人脸检测算法及其芯片实现关键技术研究
|
摘要
随着目标监控、目标跟踪、人机交互、人流统计等领域的兴起,人脸检测已不仅是人脸识别前期的一个重要步骤,它开始作为一门独立的技术受到了人们越来越广泛的关注。从数码相机、人机交互中的人脸定位,3G业务的图像通信,到人物跟踪、警戒区报警都离不开人脸检测技术。但由于人脸检测需要进行的计算量大,检测速度的提高和精确度的保证成了相互矛盾的两个方面。而很多应用中对这两方面都是有所要求的。另外,要使人脸检测技术能在未来发挥重要作用,真正有效应用于各种应用场合,那么人脸检测芯片的功耗、成本、可配置性都是值得研究的,这同时也是现今人脸检测技术面临的难题。
本论文致力于研究高性能人脸检测芯片的关键技术,从算法的改进、结构的设计、可配置性等多方面提出了实现高精度高速人脸检测芯片的一些创新性想法。
考虑到算法的有效性是高性能检测的一个重要方面,本文对目前最为高效的基于AdaBoost的人脸检测算法进行了深入的分析,介绍了其训练与检测的具体方法。并提出了方差预处理与级联结构相结合的人脸检测算法,以及适合于硬件实现、减少图像访存频率的图像缩小法。然后对目前国际公认的五个人脸数据库进行了总结与归纳,用各个数据库的测试结果证明了改进后的人脸检测算法的有效性。并对算法进行了定点化分析,选择了合适的定点化位数。
本文还从检测速度的提高、芯片的面积消耗、功率消耗各方面综合考虑,提出了高效的存储方案设计、积分图快速更新法、四级流水线处理结构,对芯片内部各模块的划分、各模块的结构、它们之间的工作时序等都进行了分析研究。并对设计的高性能人脸检测芯片进行了仿真、综合、验证与测试。实验结果表明,算法上的改进以及芯片的上述设计技术使得人脸检测芯片可以达到在保证高精度高速的前提下,具有较低的功耗和面积,与性能居于国际前沿的其他人脸检测芯片的测试结果相比,具有其优势。
鉴于人脸检测芯片的可配置直接影响其未来多场合应用的灵活性和开发成本,本文义提出了多模式可调人脸检测的概念。从人脸检测四个关键因子着于,分析其对检测性能的具体影响。并使其作为能调节芯片工作于不同模式的四个输入参数,实现了芯片的参数可调性能。
人脸检测技术是一门值得不断深入研究的课题,该课题的开展能带来巨大的社会效益,其研究成果也能为其他类型的目标检测提供有意义的参考。
With the rise of fields such as target monitoring, object tracking, human-computer interaction, statistics of people stream etc., face detection has not only been an important step of face recognition, but also become an independent technology being concerned by more and more people. It now has become indispensable in applications such as digital camera and human-computer interaction, the image communication of3G, the human tracking and alarm of security area. However, due to its huge computation, it is difficult to improve its speed and accuracy to satisfy the demand of many applications at the same time. And what's more, to really play its important role in future and to be efficiently applied to different situations, the promotion of power consumption, cost and processing ability of face detection chip are worthy to be researched. Nevertheless, these are just difficult problems we now confront.
The paper describes the research on the key technology of designing face detection chip with good performance, and puts forward some creative ideas in realizing face detection of high precision and speed from the side of algorithm improvement, architecture design and reconfiguration.
In considering that the efficiency of the algorithm is one of the most important factors in detection, the paper analyses the most efficient face detection method based on AdaBoost algorithm in depth. And after introducing its training and detection procedure, the paper proposes an improved algorithm integrating variance preprocess and cascade structure, and adopts the image scaling method for hardware realizing, which could greatly decrease the access of memory. Five commonly used face databases in the world are summarized then, and are used to test the efficiency of improved face detection algorithm. And the paper also gives out the fixed-point bits of every data in the algorithm for the concrete design of face detection chip later.
When considering the promotion of detection speed, and decrease of the power and area consumption, ideas of efficient memory scheme, quick refresh of integral image,4-stage pipeline processing method are proposed. The partition, architecture and the work order of each module are all researched in the paper. And they are also simulated, synthesized, validated and tested by corresponding tools. The results show that, the improvement of detection algorithm and creative chip design method are efficient, which makes the design have a relative less consumption of power and area compared to other advanced international designs, while maintaining a high precision and speed.
As the reconfiguration of the face detection chip will directly affect the flexibility in applications of face detection technology in different situations and the development cost, the paper also brings forward a mode adjustable design method. It mainly makes use of four key factors greatly affecting on the detection capability. And by adjusting these four factors as input parameters, we finally realize the reconfiguration and enable the chip work in different modes.
Face detection technology is a subject which is worthy to be researched continuously. It can bring with huge benefit to the society, and its research fruits can also provide meaningful reference to detection of other kinds of objects.
