基于小波变换和神经网络的人数统计方法研究
|
摘要
摘要
随着经济社会的发展，各种公共场地和设施中的人群流动越来越频繁。如何
对公共场合的人群进行有效管理与控制，是不得不考虑的重大问题，智能化人群
人数统计方法应运而生。智能化人群人数统计可以用于人群的监测和管理，同时
也可用于商业领域如市场调查、交通安全以及建筑设计领域等。它直接或间接地
提高了上述场合工作人员的工作效率和建筑设施的利用率，对人群人数统计方法
的研究有着深远的意义和广阔的前景。
本课题的研究内容是运用图像/视频处理和模式识别等技术对人群人数进行
智能化统计。其中，如何有效地提取表征人群个体的特征，如何对人群个体和背
景进行分类，以及如何快速统计人群人数是人群人数统计方法的关键技术，也是
本论文的主要研究内容。
本论文首先介绍了智能化人群监测系统的构成和基本原理以及它的发展。然
后指出了现有人群监测系统的不足之处。论文提出了一种通过定位头部识别人群
个体从而对人群人数进行统计的方法。首先对头部图像作二维 Haar 小波变换，
对一级、二级小波系数进行了分析，并利用反向传播神经网络加以详细验证，最
后采用了一级和二级小波的 HL 和 LH 子带系数作为特征量。特征量的选取的理
论依据是小波 HL 和 LH 子带能够反映图像的轮廓及横向和纵向的纹理特征。为
了进一步降低误检率，我们采用自举的方法对训练样本库进行补充扩大。然后借
助基于 YCbCr 空间的肤色模型对实验结果进行了后验证，相比于传统的只考虑
色度的肤色模型，我们采用的是最新提出的加入亮度补偿的椭圆肤色模型。最后
对结果图像中相同个体的窗口采用目标聚类的分析方法加以合并。实验取得了较
好的效果。
With the development of the society, more and more people appeared in public
places and facilities. So, how to manage the crowd is a problem that we have to pay
special attention to. And intelligent crowd surveillance based on image processing
emerges as requested. It can be applied to the fields of crowd surveillance and
management, market research, traffic safety, and building design. It may improve
work efficiency of the above situations and the rate in use of buildings directly or
indirectly. Research on people counting has deep meanings and wide future.
The emphasis of the thesis is people counting using technology of image/video
processing and pattern recognition. And how to extract the features of head effectively,
and how to classify people and background are the key technologies of this thesis.
The thesis first introduces the structure and development of intelligent crowd
surveillance system. And then the limitations of present system are addressed. This
thesis proposes a method of recognizing the individual in the crowd by detecting the
head, and then estimating the number of crowd. After the first and second grade of 2D
Haar wavelet transform, we analyses the wavelet coefficients, and use
back-propagation network to testify those coefficients selected as features. At last we
select the coefficients of HL sub band and LH sub band as features. The basis of
concept in selecting those features is that the coefficients reveal the contour and the
texture of horizontal and vertical orientation. In order to reduce the rate of error
detection, Bootstrapping is used to enlarge the number of samples. And as follows a
skin model of YCbCr color space is taken as post-validation. Unlike the conventional
skin model, a model of adding lighting compensation that is presented newly is used.
Finally, the head windows of same person using object clustering are merged. And the
test has got good results.
