基于鼻子下轮廓线的鼻尖定位法

华东师范大学学报(自然科学版) ›› 2014, Vol. 2014 ›› Issue (4): 54-61.

基于鼻子下轮廓线的鼻尖定位法

刘丹, 童卫青

华东师范大学~~计算机科学技术系, 上海 200241

收稿日期:2013-07-01 修回日期:2013-10-01 出版日期:2014-07-25 发布日期:2014-07-25

Nose tip location based on nose contour

LIU Dan, TONG Wei-qing

Department of Computer Science and Technology, East China Normal University, Shanghai 200241, China

Received:2013-07-01 Revised:2013-10-01 Online:2014-07-25 Published:2014-07-25

摘要/Abstract

摘要： 提出了一种基于鼻子下轮廓线的鼻尖定位算法.
该算法首先利用人脸先验知识和眼睛位置确定鼻子候选区域,
然后用Canny算子抽出鼻子边缘, 通过计算其置信度获取鼻子下轮廓线,
最后采用最小二乘法拟合鼻子下轮廓线为抛物线, 从而确定鼻尖位置.
实验表明, 本算法具有较高的鼻尖定位精度和应用价值.

关键词: 鼻尖定位, Canny算子, 最小二乘拟合算法, 人脸姿态估计

Abstract: This paper presents an approach to locate nose tip using
the lower contour of the nose. Firstly we determine the candidate
nose area through the prior knowledge of face and the location of
two eyes. Then we extract the lower contour of the nose through
calculating the confidence of the nose edges that detected by Canny
operator. Finally, we use least square method to fit the lower
contour into parabolic curve, and then locate the nose tip. The
experiment results show that the proposed approach is accurate and
practical.

Key words: nose tip location, Canny operator, least square fitting method, face pose estimation

中图分类号:

TP391.41

刘丹, 童卫青. 基于鼻子下轮廓线的鼻尖定位法[J]. 华东师范大学学报(自然科学版), 2014, 2014(4): 54-61.

LIU Dan, TONG Wei-qing. Nose tip location based on nose contour[J]. Journal of East China Normal University(Natural Sc, 2014, 2014(4): 54-61.

参考文献

{1} HORPRASERT T, YACOOB Y, DAVIS L S. Computing 3-D head orientation from a monocular image sequence[C]//Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition. Washinglon DC: IEEE Computer Society, 1996: 242-247.
{2} 山世光, 高文, 陈熙霖. 基于纹理分布和变形模板的面部特征提取[J]. 软件学报, 2001, 12(4): 570-577.
{3} YIN L J, BASU A. Nose shape estimation and tracking for model-based coding[C]//Proc IEEE International Conference on Acoustics Speech and Signal Processing. Salt Lake City, Utah, USA: IEEE Press, 2001: 1477-1480.
{4} COOTES T F, TAYLOR C J. Active Shape Models-‘Smart Snakes’[C]//Proc.British Machine Vision Conference. Leeds: Springer-Verlag, 1992: 266-275.
{5} REN X B, SONG J T, YING H W, et al. Robust nose detection and tracking using gentle Boost and improved Lucas-Kanade optical flow algorithms[M]//Leture Notes in Computer Science 4681, 2007: 1240-1246.
{6} LIANG X, TONG W. Face pose estimation using near-infrared images[C]//International Conference on Communication Systems and Network Technologies. [S.l.]: IEEE, 2012: 216-220.
{7} CANNY J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.
{8} 金刚. 自适应~Canny~算法研究及其在图像边缘检测中的应用[D]. 杭州: 浙江大学理学院, 2009: 24-34.
{9} 关治, 陆金甫. 数值分析基础[M]. 2~版. 北京: 清华大学出版社, 2010: 256-268.
{10} SANKARAN P, GUNDIMADA S, TOMPKINS R C, et al. Pose Angle Determination by Face, Eyes and Nose Localization[C]//Proc, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). [S.l.]: IEEE, 2005: 161.
{11} CHEN L B, ZHANG L, ZHU L. A Novel Facial Feature Point Localization algorithm using Probabilistic-like output[C]//Proc Asian Conference on Computer Vision (ACCV). Jeju Island, Korea: [s.n.], 2004: 1-10.