对于很多基于视觉的徒手人机交互系统,指尖的检测是其中的关键环节.为此提出了一种新颖简单但高效的方法来实现不同背景下的指尖检测,该算法不需要进行任何前景分割来辅助定位.针对指尖自身的形状所具有的径向对称性质,采用改进的径向对称变换算法先检测出指尖的候选点,然后通过肤色判别操作来帮助实现指尖的准确定位.实验结果表明,本文算法在不同的实际背景下都具有很好的检测效果,对光照的鲁棒性也较高,并且能够达到实时.
The fingertip is an important feature whose detection is the key connection for many vision based barehanded HCI systems. A novel, simple but effective methodology for fingertip detection under different backgrounds was presented, and no foreground segmentation is required to assist the location. The detection was mainly based on the radial symmetry transform according to the fingertip's special shape, which had a sensible radial symmetry. Subsequently, skin color discrimination was adopted to help locate the fingertip well. Experimental results show that the proposed algorithm performs well in different backgrounds and is robust to the influence of illumination in a real-time system.