基于人脸识别技术的睡意监测系统研究
|
摘要
人脸识别与检测技术是利用计算机进行人脸图像分析，从中提取有效的识别信息，用来辨别身份或判识特定状态的一门技术。随着计算机技术的迅速发展以及现实生活的需要，人脸识别技术已经应用到许多领域中，如身份证件鉴别等。本文主要研究将人脸识别与检测技术应用于人脸的睡意监测，根据监测结果，及时给出瞌睡状态警示，降低由此引发的诸如交通事故、特殊部门监控事故等发生概率。
论文首先介绍了人脸识别技术的研究内容以及现状，指出了影响人脸识别技术应用的三大难题。接着详细阐述了睡意监测系统的研究背景和现实意义，介绍了这方面的研究现状和发展水平，并对系统进行了可行性分析和需求分析。
基于已有的研究基础，论文提出了一种新的研究思路，通过人脸识别技术实现。首先提出睡意监测系统的组成结构，对经过预处理的图像应用基于肤色模型和几何特征匹配的方法实现人脸检测与定位，利用人脸几何模型实现眼睛的定位和开合程度的计算，将计算结果与预先设定的阈值比较，判识眼睛的开／合状态。实验表明上述方法能够比较有效的实现人脸检测、眼睛定位和眼睛开／合状态的判定。接着论文提出了一种新的睡意判定准则，即通过对一定时间间隔内采集的人脸图像中眼睛开／合状态次数的统计数判定睡意。论文详细论述了应用数字图像处理理论实现系统的各种技术以及实现过程。
The technology of face recognition and detection is a technology that uses the computer to analyse the image and discriminate identity or recognize status from the worked image. With the rapid development of computer technology , many various areas have used this technology, such as entrance control in buildings; in the prominent field of criminal investigation; access control for computers in general of for automatic teller machines in particular. This paper tries to apply the technology of face recognition in sleepiness detection and to supply technical hitch such as traffic through recognizing sleepiness status.
The paper introduces the study of technology of face recognition and describes three difficult problem of application. Next we present the research background of sleepiness detection system.
Based on the research we have reached, this paper offers a new research method and sleepiness decision criteria. First explains the structure of the system, then uses the method based the skin color model and geometric feather match to achieve the face detection and location. Next achieve the eye location and calculate the open/close. The paper presents a new criteria of sleepiness decision based on the count of frequency of eye open/close.
At last the paper describes the procedure of applying the digital image process theory.
论文首先介绍了人脸识别技术的研究内容以及现状，指出了影响人脸识别技术应用的三大难题。接着详细阐述了睡意监测系统的研究背景和现实意义，介绍了这方面的研究现状和发展水平，并对系统进行了可行性分析和需求分析。
基于已有的研究基础，论文提出了一种新的研究思路，通过人脸识别技术实现。首先提出睡意监测系统的组成结构，对经过预处理的图像应用基于肤色模型和几何特征匹配的方法实现人脸检测与定位，利用人脸几何模型实现眼睛的定位和开合程度的计算，将计算结果与预先设定的阈值比较，判识眼睛的开／合状态。实验表明上述方法能够比较有效的实现人脸检测、眼睛定位和眼睛开／合状态的判定。接着论文提出了一种新的睡意判定准则，即通过对一定时间间隔内采集的人脸图像中眼睛开／合状态次数的统计数判定睡意。论文详细论述了应用数字图像处理理论实现系统的各种技术以及实现过程。
The technology of face recognition and detection is a technology that uses the computer to analyse the image and discriminate identity or recognize status from the worked image. With the rapid development of computer technology , many various areas have used this technology, such as entrance control in buildings; in the prominent field of criminal investigation; access control for computers in general of for automatic teller machines in particular. This paper tries to apply the technology of face recognition in sleepiness detection and to supply technical hitch such as traffic through recognizing sleepiness status.
The paper introduces the study of technology of face recognition and describes three difficult problem of application. Next we present the research background of sleepiness detection system.
Based on the research we have reached, this paper offers a new research method and sleepiness decision criteria. First explains the structure of the system, then uses the method based the skin color model and geometric feather match to achieve the face detection and location. Next achieve the eye location and calculate the open/close. The paper presents a new criteria of sleepiness decision based on the count of frequency of eye open/close.