本论文致力于研究高性能人脸检测芯片的关键技术,从算法的改进、结构的设计、可配置性等多方面提出了实现高精度高速人脸检测芯片的一些创新性想法。
考虑到算法的有效性是高性能检测的一个重要方面,本文对目前最为高效的基于AdaBoost的人脸检测算法进行了深入的分析,介绍了其训练与检测的具体方法。并提出了方差预处理与级联结构相结合的人脸检测算法,以及适合于硬件实现、减少图像访存频率的图像缩小法。然后对目前国际公认的五个人脸数据库进行了总结与归纳,用各个数据库的测试结果证明了改进后的人脸检测算法的有效性。并对算法进行了定点化分析,选择了合适的定点化位数。
本文还从检测速度的提高、芯片的面积消耗、功率消耗各方面综合考虑,提出了高效的存储方案设计、积分图快速更新法、四级流水线处理结构,对芯片内部各模块的划分、各模块的结构、它们之间的工作时序等都进行了分析研究。并对设计的高性能人脸检测芯片进行了仿真、综合、验证与测试。实验结果表明,算法上的改进以及芯片的上述设计技术使得人脸检测芯片可以达到在保证高精度高速的前提下,具有较低的功耗和面积,与性能居于国际前沿的其他人脸检测芯片的测试结果相比,具有其优势。
鉴于人脸检测芯片的可配置直接影响其未来多场合应用的灵活性和开发成本,本文义提出了多模式可调人脸检测的概念。从人脸检测四个关键因子着于,分析其对检测性能的具体影响。并使其作为能调节芯片工作于不同模式的四个输入参数,实现了芯片的参数可调性能。
人脸检测技术是一门值得不断深入研究的课题,该课题的开展能带来巨大的社会效益,其研究成果也能为其他类型的目标检测提供有意义的参考。
With the rise of fields such as target monitoring, object tracking, human-computer interaction, statistics of people stream etc., face detection has not only been an important step of face recognition, but also become an independent technology being concerned by more and more people. It now has become indispensable in applications such as digital camera and human-computer interaction, the image communication of3G, the human tracking and alarm of security area. However, due to its huge computation, it is difficult to improve its speed and accuracy to satisfy the demand of many applications at the same time. And what's more, to really play its important role in future and to be efficiently applied to different situations, the promotion of power consumption, cost and processing ability of face detection chip are worthy to be researched. Nevertheless, these are just difficult problems we now confront.
The paper describes the research on the key technology of designing face detection chip with good performance, and puts forward some creative ideas in realizing face detection of high precision and speed from the side of algorithm improvement, architecture design and reconfiguration.
In considering that the efficiency of the algorithm is one of the most important factors in detection, the paper analyses the most efficient face detection method based on AdaBoost algorithm in depth. And after introducing its training and detection procedure, the paper proposes an improved algorithm integrating variance preprocess and cascade structure, and adopts the image scaling method for hardware realizing, which could greatly decrease the access of memory. Five commonly used face databases in the world are summarized then, and are used to test the efficiency of improved face detection algorithm. And the paper also gives out the fixed-point bits of every data in the algorithm for the concrete design of face detection chip later.
When considering the promotion of detection speed, and decrease of the power and area consumption, ideas of efficient memory scheme, quick refresh of integral image,4-stage pipeline processing method are proposed. The partition, architecture and the work order of each module are all researched in the paper. And they are also simulated, synthesized, validated and tested by corresponding tools. The results show that, the improvement of detection algorithm and creative chip design method are efficient, which makes the design have a relative less consumption of power and area compared to other advanced international designs, while maintaining a high precision and speed.
As the reconfiguration of the face detection chip will directly affect the flexibility in applications of face detection technology in different situations and the development cost, the paper also brings forward a mode adjustable design method. It mainly makes use of four key factors greatly affecting on the detection capability. And by adjusting these four factors as input parameters, we finally realize the reconfiguration and enable the chip work in different modes.
Face detection technology is a subject which is worthy to be researched continuously. It can bring with huge benefit to the society, and its research fruits can also provide meaningful reference to detection of other kinds of objects.
引文
[1]Hjelmas, E., Face detection:A survey, computer vision and image understanding. 2001:236-274.
[2]黎冰,吴松与曾凡涛,人脸识别在智能手机中的实现.计算机工程,2006.32(7)：272-274.
[3]蒋文荣,基于手机的便携人脸远程比对系统.江苏警官学院学报,2008(5)：169-173.
[4]卓力,沈兰荪与张延华,一种嵌入式头肩图像编码方法.电子学报,2003.31(12)：1832-1834.
[5]郝晓莉,陈后金,蔡伯根,李杰.基于脸部检测和FUZZY ART的乘客检测算法.北京交通大学学报,2007.31(5)：19-22.
[6]宋红与石峰,基于人脸检测与跟踪的智能监控系统.北京理工大学学报,2004.24(11)：966-970.
[7]邢延超与强文萍,基于人脸检测与跟踪的广告效果评估系统.计算机应用,2009(10)：2700-2702.
[8]高永萍,秦华标。驾驶员疲劳检测系统.仪表技术与传感器,2007,1：60-62.