随着经济社会的发展，各种公共场地和设施中的人群流动越来越频繁。如何
对公共场合的人群进行有效管理与控制，是不得不考虑的重大问题，智能化人群
人数统计方法应运而生。智能化人群人数统计可以用于人群的监测和管理，同时
也可用于商业领域如市场调查、交通安全以及建筑设计领域等。它直接或间接地
提高了上述场合工作人员的工作效率和建筑设施的利用率，对人群人数统计方法
的研究有着深远的意义和广阔的前景。
本课题的研究内容是运用图像/视频处理和模式识别等技术对人群人数进行
智能化统计。其中，如何有效地提取表征人群个体的特征，如何对人群个体和背
景进行分类，以及如何快速统计人群人数是人群人数统计方法的关键技术，也是
本论文的主要研究内容。
本论文首先介绍了智能化人群监测系统的构成和基本原理以及它的发展。然
后指出了现有人群监测系统的不足之处。论文提出了一种通过定位头部识别人群
个体从而对人群人数进行统计的方法。首先对头部图像作二维 Haar 小波变换，
对一级、二级小波系数进行了分析，并利用反向传播神经网络加以详细验证，最
后采用了一级和二级小波的 HL 和 LH 子带系数作为特征量。特征量的选取的理
论依据是小波 HL 和 LH 子带能够反映图像的轮廓及横向和纵向的纹理特征。为
了进一步降低误检率，我们采用自举的方法对训练样本库进行补充扩大。然后借
助基于 YCbCr 空间的肤色模型对实验结果进行了后验证，相比于传统的只考虑
色度的肤色模型，我们采用的是最新提出的加入亮度补偿的椭圆肤色模型。最后
对结果图像中相同个体的窗口采用目标聚类的分析方法加以合并。实验取得了较
好的效果。
With the development of the society, more and more people appeared in public
places and facilities. So, how to manage the crowd is a problem that we have to pay
special attention to. And intelligent crowd surveillance based on image processing
emerges as requested. It can be applied to the fields of crowd surveillance and
management, market research, traffic safety, and building design. It may improve
work efficiency of the above situations and the rate in use of buildings directly or
indirectly. Research on people counting has deep meanings and wide future.
The emphasis of the thesis is people counting using technology of image/video
processing and pattern recognition. And how to extract the features of head effectively,
and how to classify people and background are the key technologies of this thesis.
The thesis first introduces the structure and development of intelligent crowd
surveillance system. And then the limitations of present system are addressed. This
thesis proposes a method of recognizing the individual in the crowd by detecting the
head, and then estimating the number of crowd. After the first and second grade of 2D
Haar wavelet transform, we analyses the wavelet coefficients, and use
back-propagation network to testify those coefficients selected as features. At last we
select the coefficients of HL sub band and LH sub band as features. The basis of
concept in selecting those features is that the coefficients reveal the contour and the
texture of horizontal and vertical orientation. In order to reduce the rate of error
detection, Bootstrapping is used to enlarge the number of samples. And as follows a
skin model of YCbCr color space is taken as post-validation. Unlike the conventional
skin model, a model of adding lighting compensation that is presented newly is used.
Finally, the head windows of same person using object clustering are merged. And the
test has got good results.
引文
1 Sime J D. Crowd psychology and engineering. Safety Science, 1995, 21 (1):1~14.
2 Davies A C, Yin J H, Velastin S A, et al. Crowd monitoring using image
processing. IEE Electronics and Communication Engineering Journal, 1995, 7
(1):37~47.
3 Still G K. Crowd Dynamics [D]. PhD Thesis, Mathematics department, Warwick
University.August 2000.
4 Fruin J J. Crowd dynamics and the design and management of public places. In: J.
Pauls(Ed.), Int. Conf. on Building Use and Safety Technology. National Institute
of Building Sciences, Washington, DC, 1985:110~113.
5 朱志刚, 林学訚, 石定机. 数字图像处理. 电子工业出版社, 1998.
6 阮秋奇. 数字图像处理学. 电子工业出版社, 2001.
7 衣淑凤, 黄祥林, 沈兰荪. 智能化人群监控技术研究[J]. 测控技术, 2003,
22(5):22~24.
8 Velastin S A, Yin J H, Davies A C, et al. Automated measurement of crowd
density and motion using image processing. Proc. 7th IEE Int. Conf. on Road
Traffic Monitoring and Control, London, 1994:127~132.
9 Chow T W S, Yam J Y F, Cho S Y. Fast training algorithm for feedforward
neural networks: application to crowd estimation at underground stations [J].
