. Neural networkbased face detection［C］//Proc of IEEE Conf on Computer Vision and Pattern Recognition. San Francisco, USA, 1996: 22-38.
［20］YANG M H, KRIEGMAN D J, AHUJA N. Detection faces in images: a survey［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(1): 34-58.
［21］VIOLA P A, JONES M J. Robust real-time object detection［C］//Proc of IEEE ICCV Workshop on Statistical and Computational Theories of Vision. Vancouver, Canada, 2001: 747.
备注/Memo
作者简介：
陈春燕，女，1985年生，硕士研究生，主要研究方向为图像处理、机器视觉.
章品正，男，1976年生，讲师，主要研究方向为面部表情特征抽取与跟踪.近年来发表学术论文10余篇.
罗立民，男，1956年生，教授、博士生导师，长江学者特聘教授，九三学社中央委员，江苏省政协委员，中国电子学会生物医学电子学分会副主委，中国电子学会理事，IEEE高级会员，教育部科技委信息学部委员，东南大学理学院副院长，法国雷恩大学和上海交通大学兼职教授，IEEE EMB Magazine等国内外重要学术刊物编委.主要研究方向为图像处理、科学可视化和计算机辅助诊断与治疗.曾获江苏省科技进步2等奖、广东省科技进步2等奖、IEEE学会贡献奖等.近年来发表学术论文200余篇，撰写和参编学术著作5部.
更新日期/Last Update:
2009-12-29