基于红外技术的驾驶员脸部识别研究
|
摘要
研究结果表明:目前在夜间经常发生汽车碰撞等重大交通事故。究其原因主要是夜晚驾驶员开车时,身体非常疲劳、注意力不集中乃至入睡,导致汽车失去控制,车毁人亡。可以说,夜间驾驶员疲劳和精神分散已成为诱发恶性交通事故的主要因素之一。因此,夜晚利用汽车安全辅助驾驶技术,有效避免夜间发生道路交通事故已经日益受到人们的关注。但是,由于在夜间一般摄像机无法监控驾驶员疲劳和精神分散状态,从而造成一些业已存在的基于有可见光照前提下的人脸识别检测算法失效。也就是说,现阶段非常有必要开展如何在无光照的条件下,基于红外技术,识别监测出驾驶员开夜车时的精神状态的算法研究。在这个意义深远的研究课题里面,从监控图像中检测识别并定位出人脸,找到眼睛的位置,是最最基础、不可逾越的重要步骤,本文就是针对所获得的夜间驾驶员脸部红外图像,着力解决脸部分割与识别和眼睛识别与定位这一基础问题,展开了积极的研究,为下一步实时判断出驾驶员精神状态,避免夜间发生交通事故打下坚实的基础。
上文说到,在夜间,普通工业摄像机是无法完成采集驾驶员面部图像这一基本任务的,自然也就无法完成后续的算法研究,所以首先需要选择好适合的摄像机等图像采集设备。在本论文中,选择了市面上常见的主动红外式监控摄像机(CCD),较好的解决了现阶段图像采集问题。然后,根据采集到的主动红外图像的特点,对图像做灰度化处理,并采用中值滤波的方法为图像去噪。采用基于二维类间方差多门限分割算法进行图像分割,将图像二值化。接着利用连通成分标记法将小面积噪声及背景区域消去,利用数学形态学的方法,进一步滤除噪声,提取出人脸宽高比等特征,定位驾驶员面部。最后,根据驾驶员眼睛区域几何特征,实现驾驶员眼部定位。在本论文中,根据驾驶员脸部和眼部的特点,将脸部图像分割算法的效果对比情况和眼睛定位采用的算法原理做了较为详细的分析和理论说明。
研究结果表明本文采用的驾驶员面部检测方法能较为准确的实现驾驶员脸部的识别定位,所采用的眼部定位方法能较好的完成驾驶员眼部定位。但由于时间等原因所限,本文没有对识别出夜间驾驶员眼部睁闭状态,进而达到判断其是否为疲劳驾车,做更加深入的研究与探讨。
Nowadays statistics in many countries show that death traffic accident at night is directly or indirectly due to drivers focused their attention, caused by fatigue or sleepiness. Driver’s factors have been one of the most important causes of road accidents. Until now many research have focused on monitoring the driver’s face, eye, pupil and so on to obtain his/her face rotation and orientation, eye activities, eye blinking rate, gaze direction, finally to determine his/her fatigue or distraction state. However, Most of researchers have neglected driver’s fatigue state such as driver’s yawning and his/her distraction like conservation and talking on a cellular phone while his/her driving in the evening. Driver monitoring has been a focus of Safety Driving Assist technologies research. In Which, fatigue driving and driving spirit scattered condition monitoring system will play an important role in lowering the accident rate at night. Machine Vision based on infrared technology in real-time, accuracy, and applicability of economic and other aspects has greater advantages than other monitoring methods at night. Study on driver visual monitoring Using vehicle-mounted camera systems is the hot technologies today. Many researchers focused on tracking the driver through the face, eyes, the pupil, has been head rotation and direction eyelid movement blink frequency, driver fatigue monitoring the direction of attention or mental scattered. However, the driver Yawns while driving or driving fatigue did not receive the spirit of scattered attention in the evening, We can also detected by the driver, the driver's eyes to fatigue and mental state decentralized monitoring. Driver’s eyes detection and location technology has a direct impact on the state of the driver eye detection. According to the analysis of the state of the driver’s eyes, this paper proposes Several methods of driver’s eye detection and location, which lays a foundation for driver monitoring based on infrared technology for further study and provides reference information and support for driver monitoring technology of the integrated monitoring system.
The research of the paper includes several parts : Pre-processing of driver's face infrared images, face detection segmentation ,eyes detection and location .