Artificial Intelligence in Engineering 1999, 13:301~307.
10 Cho S Y, Chow T W S, Leung C T. A neural -based crowd estimation by hybrid
global learning algorithm [J]. IEEE Transactions on Systems, Man, and
Cybernetics—Part B: Cybernetics, 1999, 29 (4): 535~541.
11 Chow T W S, Cho S Y. Industrial neural vision system for underground railway
station platform surveillance [J]. Advanced Engineering Informatics, 2002
(16):73~83.
12 Paragios N, Ramesh V. A MRF-based approach for real-time subway monitoring
[J]. IEEE Computer Vision and Pattern Recognition, Hawaii, USA. ICCV'01,
2001(1):1034~1040.
13 Heitz F, Perez P, Bouthemy P. Multi-scale minimization of global energy
functions in some visual recovery problems [A]. CVGIP: Image Understanding,
1994, 59:125~134.
14 Marana A N, Velastin S A, Costa L F, et al. Automatic estimation of crowd
density using texture. Safety Science, 1998, 28(3): 165~175.
- 66 -
参考文献
15 Marana A N, Verona V V. Wavelet packet analysis for crowd density estimation
[A]. Proceedings of the IASTED International Symposia on Applied Informatics,
Innsbruck,Austria,ACTAPRESS, 2001:535~540.
16 Haralick R M. Statistical and structural approaches to texture. Proc IEEE, 1979,
67(5): 786~804.
17 Marana A N, Velastin S A, Costa L F, et al. Estimation of crowd density using
image processing. Image Processing for Security Applications (Digest No:
1997/074), IEE Colloquium on, 1997: 11/1~11/8.
18 Marana A N, Costa L F, Lotufo R A, et al. On the efficacy of texture analysis for
crowd monitoring. International Symposium on Computer Graphics, Image
Processing and Vision, 1998: 354~361.
19 Marana A N, Costa L F, Lotufo R A, et al. Estimating crowd density with
minkowski fractal dimension. IEEE International Conference on Acoustics,
Speech, and Signal Processing, 1999, 6: 3521~3524.
20 Regazzoni C S. Distributed extended Kalman filtering network for estimation and
tracking multiple objects [J], Electronic Letters, 1994,30(15):1202~1203.
21 Tesei A, Regazzoni C S. Local density evaluation and tracking of multiple objects
from complex image sequences. Industrial Electronics, Control and
Instrumentation, 1994. IECON'94, 20th International Conference on, 1994, 2:
744~748.
22 Regazzoni C S, Tesei A. Density evaluation and tracking of multiple objects from
image sequences. Image Processing, 1994. Proceedings. ICIP-94, IEEE Int. Conf.,
1994,1: 545~549.
23 Cravino F, Dellucca M, Tesei A. DEKF system for crowding estimation by a
multiple-model approach. Electronic Letters, 1994, 30(5): 390~391.
24 Schofield A J, Stonham T.J, Mehta P A. A ram based neural network approach to
people counting. Proceedings 5th. Int. Conference on Image Processing And Its
Applications, 1995: 652~656.
25 Schofield A J, Mehta P A, Stonham T J. A system for counting people in video
images using neural networks to identify the background scene. Pattern
Recognition, 1996, 29(8): 1421~1428.
26 Terada K, Yoshida D, Oe S, et al. A method of counting the passing people by
using the stereo images. Proceedings of the 1999 IEEE International Conference
on Image Processing, Japan, 1999, 338~342.
27 Oren M, Papageorgiou C, Sinha P, et al. Pedestrian detection using wavelet
templates. Computer Vision and Pattern Recognition, 1997. Proceedings, 1997
IEEE Computer Society Conference on, 1997:193~199.
