一种快速高效的人脸特征点定位方法
|
摘要
针对传统人脸特征点定位方法中存在的算法复杂、鲁棒性差以及精确度低等不足,提出一种基于局部特征区域快速高效的人脸特征点自动定位方法。首先对经过预处理后的人脸图像利用改进的积分投影算法结合肤色特性实现人脸区域的精确定位;然后在人脸区域内根据各特征部位的特性标定其特征区域;最后在特征区域内完成人脸特征点的自动定位。实验结果表明,该算法简单、具有较高的鲁棒性,且能够快速高效地实现人脸特征点定位。
Considering the high computational complexity,poor robustness and low accuracy of traditional algorithm for positioning facial feature points,this paper proposed a fast and efficient method based on the local feature regions for automatic positioning facial feature points.First,it positioned the face region precisely using an improved integral projection algorithm combined with color characteristics of the facial skin after pretreating the face image.Next,it positioned the feature regions according to the characteristics of each part in the face region.Finally,it positioned the facial feature points automatically in the feature region.The experiments show that this method is not only simple and robust,but also capable of positioning the facial feature points quickly and efficiently.
Considering the high computational complexity,poor robustness and low accuracy of traditional algorithm for positioning facial feature points,this paper proposed a fast and efficient method based on the local feature regions for automatic positioning facial feature points.First,it positioned the face region precisely using an improved integral projection algorithm combined with color characteristics of the facial skin after pretreating the face image.Next,it positioned the feature regions according to the characteristics of each part in the face region.Finally,it positioned the facial feature points automatically in the feature region.The experiments show that this method is not only simple and robust,but also capable of positioning the facial feature points quickly and efficiently.
引文
[1]BUTAKOFF C,FRANGI A F.Multi-view face segmentation using fusion of statistical shape and appearance models[J].Computer Vision and Image Understanding,2010,114(3):311-321.
[2]COOTES T F,WALKER K,TAYLOR C J.View-based active appearance models[C]//Proc of the 4th IEEE International Conference on Automatic Face and Gesture Recognition.[S.l.]:IEEE Press,2000:227-232.
[3]STEGMANN M B,ERSBOLL B K,LARSEN R.FAME:a flexible appearance modeling environment[J].IEEE Trans on Medical Ima-ging,2003,22(10):1319-1331.
[4]MATTHEWS I,BAKER S.Active appearance models revisited[J].International Journal of Computer Vision,2004,60(2):135-164.
[5]王丽婷,丁晓青,方驰.一种鲁棒的全自动人脸特征点定位方法[J].自动化学报,2009,35(1):9-16.
[6]林维训,潘刚,吴朝晖,等.脸部特征定位方法[J].中国图象图形学报,2003,8(8):849-859.
[7]GUO Yan-wen,PAN Yong-juan,CUI Xiu-fen,et al.Harmonic maps based constrained texture mapping method[J].Computer Aided Design and Computer Graphics,2005,17(7):1457-1462.
[8]刘成明,张立明.一种改进的人脸特征点定位方法[J].复旦学报:自然科学版,2006,45(4):457-460.
[9]崔连延,徐林,顾树生.基于复杂度和最佳阈值的人眼定位方法[J].控制工程,2008,15(1):12-14.
[10]韩玉峰,王小林.一种基于改进的ASM的人脸特征点定位方法[J].计算机科学,2013,40(4):271-274.
[2]COOTES T F,WALKER K,TAYLOR C J.View-based active appearance models[C]//Proc of the 4th IEEE International Conference on Automatic Face and Gesture Recognition.[S.l.]:IEEE Press,2000:227-232.
[3]STEGMANN M B,ERSBOLL B K,LARSEN R.FAME:a flexible appearance modeling environment[J].IEEE Trans on Medical Ima-ging,2003,22(10):1319-1331.
[4]MATTHEWS I,BAKER S.Active appearance models revisited[J].International Journal of Computer Vision,2004,60(2):135-164.
[5]王丽婷,丁晓青,方驰.一种鲁棒的全自动人脸特征点定位方法[J].自动化学报,2009,35(1):9-16.
[6]林维训,潘刚,吴朝晖,等.脸部特征定位方法[J].中国图象图形学报,2003,8(8):849-859.
[7]GUO Yan-wen,PAN Yong-juan,CUI Xiu-fen,et al.Harmonic maps based constrained texture mapping method[J].Computer Aided Design and Computer Graphics,2005,17(7):1457-1462.
[8]刘成明,张立明.一种改进的人脸特征点定位方法[J].复旦学报:自然科学版,2006,45(4):457-460.
[9]崔连延,徐林,顾树生.基于复杂度和最佳阈值的人眼定位方法[J].控制工程,2008,15(1):12-14.
[10]韩玉峰,王小林.一种基于改进的ASM的人脸特征点定位方法[J].计算机科学,2013,40(4):271-274.