1. Pre-processing algorithms of driver’s infrared images are studied. At first the images are changed into gray from true color. Second, median filtering method and average filtering method are introduced. Median filtering method is better than average filtering method by comparison. Experimental results also show that the algorithm is effective and reliable.
2. Driver's gray images normalized by similarity are segmentalized by the maximum variance of the similarity threshold segmentation method and the moment invariants algorithm. By comparison of experiment , the maximum variance of the similarity threshold segmentation method has more perfect effect than the moment invariants algorithm. Then Using Connected component labeling algorithm to locate driver’s faces. Using Projection and the relationship facial geometry to determine the regions of face in order to determine face’s location. Experimental results show that: This type of driver’s face detection and location has high reliability, real-time. It has good dynamic positioning capability, and has better adaptability for different infrared image, complex background, and the driver sitting positions. It lays a good foundation for eyes detection and monitoring.
3. When the images are segmentalized , eyes cavity and the surrounding region of the face skin has a high contrast. According to these features we analyze the characteristics of each type of image segmentation algorithm effectively. For the feature of the face image the ideal method of segmentation is the segmentation algorithm based on the character of eyes ellipse macula. So the character variance is used to confirm eyes information .In fact this method can do favor to eyes location .
4. Driver’s eyes location adopts Morphological processing algorithms to remove the noise in the light of the eyes images after segmentation. Then connected component labeling algorithm is utilized to mark areas of interest images of driver’s eyes. The results show that: the above methods could better locate the eyes under different circumstances.
All necessary software is developed using Visual C++ and Windows 2000. The software realizes various algorithm functions. The experimental results show that the algorithms have good performance and good robustness.
上文说到,在夜间,普通工业摄像机是无法完成采集驾驶员面部图像这一基本任务的,自然也就无法完成后续的算法研究,所以首先需要选择好适合的摄像机等图像采集设备。在本论文中,选择了市面上常见的主动红外式监控摄像机(CCD),较好的解决了现阶段图像采集问题。然后,根据采集到的主动红外图像的特点,对图像做灰度化处理,并采用中值滤波的方法为图像去噪。采用基于二维类间方差多门限分割算法进行图像分割,将图像二值化。接着利用连通成分标记法将小面积噪声及背景区域消去,利用数学形态学的方法,进一步滤除噪声,提取出人脸宽高比等特征,定位驾驶员面部。最后,根据驾驶员眼睛区域几何特征,实现驾驶员眼部定位。在本论文中,根据驾驶员脸部和眼部的特点,将脸部图像分割算法的效果对比情况和眼睛定位采用的算法原理做了较为详细的分析和理论说明。
研究结果表明本文采用的驾驶员面部检测方法能较为准确的实现驾驶员脸部的识别定位,所采用的眼部定位方法能较好的完成驾驶员眼部定位。但由于时间等原因所限,本文没有对识别出夜间驾驶员眼部睁闭状态,进而达到判断其是否为疲劳驾车,做更加深入的研究与探讨。
Nowadays statistics in many countries show that death traffic accident at night is directly or indirectly due to drivers focused their attention, caused by fatigue or sleepiness. Driver’s factors have been one of the most important causes of road accidents. Until now many research have focused on monitoring the driver’s face, eye, pupil and so on to obtain his/her face rotation and orientation, eye activities, eye blinking rate, gaze direction, finally to determine his/her fatigue or distraction state. However, Most of researchers have neglected driver’s fatigue state such as driver’s yawning and his/her distraction like conservation and talking on a cellular phone while his/her driving in the evening. Driver monitoring has been a focus of Safety Driving Assist technologies research. In Which, fatigue driving and driving spirit scattered condition monitoring system will play an important role in lowering the accident rate at night. Machine Vision based on infrared technology in real-time, accuracy, and applicability of economic and other aspects has greater advantages than other monitoring methods at night. Study on driver visual monitoring Using vehicle-mounted camera systems is the hot technologies today. Many researchers focused on tracking the driver through the face, eyes, the pupil, has been head rotation and direction eyelid movement blink frequency, driver fatigue monitoring the direction of attention or mental scattered. However, the driver Yawns while driving or driving fatigue did not receive the spirit of scattered attention in the evening, We can also detected by the driver, the driver's eyes to fatigue and mental state decentralized monitoring. Driver’s eyes detection and location technology has a direct impact on the state of the driver eye detection. According to the analysis of the state of the driver’s eyes, this paper proposes Several methods of driver’s eye detection and location, which lays a foundation for driver monitoring based on infrared technology for further study and provides reference information and support for driver monitoring technology of the integrated monitoring system.