28 Papageorgiou, C; Poggio, T. Trainable pedestrian detection. Image Processing,
67
北京工业大学工学硕士学位论文
1999. ICIP 99. Proceedings. 1999 International Conference on, 1999, 4:35~39.
29 Lin S F, Chen J Y, Chao H X. Estimation of number of people in crowded scenes
using perspective transformation. IEEE Transactions on Systems, Man and
Cybernetics-PartA: Systems and Humans, 2001, 31(6): 645~653.
30 Zhang L M, Lenders P. A new head detection method based on the region shield
segmentation in complex background. Proceedings of 2001 International
Symposium on Intelligent Multimedia, Video and Speech Processing, Hongkong,
2001:328~331.
31 Huang D, Chow T W S. A people counting system using a Hybrid RBF neural
network. Neural Processing Letters, 2003, 18: 97~113.
32 Mallat S.Awavelet tour of signal processing.Academic press, 1999.
33 Daubechies I. Ten lectures on wavelets. Capital City Press, Montpellier, Vermont.
34 李世雄. 小波变换及其应用. 北京:高等教育出版社, 1997.
35 程正兴. 小波分析算法与应用. 西安:西安交通大学出版社, 1998.
36 彭玉华. 小波变换与工程应用. 科学出版社, 2002.
37 崔锦泰（著）, 程正兴（译）. 小波分析导论. 西安交通大学出版社, 1995.
38 楼顺天, 施阳. 基于 MATLAB 的系统分析与设计——神经网络. 西安:西安
电子科技大学出版社, 1998.
39 黄德双. 神经网络模式识别系统理论. 北京:电子工业出版社, 1996.
40 张宏林. Visual C++数字图像模式识别技术及工程实践. 人民邮电出版社,
2003.
41 梁路宏, 艾海舟, 徐光佑等. 人脸检测研究综述. 计算机学报, 2002,
25(5):449~458.
42 Chal D, Ngan K N. Face segmentation using skin-color map in video phone
applications. IEEE Trans. Circuit System. Video Tech., 1999, 9(4):551~564.
43 康学雷, 邵凌, 张立明. 一种基于肤色和模板的人脸检测方法. 红外与毫米
波学报, 2000, 19(3): 209~214.
44 韩宏, 王鹏, 唐振民等. 彩色图像中复杂背景的多人脸检测. 南京理工大学
学报, 2001, 25(6): 561~597.
45 Habili N, Lim C C. Hand and face segmentation using motion and color cues in
digital image sequences. IEEE International Conference on Multimedia＆ Expo
2001.
46 Hua R C K, De Silva L C, Vadakkepat. Detection and tracking of faces in
real-time environments. National University of Singapore Technical Report.
47 Satoh S, Nakamura Y, Kanade T. Name-it: naming and detecting faces in news
videos. IEEE Multimedia, 1999, 6 (1):22~35.
- 68 -
参考文献
48 Soriano M, Martinkauppi B, Huovinen S. Skin detection in video under changing
illumination conditions. Proceedings of the International Conference on Pattern
Recognition, 2000.
49 Crowley J L, Berard F. Multi-model tracking of faces for video communications.
IEEE Proc. of Int. Conf. on Computer Vision and Pattern Recognition, Puerto
Rico, 1997.
50 Kapfer M, Benois P J. Detection of human faces in color image sequences with
arbitrary motions for very low bit-rate video phone coding. Pattern Recognition
Letters, 1997, 18 (14):1503~1518.
51 Sobottka K, Pitas I. A novel method for automatic face segmentation, facial
feature extraction and tracking. Signal Processing: Image Communication, 1998,
12: 263~281.
52 Kjeldsen R, Kender J. Finding skin in color images. Int. Conf. Automatic Face
and Gesture Recognition, 1996:312~317.
53 Sobottka K, Pitas I. Segmentation and tracking of faces in color images. Second
Int. Conf.Automatic Face and Gesture Recognition. 236~241.
54 Triesch J, Malsburg C V. Self-organized integration of adaptive visual cues for
face tracking. Int. Conf. Automatic Face and Gesture Recognition, Grenoble,
2000:102~107.