At last the paper describes the procedure of applying the digital image process theory.
引文
[1] 李刚，高政．人脸检测理论研究进展．计算机与现代化．2003年第3期．
[2] Xiaoguang Lu. Image Analysis for Face Recognition, Dept. of Computer Science&Engineering Michigan State University, East Lansing,MI,48824
[3] Thomas Fromherz,peter Stucki,Matin Bichsel. A Survey of Face Recognition.
[4] 李刚，高政．人脸检测技术研究与发展．计算机与现代化．2000年第4期．
[5] 张翠平等．人脸识别技术综述．中国图像图形学报．2000年11月第11期．
[6] Fridulv Sagberg. Road accidents caused by drivers falling asleep. Accident Analysis and prevention 31 (1999) 639-649
[7] Alpo Varri,Kari Hirvonen, Nonlinear eye movement detection method for drowsiness studies, international Journal of Bio-Medical Computing 43(1996)227-242
[8] Hiroshi Ueno, Development of Drowsiness Detection System, 1994IEEE
[9] Detection of the open/closed state of eyes based on analysis of relation between eye and eyebrow images in input face images, USA Patent
[10] 贾永红．计算机图像处理与分析．武汉大学出版社．2002年9月
[11] 何斌等．Visual C++数字图像处理．人民邮电出版社．2002年12月
[12] 陈纯．计算机图像处理技术与算法．清华大学出版社．2003年7月
[13] 周长发．精通Visual C++图像编程．电子工业出版社．2000年1月
[14] 张宏林．数字图像模式识别技术及工程实践．人民邮电出版社．2003．2
[15] 张兆礼等．现代图像处理技术及Matlab实现．人民邮电出版社．2001．11
[16] 谷口庆治．数字图像处理．科学出版社．2002年5月
[17] 周金萍．Matlab6.5图形图像处理与应用实例．科学出版社．2003年8月
[18] 韩海．在(r,g)和(Cr,Cb)彩色空间上进行肤色检测．计算机与现代化．2003．1
[19] 易丛琴等．基于肤色分割的彩色图像的人脸检测．贵州工业大学学报
[20] 韩锦成等．基于差值图像及子波变换的人脸检测方法．上海交通大学学报．第33卷第11期．1999年11月
[21] 袁景和，常胜江等．一种基于肤色和几何特征的人面部识别方法．光电子激光．第13卷第4期．2002年4月
[22] Yang J,Lu W,Waibe A.Shin-color modeling and adaptation
[R].Pittsburgh:CMU-CS, 1997.97-146.
[23] 艾海舟等，基于肤色和模板的人脸检测，软件学报 Vol．12，No．12 2000．
[24] Paul Smith,Mubarak Shah, Monitoring Head/Eye Motion for Driver Alertness One Camera, 2000IEEE
[25] Weimin Huang,Qibin Sun, A Robust Approach to Face and Eye Detection From Image With Cluttered Background
[26] Weimin Huang etc., Face Detection and Precise Eyes Location, 2000IEEE
[27] Claudio A.Perez,, Face and eye Tracking algorithm based on digital image processing, 2001IEEE
[28] Wang Tao等. A color based detection system using multiple templates. Journal of Zhejiang University Science V.4.No.2,P162-165,Mar.-Apr.,2003.
[29] 王光辉等．人脸识别中的眼睛定位．信号处理．第十五卷增刊．1999年12月．
[30] Shi-Hong Jeng, Hong Yuan Mark Liao, Chin Chuan Han, Ming Yang Chem and Yao Tsorng Liu, Facial feature detection using geometrical face model: an efficient approach, Pattern Recognition 31 (3), 273-282 (1998).