The research of the paper includes several parts : Pre-processing of driver's face infrared images, face detection segmentation ,eyes detection and location .
1. Pre-processing algorithms of driver’s infrared images are studied. At first the images are changed into gray from true color. Second, median filtering method and average filtering method are introduced. Median filtering method is better than average filtering method by comparison. Experimental results also show that the algorithm is effective and reliable.
2. Driver's gray images normalized by similarity are segmentalized by the maximum variance of the similarity threshold segmentation method and the moment invariants algorithm. By comparison of experiment , the maximum variance of the similarity threshold segmentation method has more perfect effect than the moment invariants algorithm. Then Using Connected component labeling algorithm to locate driver’s faces. Using Projection and the relationship facial geometry to determine the regions of face in order to determine face’s location. Experimental results show that: This type of driver’s face detection and location has high reliability, real-time. It has good dynamic positioning capability, and has better adaptability for different infrared image, complex background, and the driver sitting positions. It lays a good foundation for eyes detection and monitoring.
3. When the images are segmentalized , eyes cavity and the surrounding region of the face skin has a high contrast. According to these features we analyze the characteristics of each type of image segmentation algorithm effectively. For the feature of the face image the ideal method of segmentation is the segmentation algorithm based on the character of eyes ellipse macula. So the character variance is used to confirm eyes information .In fact this method can do favor to eyes location .
4. Driver’s eyes location adopts Morphological processing algorithms to remove the noise in the light of the eyes images after segmentation. Then connected component labeling algorithm is utilized to mark areas of interest images of driver’s eyes. The results show that: the above methods could better locate the eyes under different circumstances.
All necessary software is developed using Visual C++ and Windows 2000. The software realizes various algorithm functions. The experimental results show that the algorithms have good performance and good robustness.
引文
[1]. 网易 http://auto.163.com/special/000816N3/baoyouliang.html
[2]. 延安交警 http://www.yajjzd.com/jwgk/ShowArticle.asp?ArticleID=183
[3]. 王武宏,孙逢春,曹琦,刘淑艳.道路交通系统驾驶行为理论与方法[J].科学出版社, 2001,8,(1):1-5
[4]. 中国嘉兴 http://www.jiaxing.gov.cn/art/2007/07/21/art_28_37652.html
[5]. N.Hernandez,D.Estevez.Driver drowsiness detection:past,present and prospective work[J].Traffic technology international,1997(6)
[6]. G . Yang and T . S . Huang . Human Face Detection in Complex Background[J].Pattern Recognition,1994,27(1):53-63
[7]. Moghaddam.B,Pentland.A.Probabilistic Visual Learning for Object Representation[C].IEEE Trans Pattern Analysis and Machine Inteligence,1997,19
[8]. J.M.Vincent,J.B.Waite,D.J.Myers.Automatic location of visual features by a system of multilayered perceptions[J],IEEE proceedings,1992,139(6)
[9]. 张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1): 32-42
[10] 0suna E,Freund R.Girosi F.Training support vector machines:An application to face detection . Proc Computer Vision and Pattern Recognition, Puerto Rico,1997,130-136
[11] Viola Paul,Jones Michael.Rapid object detection using aboost edcascade of simple features[C].Proc IEEE Conference on Computer Vision and Pattern Recognition,Kauai,Hawaii,USA,2001.
[12] 梁路宏,艾海舟,何克忠等.基于多模板匹配的单人脸检测[J].中国图象图形学报,1999,4A(10):823-830
[13] 刘翼光,沈理.利用Hausdroff距离人脸图像定位算法[J].计算机研究与发展,2001,38 (4):475-481
[14] A.Yuile,P.Halinan,and D.Cohen.Feature Extraction from Faces Using Deformable Templates.Computer Vision,1992,8(2):99-111
[15] Kin-Man Lam,Hong Yan,An analytic-to-holistic approach for facerecognition based on a single frontal view,IEEE Trans.Pattern Anal Machine Intelligent,1998,20:673-686
[16] 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.
[17] 李江.红外图像人脸识别方法研究.长沙:国防科学技术大学博士学位论文,2005.