55 Chai D, Ngan K N. Locating facial region of a head-and-shoulders color image.
Proceedings of the Third Int. Conf. Automatic Face and Gesture Recognition,
124~129
56 Dai Y, Nakano Y. Face-texture model based on SGLD and its application in face
detection in a color scene. Pattern Recognition, 1996, 29(6):1007~1017.
57 Saber A, Tekalp A M. Frontal-view face detection and facial feature extraction
using color, shape and symmetry based cost functions. Pattern Recognition
Letters, 1998, 19: 669~680.
58 Wu H, Chen Q, Yachida M. Face detection from images using a fuzzy pattern
matching method. IEEE Trans. on Pattern Analysis and Machine Intelligence,
1999, 21(6):557~563.
59 Yang M H, Ahuja N. Detection human faces in color images. Proceedings of
IEEE Int. Conf. Images Processing, 1998, 1:127~130.
60 刘明宝, 姚鸿勋, 高文. 彩色图像的实时人脸跟踪方法. 计算机学报, 1998,
21(6)：527~532.
61 Hsu R L, Mohamed Al M, Jain A K. Face detection in color images. IEEE Trans.
on PatternAnalysis and Machine Intelligence, 2002, 24(5):696~706.
62 沈兰荪, 卓力, 田栋等. 视频编码与低速率传输. 电子工业出版社, 2001.
2 Davies A C, Yin J H, Velastin S A, et al. Crowd monitoring using image
processing. IEE Electronics and Communication Engineering Journal, 1995, 7
(1):37~47.
3 Still G K. Crowd Dynamics [D]. PhD Thesis, Mathematics department, Warwick
University.August 2000.
4 Fruin J J. Crowd dynamics and the design and management of public places. In: J.
Pauls(Ed.), Int. Conf. on Building Use and Safety Technology. National Institute
of Building Sciences, Washington, DC, 1985:110~113.
5 朱志刚, 林学訚, 石定机. 数字图像处理. 电子工业出版社, 1998.
6 阮秋奇. 数字图像处理学. 电子工业出版社, 2001.
7 衣淑凤, 黄祥林, 沈兰荪. 智能化人群监控技术研究[J]. 测控技术, 2003,
22(5):22~24.
8 Velastin S A, Yin J H, Davies A C, et al. Automated measurement of crowd
density and motion using image processing. Proc. 7th IEE Int. Conf. on Road
Traffic Monitoring and Control, London, 1994:127~132.
9 Chow T W S, Yam J Y F, Cho S Y. Fast training algorithm for feedforward
neural networks: application to crowd estimation at underground stations [J].
Artificial Intelligence in Engineering 1999, 13:301~307.
10 Cho S Y, Chow T W S, Leung C T. A neural -based crowd estimation by hybrid
global learning algorithm [J]. IEEE Transactions on Systems, Man, and
Cybernetics—Part B: Cybernetics, 1999, 29 (4): 535~541.
11 Chow T W S, Cho S Y. Industrial neural vision system for underground railway
station platform surveillance [J]. Advanced Engineering Informatics, 2002
(16):73~83.
12 Paragios N, Ramesh V. A MRF-based approach for real-time subway monitoring
[J]. IEEE Computer Vision and Pattern Recognition, Hawaii, USA. ICCV'01,
2001(1):1034~1040.
13 Heitz F, Perez P, Bouthemy P. Multi-scale minimization of global energy
functions in some visual recovery problems [A]. CVGIP: Image Understanding,
1994, 59:125~134.
14 Marana A N, Velastin S A, Costa L F, et al. Automatic estimation of crowd
density using texture. Safety Science, 1998, 28(3): 165~175.
- 66 -
参考文献
15 Marana A N, Verona V V. Wavelet packet analysis for crowd density estimation
[A]. Proceedings of the IASTED International Symposia on Applied Informatics,
Innsbruck,Austria,ACTAPRESS, 2001:535~540.
