| 基于模糊神经网络的静态手语词汇识别 |
| |
| 引用本文： | 邹伟, 原魁, 杜清秀, 徐春. 基于模糊神经网络的静态手语词汇识别. 自动化学报, 2003, 29(4): 616-621. |
| |
| 作者姓名： | 邹伟 原魁 杜清秀 徐春 |
| |
| 作者单位： | 1.中国科学院自动化研究所,北京 |
| |
| 基金项目： | NationalNaturalScienceFoundationofP .R .China (6 0 2 730 2 8)，“863”ProjectofP.R.China(2 0 0 1AAN114 2 0 0 ) |
| |
| 摘 要： | 利用数据手套CAS-Glove作为输入设备,提出了一种基于模糊神经网络的中国手语单手静态词汇的识别方法:首先利用经验知识为每个词汇创建模糊规则,然后通过学习确定各模糊子集隶属函数中的参数.对于参数的学习,提出了一种适用于分类器的可微经验风险函数,该函数能够有效地利用梯度下降法进行最小化.在实验中通过比较证实了该方法的有效性和可靠性.
|
| 关 键 词： | 中国手语 模糊神经网络 推理规则 经验风险函数 CAS-Glove |
| 收稿时间： | 2002-05-17 |
A Recognition Method for Static Words of Chinese Sign Language Based on Fuzzy-Neuro Network |
| |
| ZOU Wei, YUAN Kui, DU Qing-Xiu, XU Chun. A Recognition Method for Static Words of Chinese Sign Language Based on Fuzzy-Neuro Network. ACTA AUTOMATICA SINICA, 2003, 29(4): 616-621. |
| |
| Authors: | ZOU Wei Yuan Kui DU Qing-Xiu XU Chun |
| |
| Affiliation: | 1. Institute of Automation,Chinese Academy of Sciences,Beijing |
| |
| Abstract: | In this paper, a novel recognition method of single hand static words of Chinese Sign Language based on fuzzy neuro network is introduced. First, the fuzzy reasoning rules and the network structure are established using empirical knowledge. Then the membership function parameters for each fuzzy subset are obtained by learning. For the learning process, a new kind of empirical risk function is proposed which is differentiable and can be minimized by gradient descent strategy. This method is compared with others through experiments and its validity and reliability are confirmed. |
| |
| Keywords: | Chinese sign language fuzzy neuro network reasoning rules empirical risk function CAS Glove |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
