首页> 外文期刊>Journal of visual communication & image representation >Recognition of user-dependent and independent static hand gestures: Application to sign language
【24h】

Recognition of user-dependent and independent static hand gestures: Application to sign language

机译:识别用户依赖和独立的静态手势:应用要签署语言的应用程序

获取原文
获取原文并翻译 | 示例
           

摘要

Static hand gesture (HG) recognition for both user-dependent and user-independent is a challenging problem, especially when there are changes in lighting, hand position, and background, the recognition becomes more complex. To solve this problem, this paper proposes a static hand gesture recognition based on a set of image descriptors: Gradient Local Auto-Correlation (GLAC), Gabor Wavelet Transform (GWT), and Fast Discrete Curve Transform (FDCT). Principal Component Analysis (PCA) was used to reduce dimensionality. Tests were performed on three sign language datasets and one hand posture dataset using neural network classifiers, K-Nearest Neighbor (KNN) classifiers, and combined classifiers. The results obtained were compared to the state of the art and show an accuracy of 100% for user-independent and 98.33% for user-dependent gestures, despite the difficult acquisition conditions of the datasets.
机译:静态手势(HG)对用户依赖和用户无关的识别是一个具有挑战性的问题,特别是当照明,手势和背景中发生变化时,识别变得更加复杂。 为了解决这个问题,本文提出了一种基于一组图像描述符的静态手势识别:梯度本地自相关(GLAC),Gabor小波变换(GWT)和快速离散曲线变换(FDCT)。 主要成分分析(PCA)用于减少维度。 使用神经网络分类器,K-Collect邻居(KNN)分类器和组合分类器,在三个手语数据集和一手姿势数据集上执行测试。 尽管数据集的困难的收购条件,所获得的结果与现有技术进行了比较,并且为用户无关的精度为100%,并且对于用户依赖的手势而言,这是依赖于用户依赖的手势的。

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