Mathematical morphology based electro-oculography recognition
algorithm for human-computer interaction
CHEN Wei-dong1,2, LI Xin1,2, LIU Jun1,3, HAO Yao-yao1,3,
LIAO Yu-xi1,3, SU Yu1,2, ZHANG Shao-min1,3, ZHENG Xiao-xiang1,3
1. Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou 310027, China; 2.College of Computer
Science and Technology, Zhejiang University, Hangzhou 310027, China; 3.College of Biomedical Engineering
and Instrument Science, Zhejiang University, Hangzhou 310027, China
Electro-oculography (EOG) signals can be used for recognizing the directions of eye movements and voluntary eye blinks, which can be used to develop a new human-computer interaction (HCI) system. A mathematical morphology based algorithm was presented to process the EOG signals, which always contain some interference components, such as baseline drift, EMG interference and movement artifacts. The new approach can effectively reduce the artifacts and recognize the directions of eye movements and voluntary eye blinks by using a set of thresholds. A HCI system for disabled using the method was designed and tested by both healthy and disabled people. Experimental results showed that the average correct rate was 96.2%. The system can be employed in clinical HCI fields.
［1］ TECCE J J, GIPS J, OLIVIERI C P, et al. Eye movement control of computer functions ［J］. International Journal of Psychophysiology, 1998, 29(3): 319-325.
［2］ REMMEL R S. An inexpensive eye movement monitor using the scleral search coil technique ［J］. IEEE Transactions on Biomedical Engineering, 1984, BME31(4): 388-390.
［3］ LACOURSE J R, HLUDIK J R. An eye movement communicationcontrol system for the disabled ［J］. IEEE Transaction on Biomedical English, 1990, 37(12): 1215-1220.
［4］ DI MATTIA P, CURRAN F X, GIPS J. An eye control teaching device or students without language expressive capacity: eagle eyes ［M］. Lewiston: Edwin Mellen Press, 2001: 10-13.
［5］ KENJI Y, JUNISHI H, MICHIO M. Development of EOGbased communication system controlled by eightdirectional eye movements ［C］∥ Engineering in Medicine and Biology Society, EMBS ′06. 28th Annual International Conference of the IEEE. New York: IEEE, 2006: 25742577.［6］ BAREA R, BOQUETE L, MAZO M, et al. System for assisted mobility using eye movements based on electrooculography ［J］. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2002, 10(4): 209-218.
［7］ KIMMIG H, GREENLEE M W, HUETHE F, et al. MREyetracker: a new method for eye movement recording in functional magnetic resonance imaging ［J］. Experimental Brain Research, 1999, 126(3): 443-449.
［8］ CLARKE A H, DITTERICH J, DRUEN K, et al. Using high frame rate CMOS sensors for threedimensional eye tracking ［J］. Behavior Research Methods, Instruments and Computers, 2002, 34(4): 549-600.
［9］ 方淼滨,邹俊忠,姚晓东,等.基于EOG眼电信号的机器人三维定位［J］.计算机与数字工程.2005,33(2): 28-30.
FANG Miaobin, ZOU Junzhong, YAO Xiaodong, et al. Robot 3D positioning based on EOG signal analysis ［J］. Computer and Digital Engineering, 2005, 33(2): 28-30.
［10］ ZHAO L, WU X P, LI M, et al. Implementation of the EOGbased human computer interface system ［C］∥ Bioinformatics and Biomedical Engineering. Shanghai: IEEE, 2008: 2188-2191.
［11］ 李卫娜,侯文生,郑小林,等.基于Electrooculogram的眼动信息识别［J］.仪器仪表学报,2008,28(8): 1428-1433.
LI Weina, HOU Wensheng, ZHENG XiaoLin, et al. Identification of eyemovement information based on electrooculogram ［J］. Chinese Journal of Scientific Instrument, 28(8): 1428-1433.
［12］ OGUZ S H, ASYALI M H. A morphology based algorithm for baseline wander elimination in ECG records ［C］∥Proceedings of the IEEE International Biomedical Engineering Days. Istanbul Turkey: IEEE, 1992: 160-164.
［13］ CHU C H H, DELP E J. Impulsive noise suppression and background normalization of electrocardiogram signals using morphological operators ［J］. IEEE Transactions on Biomedical Engineering, 1989, 36(2): 262-273.
［14］ 赵俊梅,张利平.基于数学形态学的车牌识别方法［J］.车辆与动力技术,2008(4): 31-34.
ZHAO Junmei, ZHANG Liping. Method of vehicle license recognition based on mathematical morphology ［J］. Vehicle and Power Technology, 2008(4): 31-34.
［15］ 耿新玲,乔志梅,胡广书.基于数学形态学预处理的神经元放电检测［J］.清华大学学报:自然科学版,2009,49(3): 435-438.
GENG Xinling, QIAO Zhimei, HU Guangshu. Neural spike detection based on mathematical morphology preprocessing ［J］. Journal of Tsinghua University: Science and Technology, 2009, 49(3): 435-438.
［16］ WOLPAW J R, BIRBAUMER N, MCFARLAND D J, et al. Braincomputer interfaces for communication and control ［J］. Clinical Neurophysiology, 2002, 113(6): 767-791.
