仿人型假肢眨眼检测与识别的原理与实现  

Principle and Implementation of Blink of an Eye Detection and Recognition for Humanoid Type Prosthetic

作　　者：苏航[1] 张维海[1] 郑义[2] SU Hang ZHANG Weihai ZHENG Yi(College of Electrical and Automation Engineering, Shandong University of Science and Technology, Qingdao Shandong 266590, China College of Mechanical and Electrical Engineering,Shandong University of Science and Technology, Qingdao Shandong 266590, China)

机构地区：[1]山东科技大学电气与自动化工程学院,山东青岛266590 [2]山东科技大学机械电子工程学院,山东青岛266590

出　　处：《机床与液压》2017年第11期5-8,27,共5页Machine Tool & Hydraulics

基　　金：国家自然科学基金资助项目(6117084)

摘　　要：针对利用眨眼检测与识别的原理来实现控制仿人型假肢运动的问题,构建了一种眨眼检测和识别系统的基本结构,介绍了眨眼检测和识别的基本原理,论述了从检测眨眼事件到识别控制指令的整个流程,利用眼动仪结合上位机应用程序进行了眨眼检测,提取了特征向量,最后对软件的检测效果进行了测试。实验表明,这种方法可以以很高的准确率检测眨眼信号并获得特征向量,达到了准确控制假肢运动的目的。Aiming at realizing the humanoid type prosthetic movement control problem by use the principle of blinking detection and recognition, the basic structure of a blink of an eye detection and recognition system was built, and the basic principles of blink of an eye detection and recognition were introduced. Aiming at realizing the humanoid type prosthetic movement control problem by use the principle of blinking detection and recognition, the basic structure of a blink of an eye detection and recognition system is built, and the basic principles of blink of an eye detection and recognition are introduced. The whole process from blink event detection to identify control instruction was discussed, the blink of an eye detection and extraction of feature vector were carried out by using Eye-movement apparatus combined with host personal computer （PC） application program, and finally, the software testing effect was tested. Experi-mental results show that this method can detect blink signal at high accuracy and obtain feature vector to achieve the purpose of the ac-curate control prosthetic limbs movement.

关 键 词：眨眼检测 眼动仪 仿人型假肢 特征向量 

分 类 号：TN911.71[电子电信—通信与信息系统]