[18] Zhu Z.,Ji Q. Real-Time and non-intrusive driver fatigue monitoring[C]. Proceedings of the 7th International IEEE Conference on Intelligent Transportation System.Washington,USA,2004:657-662
[19] Copilot.http://www.ri.cmu.edu/projects/project_435.html.
[20] Smart Eye.http://www.smarteye.se/.
[21] ITS-ASVMitsubishiASV2. http://www.mitsubishi-motors.co.jp/docs4/asv2/its/index.html.
[22] 吴林托,李芳,阙步军,沈翀.基于红外LED的人眼快速定位与跟踪的研究.光学仪器,2006,Vol.28,No.1
[23] 中国嘉兴 http://www.jiaxing.gov.cn/art/2007/07/21/art_28_37652.html
[24]. 郭克友.驾驶员疲劳状态视觉监测技术的研究[D].长春:吉林大学博士学位论文,2003.
[25]. 童兵亮.基于嘴部状态的疲劳驾驶和精神分散状态监测方法研究[D].长春:吉林大学硕士学位论文,2004
[26]. 张明恒. 基于面部朝向的驾驶员精神分散检测方法研究[D]. 长春:吉林大学博士学位论文,2007.
[27]. 孙萱. 基于单目视觉的驾驶员嘴部分割与定位方法研究[D] . 长春:吉林大学硕士学位论文,2007.
[28]. 邸巍. 驾驶员头部检测算法研究[D]. 长春:吉林大学硕士学位论文,2007.
[29]. 付娜.红外图像的采集、增强与分割处理研究.大连:大连理工大学硕士学位论文,2006
[30]. 杨淑莹.VC++图像处理程序设计(第二版).北京:清华大学出版社、北京交通大学出版,2005
[31]. R. Kenneth.Digital Image Processing (影印版)[M].北京:清华大学出版社,1998
[32]. 赵荣椿.数字图像处理导论[M].西安:西北工业大学出版社,1996
[33]. 容观澳.计算机图像处理[M].北京:清华大学出版社,2000
[34]. 阮秋艺.数字图像处理学[M].北京:电子工业出版社,2001
[35]. 谷口庆治[日].数字图像处理-基础篇[M].科学出版社,2002
[36]. 吴健康.数字图像分析[M].北京:人民邮电出版社,1989:25-26
[37]. Yang Hui.Image Segmentation by Histogram Thresholding Using Fuzzy Sets[J].Journal of Liaoning University(Natural Sciences Edition, 2006,33(2): 135-137
[38]. 王思贤,刘宗义,梅建新.低对比度图像目标分割的研究[J].武汉:武汉大学学报(自然科学版),第 46 卷第 5 期,2000 年 10 月,641-644
[39]. 王荣本,顾柏园,郭烈,余天洪.基于二维类间方差多门限阈值分割的石块识别方法.:计算机工程与应用,Vol.42,No.28,2006 年 9 月,230-232
[40]. 龚坚,李立源,陈维南.二维熵阈值分割的快速算法[J].东南大学学报,1996,26(4),31-36
[41]. 景晓军,蔡安妮.一种基于二维最大类间方差的图像分割算法[J].通信学报,2001,(4),71-76
[42]. 芦蓉,沈毅.一种改进的二维直方图的图像分割方法[J].系统工程与电子技术,2004,(10),1487-1489
[43]. 郭克友.驾驶员疲劳状态视觉监测技术的研究[D].长春:吉林大学交通学院,47-49
[44]. 于兴玲. 驾驶员眼睛检测与定位方法研究 . 西安:西安建筑科技大学硕士学位论文,2007.
[45]. 冈萨雷斯等著,阮秋琦等译.数字图像处理[M].北京:电子工业出版社,2006,04,255-263
[46]. 孙萱. 基于单目视觉的驾驶员嘴部分割与定位方法研究[D] . 长春:吉林大学硕士学位论文,2007.
[47]. 李峰,曾超,徐向东.驾驶防瞌睡装置中人眼快速定位方法研究.光学仪器,Vol.24,No.4-5,2002 年 8 月,70-72
[48]. 李璇,罗敏,施荣华,李丽.复杂背景下基于肤色和几何特征的人眼定位.计算机测量与控制,Vol.13,No.3,2002 年 8 月,281-283
[49]. 艾海舟,梁路宏等.基于肤色和模板的人脸检测.软件学报,Vol.12,No.12,2001 年 12 月,1784-1792
[50]. 陈艳琴. 关于司机疲劳检测的人眼检测与跟踪研究 . 长沙:中南大学硕士学位论文,2004.
