计算机与现代化

• 图像处理 • 上一篇    下一篇

鱼眼图像中手部定位及手势识别

  

  1. 1.华南理工大学数学学院,广东广州510640; 2.华南理工大学电子与信息学院,广东广州510640
  • 收稿日期:2016-12-17 出版日期:2017-03-29 发布日期:2017-03-30
  • 作者简介:张艳(1992-),女,湖南常德人,华南理工大学数学学院硕士研究生,研究方向:计算智能与信息处理; 田翔(1974-),男,湖北黄陂人,华南理工大学电子与信息学院副教授,研究方向 :计算智能与信息处理。

Hand Location and Hand Gesture Recognition in Fisheye Image

  1. 1. School of Mathematics, South China University of Technology, Guangzhou 510640, China;
    2. School of Electronics and Information, South China University of Technology, Guangzhou 510640, China
  • Received:2016-12-17 Online:2017-03-29 Published:2017-03-30

摘要:

针对增强现实领域手势交互的需求,提出鱼眼图像中手部定位及手势识别的方法。首先在YCbCr颜色空间中检测肤色区域,再利用HSV空间颜色直方图特征和形状特征在肤色区域中检测标识物,分割
手部区域。然后将标识物质心作为手部定位中心,根据鱼眼镜头的成像原理,计算该点相对于鱼眼镜头的三维位置。最后提取手势形状特征,实现手势识别。通过对85幅不同背景及光照条件下的鱼眼图
像进行实验,此方法识别手势的正确率为96%,识别单幅鱼眼图像约耗时0.03 s。实验结果表明,该方法可以快速准确地实现在复杂背景下的手部定位与手势识别。
关键词:
中图分类号:doi:

关键词: 手势识别, 手部定位, 鱼眼图像, 肤色检测, 形状特征提取

Abstract:

In view of the demand for hand gesture interaction in Augmented Reality (AR), this paper proposes a method of hand location and hand gesture recognition in fisheye
image. First, skin color region is detected in YCbCr color space, then HSV space color histogram feature and shape feature is used to detect mark in the skin region, and to
divide hand area. Second, this method uses the centroid of mark as hand positioning center, according to imaging principle of fisheye lens, to calculate the 3D position of the
point relative to fisheye lens. Last, this paper extracts hand gesture shape features, to complete the procedure of recognizing hand gestures. Through the experiment of the 85
fisheye images with different background and light, the correct rate for recognizing gestures is 96%, recognizing single fisheye image takes about 0.03 s. The experimental
results show that the proposed method can realize hand location and hand gesture recognition quickly and effectively in complex background.

Key words:  , hand gesture recognition; hand location; fisheye image; skin detection; shape features extraction

中图分类号: