研究了一种改进的基于 Hough变换圆检测的瞳孔识别方法.直接利用 Hough 变换圆检测进行瞳孔识别准确度低、运算量大,为此,本文提出了改进的识别方法.在实现Canny边缘检测的基础上,利用 Hough变换进行求解时,限定检测的半径范围,在此范围内,根据参数空间圆的方程,求出对应的圆心坐标,得到最佳拟合圆,最终实现瞳孔识别以及中心点定位.在vc＋＋6．0开发平台下,对150幅图像进行瞳孔识别检测实验,结果显示,直接利用 Hough变换检测方法的准确率为70．7％,平均速度为1 s；本方法的准确率为94％,平均速度为0．45 s,可见相较于直接利用 Hough变换进行瞳孔识别,本文方法在识别准确率和识别速度方面均有显著提高.结果表明,此方法能够快速而准确地进行瞳孔识别以及中心点定位.
As traditional way for pupil recognition based on Hough transform circle detection has lower accuracy and speed,an improved method is proposed in this paper.After edge detection by Canny op-erator,Hough transform is performed in a limited radius.Within this range,finding the best fitting circle based on the circle equation in parameter space to get the center coordinates and radius,pupil recognition and center positioning are achieved ultimately.150 images are used to test the effects of pupil recognition under vc ++ 6.0 development platform.The experiments results show that the ac-curacy is 70.7% with an average speed of 1 s based on Hough transform which is used directly.In comparison the accuracy is 94% and the average speed is 0.45 s with the method proposed in this pa-per.It indicates that this method has a significant improvement on accuracy and speed.It can recog-nize the pupil and locate the center faster and has more accuracy.
参考文献
| [1] | 王先梅;杨萍;王志良.多姿态眼球中的瞳孔定位算法[J].计算机辅助设计与图形学学报,2011(8):1427-1432. |
| [2] | 王长元;张景;李京京.瞳孔中心快速定位方法研究[J].计算机工程与应用,2011(24):196-198,201. |
| [3] | Yuanxin Zhu;Carragher B.;Mouche F.;Potter C.S..Automatic particle detection through efficient Hough transforms[J].IEEE Transactions on Medical Imaging,20039(9):53-62. |
| [4] | Wildes R.P..Iris recognition: an emerging biometric technology[J].Proceedings of the IEEE,19979(9):1348-1363. |
| [5] | 宓翔;邱飞岳.基于CCD的瞳孔自动识别方法的设计与实现[J].轻工机械,2012(1):88-91,94. |
| [6] | 王林波;王延杰;邸男;金明河.基于几何特征的圆形标志点亚像素中心定位[J].液晶与显示,2014(6):1003-1009. |
| [7] | 吕哲;王福利;常玉清.一种改进的Canny边缘检测算法[J].东北大学学报（自然科学版）,2007(12):1681-1684. |
| [8] | 朱桂英;张瑞林.基于Hough变换的圆检测方法[J].计算机工程与设计,2008(6):1462-1464. |
| [9] | 杨全银 .基于Hough变换的图像形状特征检测[D].山东大学,2009. |
- 下载量()
- 访问量()
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%