[51]. 于威威,滕晓龙,刘重庆.一种快速准确的人眼定位方法.光电子? 激光,Vol.16,No.4,2005 年 4 月,479-483
[52]. 王荣本,郭克友,储江伟,初秀民.适用驾驶员疲劳状态检测的人眼定位方法研究.公路交通科技,Vol.20,No.5,2003 年 10 月,111-114
[53]. 胡恬.利用几何分析法和 BP 神经网络进行人脸识别的研究.计算机工程与设计,Vol.23,No.9,2002 年 9 月,18-21
[54]. Haralick,Shapiro.Computer and Robot[J].Addision-Wesley,1992,1:59-83, 639-658
[55]. 边肇祺等编著.模式识别.北京:清华大学出版社,1988,06,272-274
[2]. 延安交警 http://www.yajjzd.com/jwgk/ShowArticle.asp?ArticleID=183
[3]. 王武宏,孙逢春,曹琦,刘淑艳.道路交通系统驾驶行为理论与方法[J].科学出版社, 2001,8,(1):1-5
[4]. 中国嘉兴 http://www.jiaxing.gov.cn/art/2007/07/21/art_28_37652.html
[5]. N.Hernandez,D.Estevez.Driver drowsiness detection:past,present and prospective work[J].Traffic technology international,1997(6)
[6]. G . Yang and T . S . Huang . Human Face Detection in Complex Background[J].Pattern Recognition,1994,27(1):53-63
[7]. Moghaddam.B,Pentland.A.Probabilistic Visual Learning for Object Representation[C].IEEE Trans Pattern Analysis and Machine Inteligence,1997,19
[8]. J.M.Vincent,J.B.Waite,D.J.Myers.Automatic location of visual features by a system of multilayered perceptions[J],IEEE proceedings,1992,139(6)
[9]. 张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1): 32-42
[10] 0suna E,Freund R.Girosi F.Training support vector machines:An application to face detection . Proc Computer Vision and Pattern Recognition, Puerto Rico,1997,130-136
[11] Viola Paul,Jones Michael.Rapid object detection using aboost edcascade of simple features[C].Proc IEEE Conference on Computer Vision and Pattern Recognition,Kauai,Hawaii,USA,2001.
[12] 梁路宏,艾海舟,何克忠等.基于多模板匹配的单人脸检测[J].中国图象图形学报,1999,4A(10):823-830
[13] 刘翼光,沈理.利用Hausdroff距离人脸图像定位算法[J].计算机研究与发展,2001,38 (4):475-481
[14] A.Yuile,P.Halinan,and D.Cohen.Feature Extraction from Faces Using Deformable Templates.Computer Vision,1992,8(2):99-111
[15] Kin-Man Lam,Hong Yan,An analytic-to-holistic approach for facerecognition based on a single frontal view,IEEE Trans.Pattern Anal Machine Intelligent,1998,20:673-686
[16] 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.
[17] 李江.红外图像人脸识别方法研究.长沙:国防科学技术大学博士学位论文,2005.
[18] Zhu Z.,Ji Q. Real-Time and non-intrusive driver fatigue monitoring[C]. Proceedings of the 7th International IEEE Conference on Intelligent Transportation System.Washington,USA,2004:657-662
[19] Copilot.http://www.ri.cmu.edu/projects/project_435.html.
[20] Smart Eye.http://www.smarteye.se/.
[21] ITS-ASVMitsubishiASV2. http://www.mitsubishi-motors.co.jp/docs4/asv2/its/index.html.
[22] 吴林托,李芳,阙步军,沈翀.基于红外LED的人眼快速定位与跟踪的研究.光学仪器,2006,Vol.28,No.1
[23] 中国嘉兴 http://www.jiaxing.gov.cn/art/2007/07/21/art_28_37652.html
[24]. 郭克友.驾驶员疲劳状态视觉监测技术的研究[D].长春:吉林大学博士学位论文,2003.