[31] Takehiro Ito,Shinji Mita, Kazuhiro Kozuka, The IEEE 5th International Conference on Intelligent Transportation System 3-6 September 2002,Singpore, Driver Blink Measurement by the motion Picture Processing and its Application to Drowsiness Detection
[32] Yoo-jin Seo, Changes in sleep patterns during simulated heliox saturation dive at 16,19,and 24 ATA, international Journal of Industrial Ergonomics 28(2001)203-218
[33] W. W. Boles, A Security system based on human iris identification using wavelet tranform, Engineering Applications of Artificial Intelligence 11 (1998)75-85
[34] C.Colombo Prototype of a vision-based gaze-driven man-machine interface, 1995IEEE
[35] Takchito Hayami, Detecting Drowsiness while Driving by Measuring Eye Movement-A Pilot Study, 2002IEEE
[36] Richard Grace,A Drowsy Driver Detection System For Heavy Vehicles, 1998IEEE
[37] Philip W. Kithil, Development of Driver Alertness Detection System Using Overhead Capacitive Sensor Array
[38] Kenji Ogawa Mitsuo Shimotani, A Drowsiness Detection System
[39] Rainer Herpers, Context Based Detection of Keypoints and Features in Eye Regions, 1996IEEE
[40] Erik Hjelmas, Boon Kee Low Face Detection: A Survey, Computer Vision and Image Understangding 83,236-274 (2001)
[41] Tsuyoshi Kawaguchi,Mohamed Rizon, Iris detection using intensity and edge information,: Pattern Recognition 36(2003)549-562
[42] Albert Kircher,Marcus Uddman,Jesper Sandin, Vehicle control and drowsiness
[43] Method and apparatus for uniquely identifying individuals by particular physical characteristics and security system utilizing the same, USA Patent
[44] System and Method For Measuring And Quantitating Facial Movement, USA Patent
[45] Apparatus for Identification of Individuals, USA Patent
[46] Eye Position Detecting system and Method Therefor, USA Patent
[47] Scott Stillman,,Q Alex Zhao,Xin Zhong.The Smart Room-Final Report-Fall 1997EB/OL].http://www.cc.gatech.edu/classes/cs8113g-97-fall/projects/smartspace/final.html,2002-11-04.
[48] Ramesh,Kasturi R, Schunck B.Machine Vision [M].New York:McGraw Hill,1995.31-51.
[49] Shi-Hong Jeng, Hong Yuan Mark Liao, Chin Chuan Han, Ming Yang Chern and Yao Tsomg Liu, Facial feature detection using geometrical face model: an efficient approach, Pattern Recognition 31 (3), 273-282 (1998)
[50] 陈桂明等．应用MatLab语言处理数字信号与数字图像．科学出版社．2000．1
[2] Xiaoguang Lu. Image Analysis for Face Recognition, Dept. of Computer Science&Engineering Michigan State University, East Lansing,MI,48824
[3] Thomas Fromherz,peter Stucki,Matin Bichsel. A Survey of Face Recognition.
[4] 李刚，高政．人脸检测技术研究与发展．计算机与现代化．2000年第4期．
[5] 张翠平等．人脸识别技术综述．中国图像图形学报．2000年11月第11期．
[6] Fridulv Sagberg. Road accidents caused by drivers falling asleep. Accident Analysis and prevention 31 (1999) 639-649
[7] Alpo Varri,Kari Hirvonen, Nonlinear eye movement detection method for drowsiness studies, international Journal of Bio-Medical Computing 43(1996)227-242
[8] Hiroshi Ueno, Development of Drowsiness Detection System, 1994IEEE
[9] Detection of the open/closed state of eyes based on analysis of relation between eye and eyebrow images in input face images, USA Patent
[10] 贾永红．计算机图像处理与分析．武汉大学出版社．2002年9月
[11] 何斌等．Visual C++数字图像处理．人民邮电出版社．2002年12月
[12] 陈纯．计算机图像处理技术与算法．清华大学出版社．2003年7月
[13] 周长发．精通Visual C++图像编程．电子工业出版社．2000年1月
[14] 张宏林．数字图像模式识别技术及工程实践．人民邮电出版社．2003．2
[15] 张兆礼等．现代图像处理技术及Matlab实现．人民邮电出版社．2001．11
[16] 谷口庆治．数字图像处理．科学出版社．2002年5月
[17] 周金萍．Matlab6.5图形图像处理与应用实例．科学出版社．2003年8月
[18] 韩海．在(r,g)和(Cr,Cb)彩色空间上进行肤色检测．计算机与现代化．2003．1
[19] 易丛琴等．基于肤色分割的彩色图像的人脸检测．贵州工业大学学报
[20] 韩锦成等．基于差值图像及子波变换的人脸检测方法．上海交通大学学报．第33卷第11期．1999年11月
[21] 袁景和，常胜江等．一种基于肤色和几何特征的人面部识别方法．光电子激光．第13卷第4期．2002年4月
[22] Yang J,Lu W,Waibe A.Shin-color modeling and adaptation
[R].Pittsburgh:CMU-CS, 1997.97-146.