16 Haralick R M. Statistical and structural approaches to texture. Proc IEEE, 1979,
67(5): 786~804.
17 Marana A N, Velastin S A, Costa L F, et al. Estimation of crowd density using
image processing. Image Processing for Security Applications (Digest No:
1997/074), IEE Colloquium on, 1997: 11/1~11/8.
18 Marana A N, Costa L F, Lotufo R A, et al. On the efficacy of texture analysis for
crowd monitoring. International Symposium on Computer Graphics, Image
Processing and Vision, 1998: 354~361.
19 Marana A N, Costa L F, Lotufo R A, et al. Estimating crowd density with
minkowski fractal dimension. IEEE International Conference on Acoustics,
Speech, and Signal Processing, 1999, 6: 3521~3524.
20 Regazzoni C S. Distributed extended Kalman filtering network for estimation and
tracking multiple objects [J], Electronic Letters, 1994,30(15):1202~1203.
21 Tesei A, Regazzoni C S. Local density evaluation and tracking of multiple objects
from complex image sequences. Industrial Electronics, Control and
Instrumentation, 1994. IECON'94, 20th International Conference on, 1994, 2:
744~748.
22 Regazzoni C S, Tesei A. Density evaluation and tracking of multiple objects from
image sequences. Image Processing, 1994. Proceedings. ICIP-94, IEEE Int. Conf.,
1994,1: 545~549.
23 Cravino F, Dellucca M, Tesei A. DEKF system for crowding estimation by a
multiple-model approach. Electronic Letters, 1994, 30(5): 390~391.
24 Schofield A J, Stonham T.J, Mehta P A. A ram based neural network approach to
people counting. Proceedings 5th. Int. Conference on Image Processing And Its
Applications, 1995: 652~656.
25 Schofield A J, Mehta P A, Stonham T J. A system for counting people in video
images using neural networks to identify the background scene. Pattern
Recognition, 1996, 29(8): 1421~1428.
26 Terada K, Yoshida D, Oe S, et al. A method of counting the passing people by
using the stereo images. Proceedings of the 1999 IEEE International Conference
on Image Processing, Japan, 1999, 338~342.
27 Oren M, Papageorgiou C, Sinha P, et al. Pedestrian detection using wavelet
templates. Computer Vision and Pattern Recognition, 1997. Proceedings, 1997
IEEE Computer Society Conference on, 1997:193~199.
28 Papageorgiou, C; Poggio, T. Trainable pedestrian detection. Image Processing,
67
北京工业大学工学硕士学位论文
1999. ICIP 99. Proceedings. 1999 International Conference on, 1999, 4:35~39.
29 Lin S F, Chen J Y, Chao H X. Estimation of number of people in crowded scenes
using perspective transformation. IEEE Transactions on Systems, Man and
Cybernetics-PartA: Systems and Humans, 2001, 31(6): 645~653.
30 Zhang L M, Lenders P. A new head detection method based on the region shield
segmentation in complex background. Proceedings of 2001 International
Symposium on Intelligent Multimedia, Video and Speech Processing, Hongkong,
2001:328~331.
31 Huang D, Chow T W S. A people counting system using a Hybrid RBF neural
network. Neural Processing Letters, 2003, 18: 97~113.
32 Mallat S.Awavelet tour of signal processing.Academic press, 1999.
33 Daubechies I. Ten lectures on wavelets. Capital City Press, Montpellier, Vermont.
34 李世雄. 小波变换及其应用. 北京:高等教育出版社, 1997.
35 程正兴. 小波分析算法与应用. 西安:西安交通大学出版社, 1998.
36 彭玉华. 小波变换与工程应用. 科学出版社, 2002.
37 崔锦泰（著）, 程正兴（译）. 小波分析导论. 西安交通大学出版社, 1995.
38 楼顺天, 施阳. 基于 MATLAB 的系统分析与设计——神经网络. 西安:西安
电子科技大学出版社, 1998.