[25]. 童兵亮.基于嘴部状态的疲劳驾驶和精神分散状态监测方法研究[D].长春:吉林大学硕士学位论文,2004
[26]. 张明恒. 基于面部朝向的驾驶员精神分散检测方法研究[D]. 长春:吉林大学博士学位论文,2007.
[27]. 孙萱. 基于单目视觉的驾驶员嘴部分割与定位方法研究[D] . 长春:吉林大学硕士学位论文,2007.
[28]. 邸巍. 驾驶员头部检测算法研究[D]. 长春:吉林大学硕士学位论文,2007.
[29]. 付娜.红外图像的采集、增强与分割处理研究.大连:大连理工大学硕士学位论文,2006
[30]. 杨淑莹.VC++图像处理程序设计(第二版).北京:清华大学出版社、北京交通大学出版,2005
[31]. R. Kenneth.Digital Image Processing (影印版)[M].北京:清华大学出版社,1998
[32]. 赵荣椿.数字图像处理导论[M].西安:西北工业大学出版社,1996
[33]. 容观澳.计算机图像处理[M].北京:清华大学出版社,2000
[34]. 阮秋艺.数字图像处理学[M].北京:电子工业出版社,2001
[35]. 谷口庆治[日].数字图像处理-基础篇[M].科学出版社,2002
[36]. 吴健康.数字图像分析[M].北京:人民邮电出版社,1989:25-26
[37]. Yang Hui.Image Segmentation by Histogram Thresholding Using Fuzzy Sets[J].Journal of Liaoning University(Natural Sciences Edition, 2006,33(2): 135-137
[38]. 王思贤,刘宗义,梅建新.低对比度图像目标分割的研究[J].武汉:武汉大学学报(自然科学版),第 46 卷第 5 期,2000 年 10 月,641-644
[39]. 王荣本,顾柏园,郭烈,余天洪.基于二维类间方差多门限阈值分割的石块识别方法.:计算机工程与应用,Vol.42,No.28,2006 年 9 月,230-232
[40]. 龚坚,李立源,陈维南.二维熵阈值分割的快速算法[J].东南大学学报,1996,26(4),31-36
[41]. 景晓军,蔡安妮.一种基于二维最大类间方差的图像分割算法[J].通信学报,2001,(4),71-76
[42]. 芦蓉,沈毅.一种改进的二维直方图的图像分割方法[J].系统工程与电子技术,2004,(10),1487-1489
[43]. 郭克友.驾驶员疲劳状态视觉监测技术的研究[D].长春:吉林大学交通学院,47-49
[44]. 于兴玲. 驾驶员眼睛检测与定位方法研究 . 西安:西安建筑科技大学硕士学位论文,2007.
[45]. 冈萨雷斯等著,阮秋琦等译.数字图像处理[M].北京:电子工业出版社,2006,04,255-263
[46]. 孙萱. 基于单目视觉的驾驶员嘴部分割与定位方法研究[D] . 长春:吉林大学硕士学位论文,2007.
[47]. 李峰,曾超,徐向东.驾驶防瞌睡装置中人眼快速定位方法研究.光学仪器,Vol.24,No.4-5,2002 年 8 月,70-72
[48]. 李璇,罗敏,施荣华,李丽.复杂背景下基于肤色和几何特征的人眼定位.计算机测量与控制,Vol.13,No.3,2002 年 8 月,281-283
[49]. 艾海舟,梁路宏等.基于肤色和模板的人脸检测.软件学报,Vol.12,No.12,2001 年 12 月,1784-1792
[50]. 陈艳琴. 关于司机疲劳检测的人眼检测与跟踪研究 . 长沙:中南大学硕士学位论文,2004.
[51]. 于威威,滕晓龙,刘重庆.一种快速准确的人眼定位方法.光电子? 激光,Vol.16,No.4,2005 年 4 月,479-483
[52]. 王荣本,郭克友,储江伟,初秀民.适用驾驶员疲劳状态检测的人眼定位方法研究.公路交通科技,Vol.20,No.5,2003 年 10 月,111-114
[53]. 胡恬.利用几何分析法和 BP 神经网络进行人脸识别的研究.计算机工程与设计,Vol.23,No.9,2002 年 9 月,18-21
[54]. Haralick,Shapiro.Computer and Robot[J].Addision-Wesley,1992,1:59-83, 639-658
[55]. 边肇祺等编著.模式识别.北京:清华大学出版社,1988,06,272-274
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |