Detection of Winking by a Neural Network
Detection of Winking by a Neural Network
复制标题
通过神经网络检测眨眼
DOI：
10.1541/ieejeiss1987.115.3_367
复制
发表时间：
1995
期刊：
影响因子：
--
通讯作者：
K. Inoue
中科院分区：
文献类型：
--
作者：
Naoyuki Kanou;M. Inoue;Yasuhiro Kobayashi;T. Kawakami;K. Inoue
我们为重症患者开发了几种沟通辅助工具（CA）（例如，脊髓损伤患者、肌萎缩侧索硬化症患者等）丧失沟通能力的患者。CA的输入传感器对于CA的顺利使用非常重要。大多数患者使用的传感器都是穿戴式的。但很难将这种传感器准确地放在相关的肌肉上。在本文中，我们将眨眼应用于CA的输入信号。通过训练一个三层神经网络对电视摄像机上检测到的眨眼进行识别。为了提高其模式泛化能力，我们将神经网络训练的初始权值设置到其输入图像。
We have developed several Communication Aids ( CAs) for serious patients ( e.q., Spinal Cord Injured Patients, Amyotrophic Lateral Sclerosis etc. ) who lose their ability of communication. The input sensor of the CA is very important to use it smoothly. Most patients have used sensors of put-on-type. But it is difficult to put such sensors on their relevant muscle exactly. In this paper, we apply the winking to an input signal of the CA. The winking, whitch is detected on a TV camera, is recognized by training a neural network ( NN) with three layers. To implove their ability of pattern generalization, we set the initial weights of the NN refering to its input images.