...
首页> 外文期刊>Instrumentation and Measurement, IEEE Transactions on >Dynamic Sign Language Recognition for Smart Home Interactive Application Using Stochastic Linear Formal Grammar
【24h】

Dynamic Sign Language Recognition for Smart Home Interactive Application Using Stochastic Linear Formal Grammar

机译:基于随机线性形式语法的智能家居交互式应用程序的动态手语识别

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       

摘要

This paper presents the state-of-the art dynamic sign language recognition (DSLR) system for smart home interactive applications. Our novel DSLR system comprises two main subsystems: an image processing (IP) module and a stochastic linear formal grammar (SLFG) module. Our IP module enables us to recognize the individual words of the sign language (i.e., a single gesture). In this module, we used the bag-of-features (BOFs) and a local part model approach for bare hand dynamic gesture recognition from a video. We used dense sampling to extract local 3-D multiscale whole-part features. We adopted 3-D histograms of a gradient orientation descriptor to represent features. The -means++ method was applied to cluster the visual words. Dynamic hand gesture classification was conducted using the BOFs and nonlinear support vector machine methods. We used a multiscale local part model to preserve temporal context. The SLFG module analyzes the sentences of the sign language (i.e., sequences of gestures) and determines whether or not they are syntactically valid. Therefore, the DSLR system is not only able to rule out ungrammatical sentences, but it can also make predictions about missing gestures, which, in turn, increases the accuracy of our recognition task. Our IP module alone seals the accuracy of 97% and outperforms any existing bare hand dynamic gesture recognition system. However, by exploiting syntactic pattern recognition, the SLFG module raises this accuracy by 1.65%. This makes the aggregate performance of the DSLR system as accurate as 98.65%.
机译:本文介绍了用于智能家居交互式应用程序的最新动态手语识别(DSLR)系统。我们新颖的DSLR系统包括两个主要子系统:图像处理(IP)模块和随机线性形式语法(SLFG)模块。我们的IP模块使我们能够识别手语的单个单词(即单个手势)。在此模块中,我们使用功能包(BOF)和局部零件模型方法从视频中进行裸手动态手势识别。我们使用密集采样来提取局部3D多尺度整体零件特征。我们采用了梯度方向描述符的3D直方图来表示特征。 -means ++方法用于对视觉单词进行聚类。使用BOF和非线性支持向量机方法进行动态手势分类。我们使用了多尺度局部模型来保留时间上下文。 SLFG模块分析手语的句子(即手势序列),并确定它们在语法上是否有效。因此,DSLR系统不仅可以排除不合语法的句子,还可以对丢失的手势做出预测,从而提高了识别任务的准确性。仅我们的IP模块就可以将精度提高到97%,并且胜过任何现有的裸手动态手势识别系统。但是,通过利用句法模式识别,SLFG模块将精度提高了1.65%。这使得DSLR系统的综合性能精确到98.65%。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号