基于眼电的智能输入系统研究

发布时间：2018-06-30 21:32

本文选题：眼电图 + 人机交互　；参考：《中国生物医学工程学报》2015年06期

【摘要】：为了帮助肢体运动功能障碍患者与外界交流,设计一套基于眨眼眼电的便携式智能输入系统,使用者仅通过眨眼便能控制人机交互界面上的虚拟键盘进行字符输入。该系统中的信号采集模块先对眼电信号经行预处理,然后将其转换为数字信号传输至微处理。微处理首先通过数字形态学方法滤除信号中的尖峰噪声,然后通过动态阈值和归一化、微分算法识别主动眨眼信号,并完成对虚拟键盘的控制,实现中文、英文或数字的输入。选择12名受试者分别在常规实验室、电磁干扰较大的磁共振设备室和户外的运动场进行测试。结果表明,该系统在上述3个不同的环境中能够准确识别眨眼信号并实现中文、英文及数字的输入,而且输入字符的平均准确率不低于98%,中文、英文字符和数字的平均输入速度分别为(2.8±0.3)、(6.6±0.35)、(9.7±0.38)个/min。因此,该系统的抗干扰能力较强,能够帮助肢体运动功能障碍患者实现与外界交流。
[Abstract]:In order to help the patients with limb motor dysfunction communicate with the outside world, a portable intelligent input system based on blinking is designed. The user can only control the virtual keyboard on the human-computer interface to input characters by blinking. The signal acquisition module of the system preprocesses the Eye-signal and then converts it to digital signal for microprocessing. Firstly, the signal peak noise is filtered by digital morphology, then the active blinking signal is recognized by the dynamic threshold and normalization, and the virtual keyboard is controlled to realize the Chinese, English or digital input. Twelve subjects were tested in conventional laboratory, magnetic resonance equipment room and outdoor sports field. The results show that the system can accurately recognize blinking signals and input Chinese, English and digital signals in the above three different environments, and the average accuracy of input characters is not less than 98. The average input speed of English characters and numbers was (2.8 卤0.3), (6.6 卤0.35), (9.7 卤0.38) / min, respectively. Therefore, the system has strong anti-interference ability and can help patients with limb motor dysfunction to communicate with the outside world.
【作者单位】：电子科技大学生命科学与技术学院;
【基金】：国家重大科学仪器开发专项(2012YQ120046) 国家高技术研究发展计划(863计划)(2015AA020510)
【分类号】：TP334.2;R49

【参考文献】