[9]梁路宏,艾海舟等,人脸检测研究综述.计算机学报,2002.25(5)：449-458.
[10]Sung K, Poggio T. Example-based learning for view based human face detection. IEEE Trans Pattern Analysis and Machine Intelligence,1998,20(1):39-51.
[11]Yang MH, Roth D, Ahuja N. A SNo W-Based Face Detector. Advances in Neural Information Processing Systems 12, S.A. Solla, T. K. Leen, and K.-R. Muller, eds., pp. 855-861, MIT Press,2000.
[12]Schneiderman H. A statistical method for 3D object detection applied to faces and cars. In International Conference on Computer Vision,2000
[13]Jones MJ. Rehg JM. Statistical color models with application to skin detection. Technical report, Cambridge Res. Lab., Compaq Computer Corp.,1998.
[14]Martinkauppi B. Face colour under varying illumination-analysis and applications. PhD thesis, University of Oulu,2002.
[15]Terrillon JC, Shirazi M N, Fukamachi H, and Akamatsu S. Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images. Proc. IEEE Int'l Conf. on Face and Gesture Recognition, pp.54-61,2000.
[16]Comaniciu D, Ramesh V, Meer P. Real-Time Tracking of Non-Rigid Objects using Mean Shift. IEEE Conf. Computer Vision and Pattern Recognition (CVPR'00), Hilton Head Island, South Carolina, Vol.2,142-149,2000.
[17]Comaniciu D, Ramesh V. Robust Detection and Tracking of Human Faces with an Active Camera. IEEE Int. Workshop on Visual Surveillance, Dublin, Ireland, 11-18,2000.
[18]Hsu RL, Abdel-Mottaleb M, A K Jain. Face detection in color images. IEEE Trans. Pattern Analysis and Machine Intelligence, vol.24, no.5, pp.696-706, May 2002.
[19]Sobottka K and Pitas I. Face Localization and Feature Extraction Based on Shape and Color Information. Proc. IEEE Int'l Conf. Image Processing, pp.483-486,1996.
[20]Kim H, Kang W, Shin J, Park S. Face Detection Using Template Matching and Ellipse Fitting. IEICE Trans. Inf.& Syst., Vol.E38-D, No.11, pp2008-2011, Nov 2000.
[21]Wang J, Tan T. A new face detection method based on shape information. PRL, vol.21, pp.463-471,00.
[22]Govindaraju V, Srihari SN, Sher DB. A computational model for face location. In: Proc IEEE Conference on Computer Vision, Osaka, Japan,1990.718-721.
[23]Miao J, Yin BC, Wang KQ et.al. A hierarchical multiscale and multiangle system for human face detection in a complex back-ground using gravity-center template. Pattern Recognition,1999,32(10):1237-1248.
[24]Schneiderman H, Kanade T. Probabilistic modeling of local appearance and spatial relationships for object recognition. In: Proc IEEE Conference on Computer Vision and Pattern Recognition, Santa Barbara, California.1998.45-51.
[25]Viola P. Rapid object detection using a Boosted cascade of simple features. In: Proc IEEE Conference on Computer Vision and Pattern Recognition, pp:511-518, 2001.
[26]Craw I, Ellis H, Lishman J. Automatic extraction of face features. Pattern Recognition Letters,1987,5(2):183-187.
[27]Heisele B, Serre T, Prentice S, Poggio T. Hierarchical Classification and Feature Reduction for Fast Face Detection with Support Vector Machines. Pattern Recognition, Vol.36, No.9,2007-2017,2003.
[28]Heisele B, Serre T, Mukherjee S and Poggio T. Feature Reduction and Hierarchy of Classifiers for Fast Object Detection in Video Images. Proceedings of 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'2001), Kauai, Hawaii, Vol.2,18-24, December 2001.
[29]Garcia C, Delakis M. A Neural Architecture for Fast and Robust Face Detection. Proc. of the IEEE-IAPR International Conference on Pattern Recognition (ICPR'2002), Volume 2, pages 40-43.
[30]Boris E Shpungin, Javier R. Movellan. A Multi-Threaded Approach to Real Time Face Tracking. UCSD MP Lab TR 2000, July 2000
[31]Liu C.J. A Bayesian Discriminating Features Method for Face Detection. IEEE Trans. Pattern Analysis and Machine Intelligence, vol.25, no.6, pp.725-740,2003.
[32]Rowley HA. Neural Network-Based Face Detection. PhD thesis, Carnegie Mellon Univ.,1999.
[33]Rowley H, Baluja S, Kanade T. Rotation Invariant Neural Network-Based Face Detection. Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp.38-44, 1998.
[34]Chen ZY, Qi FH. Cascading Neural Networks-based human face detection. Joural of Infrated Millim. Waves, Vol.19,No.1 February,2000 pp:57-61.
[35]Juell P, Marsh R. A hierarchical neural network for human face detection. Pattern Recognition,1996,29(5):781-787.
