• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>ICCCI 2010;International conference on computer and computational intelligence >Robust Gesture Recognition using Euclidian Distance
【24h】

Robust Gesture Recognition using Euclidian Distance

机译：欧氏距离的鲁棒手势识别

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, we have applied a novel approach for recognizing the hand gesture and we have studied other methods and made a comparative study with these methods, in our suggested system, the input gesture is preprocessed first in order to get the hand gesture boundary; and then the hand gesture is divided into non-overlapped blocks each of 23x23 pixels, we also have computed the local brightness value for each block and we plot a curve, this plotted curve represents the feature vector for this gesture, this process has been repeated for the rest of the training gestures, we have used the Euclidian Distance in order to recognize the new presented testing gesture against the database feature vectors after extracting the feature vector of the testing gesture and we have achieved 88% recognition percentage with approximate time of 1.55 second. This Paper focuses on the hand gesture instead of the whole body movement since hands are the most flexible part of the body and can transfer the most meaning.
机译：在本文中，我们采用了一种新颖的手势识别方法，并研究了其他方法，并与这些方法进行了比较研究。然后将手势分为23x23像素的非重叠块，我们还计算了每个块的局部亮度值，并绘制了一条曲线，该绘制的曲线表示该手势的特征向量，此过程已重复进行对于其余的训练手势，在提取测试手势的特征向量后，我们使用了欧几里德距离来针对数据库特征向量识别新呈现的测试手势，并且在大约1.55的时间里，我们获得了88％的识别率第二。本文着重于手势而不是整个身体的动作，因为手是身体最灵活的部分，可以传递最多的含义。

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