39 黄德双. 神经网络模式识别系统理论. 北京:电子工业出版社, 1996.
40 张宏林. Visual C++数字图像模式识别技术及工程实践. 人民邮电出版社,
2003.
41 梁路宏, 艾海舟, 徐光佑等. 人脸检测研究综述. 计算机学报, 2002,
25(5):449~458.
42 Chal D, Ngan K N. Face segmentation using skin-color map in video phone
applications. IEEE Trans. Circuit System. Video Tech., 1999, 9(4):551~564.
43 康学雷, 邵凌, 张立明. 一种基于肤色和模板的人脸检测方法. 红外与毫米
波学报, 2000, 19(3): 209~214.
44 韩宏, 王鹏, 唐振民等. 彩色图像中复杂背景的多人脸检测. 南京理工大学
学报, 2001, 25(6): 561~597.
45 Habili N, Lim C C. Hand and face segmentation using motion and color cues in
digital image sequences. IEEE International Conference on Multimedia＆ Expo
2001.
46 Hua R C K, De Silva L C, Vadakkepat. Detection and tracking of faces in
real-time environments. National University of Singapore Technical Report.
47 Satoh S, Nakamura Y, Kanade T. Name-it: naming and detecting faces in news
videos. IEEE Multimedia, 1999, 6 (1):22~35.
- 68 -
参考文献
48 Soriano M, Martinkauppi B, Huovinen S. Skin detection in video under changing
illumination conditions. Proceedings of the International Conference on Pattern
Recognition, 2000.
49 Crowley J L, Berard F. Multi-model tracking of faces for video communications.
IEEE Proc. of Int. Conf. on Computer Vision and Pattern Recognition, Puerto
Rico, 1997.
50 Kapfer M, Benois P J. Detection of human faces in color image sequences with
arbitrary motions for very low bit-rate video phone coding. Pattern Recognition
Letters, 1997, 18 (14):1503~1518.
51 Sobottka K, Pitas I. A novel method for automatic face segmentation, facial
feature extraction and tracking. Signal Processing: Image Communication, 1998,
12: 263~281.
52 Kjeldsen R, Kender J. Finding skin in color images. Int. Conf. Automatic Face
and Gesture Recognition, 1996:312~317.
53 Sobottka K, Pitas I. Segmentation and tracking of faces in color images. Second
Int. Conf.Automatic Face and Gesture Recognition. 236~241.
54 Triesch J, Malsburg C V. Self-organized integration of adaptive visual cues for
face tracking. Int. Conf. Automatic Face and Gesture Recognition, Grenoble,
2000:102~107.
55 Chai D, Ngan K N. Locating facial region of a head-and-shoulders color image.
Proceedings of the Third Int. Conf. Automatic Face and Gesture Recognition,
124~129
56 Dai Y, Nakano Y. Face-texture model based on SGLD and its application in face
detection in a color scene. Pattern Recognition, 1996, 29(6):1007~1017.
57 Saber A, Tekalp A M. Frontal-view face detection and facial feature extraction
using color, shape and symmetry based cost functions. Pattern Recognition
Letters, 1998, 19: 669~680.
58 Wu H, Chen Q, Yachida M. Face detection from images using a fuzzy pattern
matching method. IEEE Trans. on Pattern Analysis and Machine Intelligence,
1999, 21(6):557~563.
59 Yang M H, Ahuja N. Detection human faces in color images. Proceedings of
IEEE Int. Conf. Images Processing, 1998, 1:127~130.
60 刘明宝, 姚鸿勋, 高文. 彩色图像的实时人脸跟踪方法. 计算机学报, 1998,
21(6)：527~532.
61 Hsu R L, Mohamed Al M, Jain A K. Face detection in color images. IEEE Trans.
on PatternAnalysis and Machine Intelligence, 2002, 24(5):696~706.
62 沈兰荪, 卓力, 田栋等. 视频编码与低速率传输. 电子工业出版社, 2001.