[36]Kouzani AZ, He F, Sammut K. Commonsense knowledge-based face detection. In:Proc Conference on Intelligent Engineering Systems, Budapast, Hungary,1997. 215-220.
[37]Anifantis D, Dermatas E, Kokkinakis G. A neural network method for accurate face detection on arbitrary images. In:Proc Conference on Electronics, Circuits and Systems, Pafos, Cyprus,1999,1:109-112.
[38]Sanderson C, Paliwal KK. Fast Features for Face Authentication under Illumination Direction Changes. Pattern Recognition Letters 24 (14) 2003.
[39]Osuna E, Girosi F. Reducing the run-time complexity of Support Vector Machines. ICPR'98, Brisbane, Australia,16-20 Aug.,1998.
[40]Murai K and Nakamura S. Real Time Face Detection for Multimodal Speech Recognition. Proc. of ICME2002(International Conference on Multimedia and Expo), Vol.2, pp.373-376,2002.
[41]Feraud R, Olivier J Bernier, Viallet J, and Collobert M. A Fast and Accurate Face Detector Based on Neural Networks. IEEE Trans, on Pattern Analysis and Machine Intelligence, Vol.23, No.1, JANUARY 2001.
[42]Viola P, Jones M. Robust real time object detection Technical Report. CRL 2001/01, Compaq Cambridge Research Laboratory, February 2001.
[43]Lienhart R, Kuranov A, V Pisarevsky. Empirical analysis of detection cascades of boosted classifiers for rapid object detection. DAGM'03,2003.
[44]Lienhart R, Liang L, and Kuranov A. A detector tree of boosted classifier for real time object detection and tracking. IEEE International Conference on Multimedia & Expo,2003.
[45]Li SZ, Zhu L, Zhang ZQ, Zhang HJ. Learning to Detect Multi-View Faces in Real-Time. In Proceedings of the 2nd International Conference on Development and Learning. Washington DC. June,2002.
[46]Li SZ, Zhu L, Zhang ZQ, Blake A, Zhang HJ, Shum H. Statistical Learning of Multi-View Face Detection. In Proceedings of the 7th European Conference on Computer Vision. Copenhagen, Denmark. May,2002.
[47]Li SZ, Zou XL, Hu YX, Zhang ZQ, Yan SC, Peng XH, Huang L, Zhang HJ. Real-Time Multi-View Face Detection, Tracking, Pose Estimation, Alignment, and Recognition. CVPR 2001 Demo Summary. Hawaii. December,2001
[48]Liu C, Shum HY. Kullback-Leibler Boosting. Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'03).2003.
[49]Viola P. Fast and Robust Classification using Asymmetric AdaBoost and a Detector Cascade NIPS 2001:1311-1318.
[50]Zhang ZQ, Li M, Li SZ, Zhang HJ. Multi-view face detection with floatboost. WACV02(184-188). IEEE Top Reference.0303 Bib Ref.
[51]Sahbi H. Coarse-to-Fine Support Vector Machines for Hierarchical Face Detection. PhD Thesis, University of Versailles, April 2003.
[52]Sahbi H, Geman D, Boujemma N. Face Detection Using Coarse-to-Fine Support Vector Classifiers In the IEEE, International Conference on Image Processing, ICIP 2002.
[53]Khattab, K., et al., Embedded System Study for Real Time Boosting Based Face Detection,32nd Annual Conference on IEEE Industrial Electronics.2006:3461-3465.
[54]Theocharides, T., N. Vijaykrishnan and M.J. Irwin, "A Parallel Architecture for Hardware Face Detection". ISVLSI 2006, Karlsruhe, Germany,452-453.
[55]Hung-Chih, L., M. Savvides and C. Tsuhan. Proposed FPGA Hardware Architecture for High Frame Rate Face Detection(>100 fps)Using Feature Cascade Classifiers. First IEEE International Conference on Biometrics:Theory, Applications, and Systems,2007.
[56]Hiromoto, M., H. Sugano and R. Miyamoto, Partially Parallel Architecture for AdaBoost-Based Detection With Haar-like Features. IEEE Transactions on Circuits and Systems for Video Technology,2009.19(1):41-52.
[57]Cho, J., B. Benson and R. Kastner, Hardware Acceleration of Multi-view Face Detection, SASP'09,2009:66-69.
[58]Yuehua, S., Z. Feng and Z. Zhong. Hardware Implementation of ADABOOST ALGORITHM and Verification.22nd International Conference on Advanced Information Networking and Applications,2008. pp.343-346
[59]施跃华,赵峰与张忠,AdaBoost算法的人脸检测系统的SoC软硬件设计.信息技术,2008.32(9)：151-153.
[60]Christos Kyrkou, and Thecharis Theocharides, "A flexible parallel hardware architecture for AdaBoost-based real-time object detection," IEEE Trans, on Very Large Scale Integration Systems, vol.19, no.6, pp.1034-1047, Jun.2011.
[61]Yu, W., B. Xiong and C. Chareonsak. FPGA implementation of AdaBoost algorithm for detection of face biometrics. IEEE International Workshop on Biomedical Circuits and Systems,2004.
[62]Ming, Y., et al. Face detection for automatic exposure control in handheld camera. IEEE International Conference on Computer Vision Systems,2006.
[63]Hori, Y., M. Kusaka and T. Kuroda. A 0.79mm2 29mW Real-Time Face Detection IP Core.2006 Symposium on VLSI Circuits,2006.
[64]Hanai, Y., et al. A versatile recognition processor employing Haar-like feature and cascaded classifier. IEEE International on Solid-State Circuits Conference, vol.52, pp.148-149, Feb.2009.
[65]Wei-Su, W., C. Chih-Rung and C. Ching-Te. A 100MHz hardware-efficient boost cascaded face detection design.16th IEEE International Conference on Image Processing,2009.
[66]Chen, C.R., W.S. Wong and C.T. Chiu, A 0.64 mmΛ2 Real-Time Cascade Face Detection Design Based on Reduced Two-Field Extraction. IEEE Transactions on Very Large Scale Integration Systems,2010.99:1-12.
[67]居然,上海交通大学硕士学位论文,2008
[68]郑峰.基于AdaBoost学习算法的人脸检测方法研究[硕士论文].上海：上海交通大学,2005.
[69]Carnegie Mellon Univ., Pittsburgh, PA, "CMU face datasets," 2000.[Online]. Available:http://vasc.ri.cmu.edu//idb/htrnl/face/frontal_images/index.html
[70]R. Frischholz, "Bao face database at the face detection homepage," 2008. [Online]. Available:http://www.facedetection.com/downloads/BaoDataBase.zip
[71]Robert Frischholz, "face detection homepage",2001.[Online]. Available: https://www.bioid. com/download-center/so ftware/bioid-face-database.html
[72]Deng Cai,"Four face databases in matlab format",1997 [Online]. Available: http://www.zjucadcg.cn/dengcai/Data/FaceData.html
[73]Libor Spacek, "Description of the Collection of Facial Images",Updated 2008 [Online]. Available:http://cswww.essex.ac.uk/mv/allfaces/
[74]Lu Peng, Chen Yi song, Chen Wen guang "Cascade Based Multi-feature Fusion MethodAlgorithm for Face detection". Computer Engineering.2011.37(2):7-9.
[75]Zhengming Li; Lijie Xue; Fei Tan. "Face Detection in Complex Background Based on Skin Color Features and Improved AdaBoost Algorithms". PIC 2010. PP:723-727
[76]R. Lienhart and J. Maydt, "An extended set of Haar-like features for rapid object detection," in Proc. IEEE Int. Conf. Image Process., Sep.2002, vol.1, pp.I-900-903.
[77]R. Gonzalez and R.Woods, Digital Image Processing,2nd ed. Upper Saddle River, NJ:Prentice Hall,2002.
[78]Junguk Cho, Bridget Benson, Shahnam Marzaei, et al, Parallelized Architecture of multiple classifiers for face detection, IEEE International Conference on ASSAP, 2009,pp72-82
[79]Ren C.Luo, Hsin-Hung Liu. Design and Implementation of Efficient Hardware Solution Based Sub-window Architecture of Haar Classifiers for Real-time Detection of Face Biometrics. IEEE International Conference on Mechatronics and Automation. 2010.1563-1568.
[80]Junguk Cho, Bridget Benson, Shahnam Marzaei, et al, Parallelized Architecture of multiple classifiers for face detection, IEEE International Conference on ASSAP, 2009,pp72-82
[81]魏良,苏光大,邓亚峰,基于FPGA的快速人脸检测,电子技术应用,2006年第11期,33-35.
[82]B. Heiselet, T Serre, M Pontil, et al., Component-based Face Detection, Proc IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001, vol:1,657-662.
[83]T. Theocharides, G. Link, N. Vijaykrishnan, M. J. Irwin, and W.Wolf,"Embedded hardware face detection," in Proc. IEEE Int. Conf. VLSIDes.,2004, pp.133-138.
[84]谢长生,徐睿FPGA在ASIC设计流程中的应用,微电子技术,VOL29,第6期,2001.12.
[85]V. Kianzad etal., "An architectural level design methodology for embedded face detection", International Conference on Hardware/Software Codesign and System Synthesis, Sep.2005.
[86]Mariatos, V., K.D. Adaos and G.P. Alexiou. "Design and implementation of a reconfigurable embedded real-time face detection system, in Rapid System Prototyping,2007. RSP 2007.18th IEEE/IFIP International Workshop on.2007.
[2]黎冰,吴松与曾凡涛,人脸识别在智能手机中的实现.计算机工程,2006.32(7)：272-274.
[3]蒋文荣,基于手机的便携人脸远程比对系统.江苏警官学院学报,2008(5)：169-173.
[4]卓力,沈兰荪与张延华,一种嵌入式头肩图像编码方法.电子学报,2003.31(12)：1832-1834.
[5]郝晓莉,陈后金,蔡伯根,李杰.基于脸部检测和FUZZY ART的乘客检测算法.北京交通大学学报,2007.31(5)：19-22.
[6]宋红与石峰,基于人脸检测与跟踪的智能监控系统.北京理工大学学报,2004.24(11)：966-970.
[7]邢延超与强文萍,基于人脸检测与跟踪的广告效果评估系统.计算机应用,2009(10)：2700-2702.
[8]高永萍,秦华标。驾驶员疲劳检测系统.仪表技术与传感器,2007,1：60-62.
[9]梁路宏,艾海舟等,人脸检测研究综述.计算机学报,2002.25(5)：449-458.
[10]Sung K, Poggio T. Example-based learning for view based human face detection. IEEE Trans Pattern Analysis and Machine Intelligence,1998,20(1):39-51.
[11]Yang MH, Roth D, Ahuja N. A SNo W-Based Face Detector. Advances in Neural Information Processing Systems 12, S.A. Solla, T. K. Leen, and K.-R. Muller, eds., pp. 855-861, MIT Press,2000.
[12]Schneiderman H. A statistical method for 3D object detection applied to faces and cars. In International Conference on Computer Vision,2000
[13]Jones MJ. Rehg JM. Statistical color models with application to skin detection. Technical report, Cambridge Res. Lab., Compaq Computer Corp.,1998.
[14]Martinkauppi B. Face colour under varying illumination-analysis and applications. PhD thesis, University of Oulu,2002.
[15]Terrillon JC, Shirazi M N, Fukamachi H, and Akamatsu S. Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images. Proc. IEEE Int'l Conf. on Face and Gesture Recognition, pp.54-61,2000.
[16]Comaniciu D, Ramesh V, Meer P. Real-Time Tracking of Non-Rigid Objects using Mean Shift. IEEE Conf. Computer Vision and Pattern Recognition (CVPR'00), Hilton Head Island, South Carolina, Vol.2,142-149,2000.
[17]Comaniciu D, Ramesh V. Robust Detection and Tracking of Human Faces with an Active Camera. IEEE Int. Workshop on Visual Surveillance, Dublin, Ireland, 11-18,2000.
[18]Hsu RL, Abdel-Mottaleb M, A K Jain. Face detection in color images. IEEE Trans. Pattern Analysis and Machine Intelligence, vol.24, no.5, pp.696-706, May 2002.
[19]Sobottka K and Pitas I. Face Localization and Feature Extraction Based on Shape and Color Information. Proc. IEEE Int'l Conf. Image Processing, pp.483-486,1996.
[20]Kim H, Kang W, Shin J, Park S. Face Detection Using Template Matching and Ellipse Fitting. IEICE Trans. Inf.& Syst., Vol.E38-D, No.11, pp2008-2011, Nov 2000.
[21]Wang J, Tan T. A new face detection method based on shape information. PRL, vol.21, pp.463-471,00.
[22]Govindaraju V, Srihari SN, Sher DB. A computational model for face location. In: Proc IEEE Conference on Computer Vision, Osaka, Japan,1990.718-721.
[23]Miao J, Yin BC, Wang KQ et.al. A hierarchical multiscale and multiangle system for human face detection in a complex back-ground using gravity-center template. Pattern Recognition,1999,32(10):1237-1248.
[24]Schneiderman H, Kanade T. Probabilistic modeling of local appearance and spatial relationships for object recognition. In: Proc IEEE Conference on Computer Vision and Pattern Recognition, Santa Barbara, California.1998.45-51.
[25]Viola P. Rapid object detection using a Boosted cascade of simple features. In: Proc IEEE Conference on Computer Vision and Pattern Recognition, pp:511-518, 2001.
[26]Craw I, Ellis H, Lishman J. Automatic extraction of face features. Pattern Recognition Letters,1987,5(2):183-187.
[27]Heisele B, Serre T, Prentice S, Poggio T. Hierarchical Classification and Feature Reduction for Fast Face Detection with Support Vector Machines. Pattern Recognition, Vol.36, No.9,2007-2017,2003.
[28]Heisele B, Serre T, Mukherjee S and Poggio T. Feature Reduction and Hierarchy of Classifiers for Fast Object Detection in Video Images. Proceedings of 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'2001), Kauai, Hawaii, Vol.2,18-24, December 2001.
[29]Garcia C, Delakis M. A Neural Architecture for Fast and Robust Face Detection. Proc. of the IEEE-IAPR International Conference on Pattern Recognition (ICPR'2002), Volume 2, pages 40-43.
[30]Boris E Shpungin, Javier R. Movellan. A Multi-Threaded Approach to Real Time Face Tracking. UCSD MP Lab TR 2000, July 2000
[31]Liu C.J. A Bayesian Discriminating Features Method for Face Detection. IEEE Trans. Pattern Analysis and Machine Intelligence, vol.25, no.6, pp.725-740,2003.
[32]Rowley HA. Neural Network-Based Face Detection. PhD thesis, Carnegie Mellon Univ.,1999.
[33]Rowley H, Baluja S, Kanade T. Rotation Invariant Neural Network-Based Face Detection. Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp.38-44, 1998.
[34]Chen ZY, Qi FH. Cascading Neural Networks-based human face detection. Joural of Infrated Millim. Waves, Vol.19,No.1 February,2000 pp:57-61.
[35]Juell P, Marsh R. A hierarchical neural network for human face detection. Pattern Recognition,1996,29(5):781-787.
[36]Kouzani AZ, He F, Sammut K. Commonsense knowledge-based face detection. In:Proc Conference on Intelligent Engineering Systems, Budapast, Hungary,1997. 215-220.
[37]Anifantis D, Dermatas E, Kokkinakis G. A neural network method for accurate face detection on arbitrary images. In:Proc Conference on Electronics, Circuits and Systems, Pafos, Cyprus,1999,1:109-112.
[38]Sanderson C, Paliwal KK. Fast Features for Face Authentication under Illumination Direction Changes. Pattern Recognition Letters 24 (14) 2003.
[39]Osuna E, Girosi F. Reducing the run-time complexity of Support Vector Machines. ICPR'98, Brisbane, Australia,16-20 Aug.,1998.
[40]Murai K and Nakamura S. Real Time Face Detection for Multimodal Speech Recognition. Proc. of ICME2002(International Conference on Multimedia and Expo), Vol.2, pp.373-376,2002.
[41]Feraud R, Olivier J Bernier, Viallet J, and Collobert M. A Fast and Accurate Face Detector Based on Neural Networks. IEEE Trans, on Pattern Analysis and Machine Intelligence, Vol.23, No.1, JANUARY 2001.
[42]Viola P, Jones M. Robust real time object detection Technical Report. CRL 2001/01, Compaq Cambridge Research Laboratory, February 2001.
[43]Lienhart R, Kuranov A, V Pisarevsky. Empirical analysis of detection cascades of boosted classifiers for rapid object detection. DAGM'03,2003.
[44]Lienhart R, Liang L, and Kuranov A. A detector tree of boosted classifier for real time object detection and tracking. IEEE International Conference on Multimedia & Expo,2003.
[45]Li SZ, Zhu L, Zhang ZQ, Zhang HJ. Learning to Detect Multi-View Faces in Real-Time. In Proceedings of the 2nd International Conference on Development and Learning. Washington DC. June,2002.
[46]Li SZ, Zhu L, Zhang ZQ, Blake A, Zhang HJ, Shum H. Statistical Learning of Multi-View Face Detection. In Proceedings of the 7th European Conference on Computer Vision. Copenhagen, Denmark. May,2002.
[47]Li SZ, Zou XL, Hu YX, Zhang ZQ, Yan SC, Peng XH, Huang L, Zhang HJ. Real-Time Multi-View Face Detection, Tracking, Pose Estimation, Alignment, and Recognition. CVPR 2001 Demo Summary. Hawaii. December,2001
[48]Liu C, Shum HY. Kullback-Leibler Boosting. Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'03).2003.
[49]Viola P. Fast and Robust Classification using Asymmetric AdaBoost and a Detector Cascade NIPS 2001:1311-1318.
[50]Zhang ZQ, Li M, Li SZ, Zhang HJ. Multi-view face detection with floatboost. WACV02(184-188). IEEE Top Reference.0303 Bib Ref.
[51]Sahbi H. Coarse-to-Fine Support Vector Machines for Hierarchical Face Detection. PhD Thesis, University of Versailles, April 2003.
[52]Sahbi H, Geman D, Boujemma N. Face Detection Using Coarse-to-Fine Support Vector Classifiers In the IEEE, International Conference on Image Processing, ICIP 2002.
[53]Khattab, K., et al., Embedded System Study for Real Time Boosting Based Face Detection,32nd Annual Conference on IEEE Industrial Electronics.2006:3461-3465.
[54]Theocharides, T., N. Vijaykrishnan and M.J. Irwin, "A Parallel Architecture for Hardware Face Detection". ISVLSI 2006, Karlsruhe, Germany,452-453.
[55]Hung-Chih, L., M. Savvides and C. Tsuhan. Proposed FPGA Hardware Architecture for High Frame Rate Face Detection(>100 fps)Using Feature Cascade Classifiers. First IEEE International Conference on Biometrics:Theory, Applications, and Systems,2007.
[56]Hiromoto, M., H. Sugano and R. Miyamoto, Partially Parallel Architecture for AdaBoost-Based Detection With Haar-like Features. IEEE Transactions on Circuits and Systems for Video Technology,2009.19(1):41-52.
[57]Cho, J., B. Benson and R. Kastner, Hardware Acceleration of Multi-view Face Detection, SASP'09,2009:66-69.
[58]Yuehua, S., Z. Feng and Z. Zhong. Hardware Implementation of ADABOOST ALGORITHM and Verification.22nd International Conference on Advanced Information Networking and Applications,2008. pp.343-346
[59]施跃华,赵峰与张忠,AdaBoost算法的人脸检测系统的SoC软硬件设计.信息技术,2008.32(9)：151-153.
