[1]王锦榕,袁学海,刘增良.基于图像处理技术的瞳孔和角膜反射中心提取算法[J].智能系统学报,2012,(05):423-428.
 WANG Jinrong,YUAN Xuehai,LIU Zengliang.An extraction method of pupil and corneal reflection centers based on image processing technology[J].CAAI Transactions on Intelligent Systems,2012,(05):423-428.
点击复制

基于图像处理技术的瞳孔和角膜反射中心提取算法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
期数:
2012年05期
页码:
423-428
栏目:
出版日期:
2012-10-25

文章信息/Info

Title:
An extraction method of pupil and corneal reflection centers based on image processing technology
文章编号:
1673-4785(2012)05-0423-06
作者:
王锦榕1袁学海1刘增良2
1.大连理工大学 控制科学与工程学院,辽宁 大连 116024;
2.中国人民解放军国防大学 信息作战与指挥训练教研部,北京 100091
Author(s):
WANG Jinrong1 YUAN Xuehai1 LIU Zengliang2
1. School of Control Science and Engineering, Dalian University of Technology, Dalian 116024, China;
2. Institute of Information Operation, National Defense University of PLA, Beijing 100091, China
关键词:
瞳孔中心角膜反射中心图像处理瞳孔〖KG-*1/3〗-〖KG-*1/3〗角膜跟踪法自适应最佳阈值椭圆拟合提取算法
Keywords:
pupil center corneal reflection center image processing pupilcorneal tracking method optimum adaptive threshold ellipse fitting extraction method
分类号:
TP751.1
文献标志码:
A
摘要:
为了提高瞳孔中心的实时提取精度和抗干扰能力,利用基于瞳孔〖KG-*1/3〗-〖KG-*1/3〗角膜跟踪法原理和图像处理的眼动跟踪技术,实现瞳孔和角膜反射中心的精确提取.首先在红外光源条件下,用摄像机捕获人眼图像,通过图像自适应二值化阈值确定图像处理区域,以减小处理时间;其次,利用高低2次二值化阈值提取角膜反射中心;然后求取自适应最佳阈值确定瞳孔位置和大小;最后用梯度法提取瞳孔轮廓特征点,并用椭圆拟合瞳孔的方法确定瞳孔中心.实验结果表明,该算法在保证瞳孔和角膜反射中心提取的准确性和稳定性的同时,能满足实时处理要求.
Abstract:
In order to improve the realtime localization accuracy and antijamming capability of the pupil center, an eyetracking method was used based on the pupilcornea tracking principle and image processing. As a result, accurate measurements of the centers of the pupil and corneal reflection were obtained. First, under the infrared light, an eye image was captured by a camera. In order to reduce the processing time, the image processing area was acquired by applying an adaptive binarization threshold. Second, the center of the corneal reflection was extracted by using a high threshold value and a low threshold value. Then, the optimum adaptive threshold value was calculated to get the location and size of the pupil. Finally, the feature points of the pupil edge were obtained by applying the gradient method, and the center of the pupil was located by a fitting ellipse. The results show that this algorithm can not only guarantee the accuracy and stability of obtaining the center of the pupil and the center of corneal reflection, but also meet the demands of realtime processing. 

参考文献/References:

[1]ROBINSON D A. A method of measuring eye movements using a scleral search coil in a magnetic field[J]. IEEE Transactions on Biomedical Engineering, 1963, BME10: 137145.
[2]SHUPERT C, FUCHS A F. Development of conjugate human eye movements[J]. Vision Research, 1988, 28(5): 585596.
[3]GAUTHIER G M. Vertical and horizontal eye movement recording in the unrestrained cat[J]. IEEE Transactions on Biomedical Engineering, 1975, BME22(3): 202207.
[4]JONES R. Two dimensional eye movement recording using a photoelectric matrix method[J]. Vision Research, 1973, 13(2): 425431.
[5]王朝英,赵乐军,陈怀琛.红外TV法眼动测量系统及实现[J].西安电子科技大学学报, 1999, 26(3): 709712.
WANG Chaoying, ZHAO Lejun, CHEN Huaichen. A system and the implementation of eye movement measurement based on the infrared TV[J]. Journal of Xidian University, 1999, 26(3): 709712.
[6]闫国利,田宏杰.眼动记录技术与方法综述[J].应用心理学, 2004, 10(2): 5558.
YAN Guoli, TIAN Hongjie. A review of eye movement recording methods and techniques[J]. Chinese Journal of Applied Psychology, 2004, 10(2): 5558.
[7]赵新灿,左洪福,任勇军.眼动仪与视线跟踪技术综述[J].计算机工程与应用, 2006, 42(12): 118120.
ZHAO Xincan, ZUO Hongfu, REN Yongjun. A review of eye tracker and eye tracking techniques[J]. Computer Engineering and Application, 2006, 42(12): 118120.
[8]王军宁,刘涛,何迪,等.红外头盔式眼动议的瞳孔中心定位算法[J].西安电子科技大学学报, 2011, 38(3): 812.
WANG Junning, LIU Tao, HE Di, et al. Pupil center localization algorithm used for the IR headmounted eye tracker[J]. Journal of Xidian University, 2011, 38(3): 812.
[9]周嘉宾.眼动跟踪系统算法研究与实现[D].西安:西安电子科技大学, 2010: 241298.
 ZHOU Jiabin. Study and implementation on the algorithm of eye tracking system[D]. Xi’an: Xidian University, 2010: 241298.
[10]阎蓓,王斌,李媛.基于最小二乘法的椭圆拟合改进算法[J].北京航空航天大学学报, 2008, 34(3): 295298.
YAN Bei, WANG Bin, LI Yuan. Optmial ellipse fitting method based on least square principle[J]. Journal of Beijing University of Aeronautics and Astronautics, 2008, 34(3): 295298.
[11]罗军辉,冯平.MATLAB 7.0在图像处理中的应用[M].北京:机械工业出版社, 2005: 252257.

备注/Memo

备注/Memo:
收稿日期: 2011-12-08.
网络出版日期:2012-05-27.
基金项目:国家自然科学基金资助项目(90818025).
通信作者:袁学海.
E-mail: yuanxuehai@yahoo.com.cn.
作者简介:
王锦榕,男,1986年生,硕士研究生,主要研究方向为运动控制算法和机器人视觉处理.
袁学海,男,1960年生,教授,博士生导师,博士,主要研究方向为智能控制和模糊系统理论.先后主持辽宁省教育厅科研项目4项,参与国家自然科学基金项目1项、数学天元基金项目1项.曾获辽宁省教委科技进步奖二等奖和辽宁省自然科学成果奖二等奖各1项,发表学术论文120余篇.
刘增良,男,1958年生,教授,博士生导师,理学博士,计算机博士后,国防大学信息作战学科带头人.主要研究方向为智能系统工程、信息对抗和指挥自动化.先后主持国家自然科学基金、国家“863”计划及军队“十五”计划等科研项目20余项.曾获国家科技进步奖二等奖2项,发表学术论文40余篇,出版专著5部.
更新日期/Last Update: 2012-11-13