[23] 艾海舟等，基于肤色和模板的人脸检测，软件学报 Vol．12，No．12 2000．
[24] Paul Smith,Mubarak Shah, Monitoring Head/Eye Motion for Driver Alertness One Camera, 2000IEEE
[25] Weimin Huang,Qibin Sun, A Robust Approach to Face and Eye Detection From Image With Cluttered Background
[26] Weimin Huang etc., Face Detection and Precise Eyes Location, 2000IEEE
[27] Claudio A.Perez,, Face and eye Tracking algorithm based on digital image processing, 2001IEEE
[28] Wang Tao等. A color based detection system using multiple templates. Journal of Zhejiang University Science V.4.No.2,P162-165,Mar.-Apr.,2003.
[29] 王光辉等．人脸识别中的眼睛定位．信号处理．第十五卷增刊．1999年12月．
[30] Shi-Hong Jeng, Hong Yuan Mark Liao, Chin Chuan Han, Ming Yang Chem and Yao Tsorng Liu, Facial feature detection using geometrical face model: an efficient approach, Pattern Recognition 31 (3), 273-282 (1998).
[31] Takehiro Ito,Shinji Mita, Kazuhiro Kozuka, The IEEE 5th International Conference on Intelligent Transportation System 3-6 September 2002,Singpore, Driver Blink Measurement by the motion Picture Processing and its Application to Drowsiness Detection
[32] Yoo-jin Seo, Changes in sleep patterns during simulated heliox saturation dive at 16,19,and 24 ATA, international Journal of Industrial Ergonomics 28(2001)203-218
[33] W. W. Boles, A Security system based on human iris identification using wavelet tranform, Engineering Applications of Artificial Intelligence 11 (1998)75-85
[34] C.Colombo Prototype of a vision-based gaze-driven man-machine interface, 1995IEEE
[35] Takchito Hayami, Detecting Drowsiness while Driving by Measuring Eye Movement-A Pilot Study, 2002IEEE
[36] Richard Grace,A Drowsy Driver Detection System For Heavy Vehicles, 1998IEEE
[37] Philip W. Kithil, Development of Driver Alertness Detection System Using Overhead Capacitive Sensor Array
[38] Kenji Ogawa Mitsuo Shimotani, A Drowsiness Detection System
[39] Rainer Herpers, Context Based Detection of Keypoints and Features in Eye Regions, 1996IEEE
[40] Erik Hjelmas, Boon Kee Low Face Detection: A Survey, Computer Vision and Image Understangding 83,236-274 (2001)
[41] Tsuyoshi Kawaguchi,Mohamed Rizon, Iris detection using intensity and edge information,: Pattern Recognition 36(2003)549-562
[42] Albert Kircher,Marcus Uddman,Jesper Sandin, Vehicle control and drowsiness
[43] Method and apparatus for uniquely identifying individuals by particular physical characteristics and security system utilizing the same, USA Patent
[44] System and Method For Measuring And Quantitating Facial Movement, USA Patent
[45] Apparatus for Identification of Individuals, USA Patent
[46] Eye Position Detecting system and Method Therefor, USA Patent
[47] Scott Stillman,,Q Alex Zhao,Xin Zhong.The Smart Room-Final Report-Fall 1997EB/OL].http://www.cc.gatech.edu/classes/cs8113g-97-fall/projects/smartspace/final.html,2002-11-04.
[48] Ramesh,Kasturi R, Schunck B.Machine Vision [M].New York:McGraw Hill,1995.31-51.
[49] Shi-Hong Jeng, Hong Yuan Mark Liao, Chin Chuan Han, Ming Yang Chern and Yao Tsomg Liu, Facial feature detection using geometrical face model: an efficient approach, Pattern Recognition 31 (3), 273-282 (1998)
[50] 陈桂明等．应用MatLab语言处理数字信号与数字图像．科学出版社．2000．1