计算机科学 ›› 2014, Vol. 41 ›› Issue (5): 296-298.doi: 10.11896/j.issn.1002-137X.2014.05.063

• 图形图像与模式识别 • 上一篇    下一篇

基于嘴部状态分类的内唇开度估计算法

黄秀清,黄巍,高强,陆云,陈传波   

  1. 武汉工程大学计算机科学与工程学院 武汉430205;武汉工程大学计算机科学与工程学院 武汉430205;武汉工程大学计算机科学与工程学院 武汉430205;武汉工程大学计算机科学与工程学院 武汉430205;华中科技大学软件学院 武汉430074
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受湖北省教育厅基金项目:多子模式非对称逆布局图像表示方法研究(Q20101502)资助

Algorithm of Estimating Inner Lip Opening Distance Based on Classification of Mouth States

HUANG Xiu-qing,HUANG Wei,GAO Qiang,LU Yun and CHEN Chuan-bo   

  • Online:2018-11-14 Published:2018-11-14

摘要: 为了准确地识别嘴部张合程度,提出了一种基于嘴部状态分类的内唇开度估计算法。将嘴部局部图像从RGB空间转化到YIQ空间,利用牙齿、嘴唇和舌头所对应的Q值的极值点数量和位置分布将嘴部状态分为3类,对每一类分别确定不同的一阶差分范围,使得能在有舌头、牙齿存在的情况下准确地定位出内唇边界点的位置,进而计算出内唇开度值。实验结果表明,基于嘴部状态分类的内唇开度估计算法计算出的内唇开度估计值与实际值之间的相关度达95%,比经典的Saha方法提高了5%。

关键词: 内唇开度,唇读,YIQ,嘴唇轮廓,Adaboost

Abstract: In order to recognize the distance of mouth opening,this article proposed an algorithm of estimating inner lip opening distance based on the classification of mouth states.Firstly,we converted mouth images to YIQ space from RGB space.Then making use of the number and position of extreme points of Q value in tooth,lip and tongue,we classified mouth states into three categories and decided the range of the first difference from different categories.Thus,we could localize the position of the boundary points of inner lip more precisely and compute the opening distance of inner lip in the condition of tooth and tongue.The experimental results show the related coefficient computed by our method is 0.95while method based on contrast enhancement with multi-threshold binarization is 0.90.Our algorithm improves 5percent in related coefficient between actual values and estimated values of inner lip opening.

Key words: Inner lip opening distance,Lip reading,YIQ,Lip contour,Adaboost

[1] 邬敏杰,穆平安,张彩艳.基于眼睛和嘴巴状态的驾驶员疲劳检测算法[J].计算机应用与软件,2013,30(3):25-27
[2] 李敏.基于眼部和嘴部特征融合的驾驶员疲劳检测方法研究[D].杭州:浙江师范大学,2011
[3] M Ying-jie,H Ying-jie,Z Hai-yan,et al.Feature mouth shapes extraction based on contour of internal lips[C]∥2010International Conference on Wireless Communications Networking and Mobile Computing (WiCOM).IEEE press,2010:1-5
[4] 柴秀娟,姚鸿勋,高文,等.唇读识别中的基本口型分类[J].计算机科学,2002,29(2):130-133
[5] Z Yi,L Quan-jie,L Yan-hua,et al.Intelligent wheelchair multi-modal human-machine interfaces in lip contour extraction based on PMM[C]∥2009IEEE International Conference on Robotics and Biomimetics (ROBIO).IEEE,2009:2108-2113
[6] Kass M,Witkin A,Terzopoulos D.Snakes:Active contour mo-dels[J].International Journal of Computer Vision,1988,1(4):321-331
[7] Feng X,He Q,Wang W.An improved GAC model for lip contour detection[C]∥ 9th International Conference on Signal Processing,2008(ICSP 2008).IEEE,2008:1215-1218
[8] Saha S,Pandey P C.Estimation of the area of mouth opening during speech production[C]∥Proceedings of the Eighth Indian Conference on Computer Vision,Graphics and Image Proces-sing.ACM,2012:27
[9] Viola P,Jones M J.Robust real-time face detection[J].International Journal of Computer Vision,2004,57(2):137-154
[10] Freund Y,Schapire R E.A decision-theroretic generalization of on-line learning and an application to boosting[C]∥Computational Learning Theory:Eurocolt 95.Springer-Verlag,1995:23-37
[11] Hsu R L,Abdel-Mottaleb M,Jain A K.Face detection in colorimages[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):696-706
[12] Nayak N S,Velmurugan R,Pandey P C,et al.Estimation of lip opening for scaling of vocal tract area function for speech trai-ning aids[C]∥Proc.18th National Conf.Comm.Kharagpur,2012:1-5

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!