[60]Christos Kyrkou, and Thecharis Theocharides, "A flexible parallel hardware architecture for AdaBoost-based real-time object detection," IEEE Trans, on Very Large Scale Integration Systems, vol.19, no.6, pp.1034-1047, Jun.2011.
[61]Yu, W., B. Xiong and C. Chareonsak. FPGA implementation of AdaBoost algorithm for detection of face biometrics. IEEE International Workshop on Biomedical Circuits and Systems,2004.
[62]Ming, Y., et al. Face detection for automatic exposure control in handheld camera. IEEE International Conference on Computer Vision Systems,2006.
[63]Hori, Y., M. Kusaka and T. Kuroda. A 0.79mm2 29mW Real-Time Face Detection IP Core.2006 Symposium on VLSI Circuits,2006.
[64]Hanai, Y., et al. A versatile recognition processor employing Haar-like feature and cascaded classifier. IEEE International on Solid-State Circuits Conference, vol.52, pp.148-149, Feb.2009.
[65]Wei-Su, W., C. Chih-Rung and C. Ching-Te. A 100MHz hardware-efficient boost cascaded face detection design.16th IEEE International Conference on Image Processing,2009.
[66]Chen, C.R., W.S. Wong and C.T. Chiu, A 0.64 mmΛ2 Real-Time Cascade Face Detection Design Based on Reduced Two-Field Extraction. IEEE Transactions on Very Large Scale Integration Systems,2010.99:1-12.
[67]居然,上海交通大学硕士学位论文,2008
[68]郑峰.基于AdaBoost学习算法的人脸检测方法研究[硕士论文].上海：上海交通大学,2005.
[69]Carnegie Mellon Univ., Pittsburgh, PA, "CMU face datasets," 2000.[Online]. Available:http://vasc.ri.cmu.edu//idb/htrnl/face/frontal_images/index.html
[70]R. Frischholz, "Bao face database at the face detection homepage," 2008. [Online]. Available:http://www.facedetection.com/downloads/BaoDataBase.zip
[71]Robert Frischholz, "face detection homepage",2001.[Online]. Available: https://www.bioid. com/download-center/so ftware/bioid-face-database.html
[72]Deng Cai,"Four face databases in matlab format",1997 [Online]. Available: http://www.zjucadcg.cn/dengcai/Data/FaceData.html
[73]Libor Spacek, "Description of the Collection of Facial Images",Updated 2008 [Online]. Available:http://cswww.essex.ac.uk/mv/allfaces/
[74]Lu Peng, Chen Yi song, Chen Wen guang "Cascade Based Multi-feature Fusion MethodAlgorithm for Face detection". Computer Engineering.2011.37(2):7-9.
[75]Zhengming Li; Lijie Xue; Fei Tan. "Face Detection in Complex Background Based on Skin Color Features and Improved AdaBoost Algorithms". PIC 2010. PP:723-727
[76]R. Lienhart and J. Maydt, "An extended set of Haar-like features for rapid object detection," in Proc. IEEE Int. Conf. Image Process., Sep.2002, vol.1, pp.I-900-903.
[77]R. Gonzalez and R.Woods, Digital Image Processing,2nd ed. Upper Saddle River, NJ:Prentice Hall,2002.
[78]Junguk Cho, Bridget Benson, Shahnam Marzaei, et al, Parallelized Architecture of multiple classifiers for face detection, IEEE International Conference on ASSAP, 2009,pp72-82
[79]Ren C.Luo, Hsin-Hung Liu. Design and Implementation of Efficient Hardware Solution Based Sub-window Architecture of Haar Classifiers for Real-time Detection of Face Biometrics. IEEE International Conference on Mechatronics and Automation. 2010.1563-1568.
[80]Junguk Cho, Bridget Benson, Shahnam Marzaei, et al, Parallelized Architecture of multiple classifiers for face detection, IEEE International Conference on ASSAP, 2009,pp72-82
[81]魏良,苏光大,邓亚峰,基于FPGA的快速人脸检测,电子技术应用,2006年第11期,33-35.
[82]B. Heiselet, T Serre, M Pontil, et al., Component-based Face Detection, Proc IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001, vol:1,657-662.
[83]T. Theocharides, G. Link, N. Vijaykrishnan, M. J. Irwin, and W.Wolf,"Embedded hardware face detection," in Proc. IEEE Int. Conf. VLSIDes.,2004, pp.133-138.
[84]谢长生,徐睿FPGA在ASIC设计流程中的应用,微电子技术,VOL29,第6期,2001.12.
[85]V. Kianzad etal., "An architectural level design methodology for embedded face detection", International Conference on Hardware/Software Codesign and System Synthesis, Sep.2005.
[86]Mariatos, V., K.D. Adaos and G.P. Alexiou. "Design and implementation of a reconfigurable embedded real-time face detection system, in Rapid System Prototyping,2007. RSP 2007.18th IEEE/IFIP International Workshop on.2007.