[1]李玉文,周家锐,沈琳琳.基于DM6446平台的实时人眼检测系统[J].深圳大学学报理工版,2009,26(4):420-424.
 LI Yu-wen,ZHOU Jia-rui,and SHEN Lin-lin.Real time eye detection system based on DM6446[J].Journal of Shenzhen University Science and Engineering,2009,26(4):420-424.
点击复制

基于DM6446平台的实时人眼检测系统()
分享到:

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

卷:
第26卷
期数:
2009年4期
页码:
420-424
栏目:
光电与信息工程
出版日期:
2009-10-31

文章信息/Info

Title:
Real time eye detection system based on DM6446
文章编号:
1000-2618(2009)04-0420-05
作者:
李玉文1周家锐2沈琳琳2
1)深圳信息职业技术学院,深圳 518029;
2)深圳大学计算机与软件学院,深圳 518060
Author(s):
LI Yu-wen1ZHOU Jia-rui2and SHEN Lin-lin2
1)Shenzhen Institute of Information Technology,Shenzhen 518029,P.R.China
2)College of Computer and Software Engineering,Shenzhen University,Shenzhen 518060,P.R.China
关键词:
类Haar特征人眼检测系统DM6446人脸识别系统
Keywords:
Haar-like featureeye detection systemDM6446face recognition system
分类号:
TP 273.5
文献标志码:
A
摘要:
基于高性能数字多媒体处理芯片TI TMS320DM6446的类Haar特征人眼检测算法.通过将人眼检测算法封装为算法包并进行优化,实现基于DM6446平台的实时人眼检测系统.封装后的算法包置于DSP端供远程调用.ARM端的应用程序负责从摄像头采集人脸图像,并将结果输出到显示器.人眼检测算法包也被应用于人脸识别系统中.该算法具有搜索速度快、检测率高等优点,适合在便携式平台上实现.实验结果表明,该实时人眼检测系统能在占用较少资源的情况下能有效检测并定位眼睛.
Abstract:
A Haar-like features based eye detection algorithm was introduced in this paper. With its fast searching speed and high detection rate, the algorithm fits to be implemented on portable platform. TI TMS320DM6446 is a high performance digital multimedia processing chip provided by Texas Instruments Corporation. With the eye detection algorithm packed into codec, an optimized real time eye detection system was implemented on DM6446 platform. The detection algorithm codec was loaded into the DSP-side for remote call. Application on the ARM-side captured face images from camera and output detection results to computer monitor. The implemented eye detection codec was also employed in a face recognition system. Experimental results demonstrate that the real time eye detection system on DM6446 can search and locate eyes effectively with limited chip resources occupied.

参考文献/References:

[1]董文会,曲培树,吴晓娟,等.复杂背景下多姿态人脸图像中的人眼检测[J].山东大学学报工学版,2006,36(3):18-25.
[2]侯贵龙,张高伟.集成人眼检测安全预防的行驶记录仪系统设计[J].电子技术,2008,6:40-42.
[3]LIN Dao-tong,YANG Chen-ming.基于脸圆拟合和黑像素滤波的实时眼睛检测[C]//2004 IEEE多媒体与展览国际会议论文集.台北:IEEE出版社,2004,2:1167-1170(英文版).
[4]LU Hu-chuan,ZHANG Wei,YANG De-li.基于矩形特征和像素模式细节的眼睛检测[C]//2007智能信号处理与通信国际研讨会论文集.厦门:IEEE出版社,2007:746-749(英文版).
[5]ZHANG Guang-yuan,CHEN Bo,FENG Rui-jia,等.基于使用胡氏不变矩支持向量机的实时司机眼睛检测[C]//第7届机器学习与神经机械学国际会议论文集.厦门:IEEE出版社,2008:2999-3004(英文版).
[6]Viola P,Jones M.强健的实时物体检测[C]//2001 IEEE统计与计算机视觉理论研讨会论文集.温哥华:IEEE出版社,2001:137-154(英文版).
[7]Lienhart R,Maydt J.用于快速物体检测的扩展Haar特征集[C]//2002图像处理会议论文集.纽约:IEEE出版社,2002:900-903(英文版).
[8]Sim T,Baker S,Bsat M.卡内基-梅隆大学姿势、光照与表情数据库[J].IEEE模式分析与机器学习通讯,2003,25(12):1615-1618(英文版).
[9]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(英文版).
[10]SHEN Lin-lin,BAI Li.使用互提升学习选择人脸识别Gabor特征[J].模式识别通讯,2006,27(15):1758-1767(英文版).

[1]DONG Wen-hui,QU Pei-shu,WU Xiao-juan,et al.Eye detection for multi-pose face image in complex background[J].Journal of Shandong University(Engineering Science),2006,36(3):18-25(in Chinese).
[2]HOU Gui-long,ZHANG Gao-wei.The design of vehicle data recorder integration with eyes detection[J].Electronic Technology,2008,6:40-42(in Chinese).
[3]LIN Dao-tong,YANG Chen-ming.Real-time eye detection using face circle fitting and dark-pixel filtering[C]//2004 IEEE International Conference on Multimedia and Expo.Taipei:IEEE Press,2004:1167-1170.
[4]LU Hu-chuan,ZHANG Wei,YANG De-li.Eye detection based on rectangle features and pixel-pattern-based texture features[C]// 2007 International Symposium on Intelligent Signal Processing and Communication Systems.Xiamen:IEEE Press,2007:746-749.
[5]ZHANG Guang-yuan,CHEN Bo,FENG Rui-jia,et al.Real-time driver eye detection method using support vector machine with Hu invariant moments[C]//The 7th International Conference on Machine Learning and Cybernetics.Xiamen:IEEE Press,2008:2999-3004.
[6]Viola P,Jones M.Robust real-time object detection[C]//2001 IEEE Workshop on Statistical and Computational Theories of Vision.Vancouver:IEEE Press,2001:137-154.
[7]Lienhart R,Maydt J.An extended set of haar-like features for rapid object detection[C]//2002 International Conference on Image Processing.NY:IEEE Press,2002:900-903.
[8]Sim T,Baker S,Bsat M.The CMU pose,illumination,and expression database[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2003,25(12):1615-1618..
[9]SHEN Lin-lin,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.
[10]SHEN Lin-lin,BAI Li.MutualBoost learning for selecting Gabor features for face recognition[J].Pattern Recognition Letters,2006,27(15):1758-1767.

备注/Memo

备注/Memo:
收稿日期:2009-01-14;修回日期:2009-06-11
基金项目:国家自然科学基金资助项目(60903112);深圳市科技计划资助项目(CXQ2008019,JC200903120074A)
作者简介:李玉文(1965-),女(汉族),湖南省邵阳市人,深圳信息职业技术学院讲师.E-mail:ywli@sziit.com.cn
通讯作者:沈琳琳(1976-),男(汉族),深圳大学副教授、博士.E-mail:llshen@szu.edu.cn
更新日期/Last Update: 2009-11-09