[1]沈琳琳,明仲.基于皮肤模板和改进HMM的自动人脸识别系统[J].深圳大学学报理工版,2008,25(1):71-75.
 SHEN Lin-lin and MING Zhong.Automatic face recognition based on skin masking and improved HMM[J].Journal of Shenzhen University Science and Engineering,2008,25(1):71-75.
点击复制

基于皮肤模板和改进HMM的自动人脸识别系统()
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第25卷
期数:
2008年1期
页码:
71-75
栏目:
电子光学与信息工程
出版日期:
2008-01-30

文章信息/Info

Title:
Automatic face recognition based on skin masking and improved HMM
文章编号:
1000-2618(2008)01-0071-05
作者:
沈琳琳明仲
深圳大学软件学院,深圳518060
Author(s):
SHEN Lin-lin and MING Zhong
College of Software,Shenzhen University,Shenzhen 518060,P.R.China
关键词:
人脸识别人脸检测彩色图像处理生物特征识别隐马尔可夫模型
Keywords:
face recognitionface detectioncolor image processingbiometricshidden Markov model
分类号:
TP 391;TP 751
文献标志码:
A
摘要:
介绍一种基于隐马尔可夫模型(hidden Markov module,HMM)的人脸识别系统,该系统对人脸采用普通网络摄像头实时检测,通过皮肤模型进行背景去除,并用改进后的HMM算法进行识别. 实验结果表明,改进后的HMM算法能提高原HMM算法的准确率,采用皮肤模板对检测到的人脸进行精确定位后,进一步提高了识别算法的准确度.
Abstract:
A new hidden Markov module (HMM) based face recognition system is presented in this paper. Face images were extracted automatically from live videos captured by a Creative WebCam,and faces were recognized in real time using an improved HMM face recognition algorithm. A fast face detection algorithm using boosted Haar-like features was applied initially to detect faces regions from the video stream. The detected face region was further refined by a skin color masking module to achieve more accurate face position. To improve the accuracy of HMM based face recognition algorithm, discrete wavelet transform, instead of discrete cosine transform, was used to extract observation sequences for HMM. Experiments were conducted using two face databases:the ORL database and the Nottingham color face image database. The results on both databases show that the proposed method can improve the accuracy by more than six percents. Further improvement has been observed when a skin masking module is used to refine the detected face region.

参考文献/References:

[1]Rowley H A,Baluja S,Kanade T. 基于神经网络的人脸检测 [J]. IEEE模式分析和机器智能汇刊,1998,20(1):23-38(英文版).
[2]Viola P,Jones M. 采用boosting简单特征级联的快速物体检测 [C]//IEEE计算机视觉和模式识别会议论文集. 夏威夷,2001:511-518(英文版).
[3]Lienhart R,Maydt J. 基于扩展的Haar特征的快速物体检测 [C]//IEEE图像处理会议论文集. 纽约,2002:900-903(英文版).
[4]Lades M,Vorbruggen J C,Buhmann J,等. 基于动态链接架构的物体识别 [J]. IEEE计算机汇刊,1993,42(3):300-311(英文版).
[5]Wiskott L,Fellous J M,Kruger N,等. 基于弹性图形匹配的人脸识别 [J]. IEEE 模式分析和机器智能汇刊,1997,19(7):775-779(英文版).
[6]Er M J,Wu S,Lu J,等. 基于RBF神经网络的人脸识别 [J]. IEEE 神经网络汇刊,2002,13(3):697-710(英文版).
[7]Shen L,Bai L,Ji Z. 基于SVM和最优Gabor特征的人脸识别 [C]//计算机讲义. 2007,4781:168-177(英文版).
[8]SHEN Lin-lin.Bai L 基于Gabor小波的人脸识别方法综述[J]. 模式分析与应用,2006,9(2): 273-292(英文版).
[9]SHEN Lin-lin. 基于Gabor小波的人脸识别[D]. 诺丁汉: 英国诺丁汉大学,2005(英文版).
[10]Nefian A,Hayes M. 基于嵌入HMM的人脸检测和识别 [C]//IEEE 声学、语音和信号处理会议论文集. Phoenix,USA ,1999:3553-3556(英文版).
[11]Menser B,Muller F. 采用主分量分析的彩色图像脸部检测 [C]//第7届图像处理及其应用会议论文集. 英国曼彻斯特,1999:620-624(英文版).
[12]Bai L,Shen L. 基于方向图的人脸检测 [C]//控制和自动化计算智能会议论文集. 维也纳,2003:363-370(英文版).
[13]Rabiner L R. 隐马尔可夫模型及其在语音识别中的应用 [J]. IEEE论文集. 1989,77(2):257-286(英文版).

[1]Rowley H A,Baluja S,Kanade T. Neural network-based face detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(1):23-38.
[2]Viola P,Jones M. Rapid object detection using a boosted cascade of simple features [C]// in Proc of IEEE Conf. on Computer Vision and Pattern Recognition. Kauai,Hawaii 2001:511-518.
[3]Lienhart R,Maydt J. An extended set of Haar-like features for rapid object detection [C] // in Proc IEEE Conference on Image Processing. NY,2002:900-903.
[4]Lades M,Vorbruggen J C,Buhmann J,et al. Distortion invariant object recognition in the Dynamic Link Architecture [J]. IEEE Transactions on Computers,1993,42(3):300-311.
[5]Wiskott L,Fellous J M,Kruger N,et al. Face recognition by elastic bunch graph matching [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):775-779.
[6]Er M J,Wu S,Lu J,et al. Face recognition with radial basis function (RBF) neural networks [J]. IEEE Transactions on Neural Networks,2002,13(3):697-710.
[7]Shen L,Bai L,Ji Z. A SVM face recognition method based on optimized Gabor features [C]//Lecture Notes in Computer Science,2007,4781:168-177.
[8]SHEN Lin-lin,Bai L. A review on Gabor wavelets for face recognition[J]. Pattern Analysis and Applications,2006,9(2):273-292.
[9]SHEN Lin-lin. Recognizing faces:an approach based on Gabor wavelet[D]. Nottingham:University of Nottingham,2005.
[10]Nefian A M. Hayes. An embedded HMM-based approach for face detection and recognition[C]// in Proc of IEEE Int. Conf. On Acoustics,Speech and ignal Processing.,Phoenix,USA,1999:3553-3556.
[11]Menser B,Muller F. Face detection in color images using principal components analysis[C]// in Proc of Seventh International Conference on Image Processing and its Applications,Manchester,1999:620-624.
[12]Bai L and Shen L. Face detection by orientation map matching[C]//in Proc of International Conference on Computational Intelligence for Modelling Control and Automation.Vienna,2003:363-370.
[13]Rabiner L R. A tutorial on hidden Markov models and selected applications in speech recognition [J]. in Proc of IEEE,1989,77(2):257-286.

备注/Memo

备注/Memo:
收稿日期:2007-09-13;修回日期:2007-11-07
基金项目:国家自然科学基金资助项目(60673122);深圳大学科研启动基金资助项目(200746)
作者简介:沈琳琳(1976-),男(汉族),浙江省武义县人,深圳大学副教授、博士. E-mail:llshen@szu.edu.cn
更新日期/Last Update: 2008-02-17