Lip-reading detection and localization based on two stage ellipse fitting

Author

Huang, Yong-hui ; Pan, Bao-chang ; Zheng, Sheng-lin ; Pan, Jianjia ; Tang, Yuanyan

Author_Institution

Fac. of Autom., Guangdong Univ. of Technol., Guangzhou

Volume

1

fYear

2008

fDate

30-31 Aug. 2008

Firstpage

168

Lastpage

171

Abstract

A method of detection and localization in lip-reading system based on least square fitting and two stage ellipse fitting was proposed in this paper. Firstly, color space transformation in simple background facial images was made to simply and fast detect skin regions and get threshold for segmenting lip area; secondly, according to two stage ellipse fitting based on least square, lip image are gained. Results show that this method is more effective in fitting effect than algebraic distance fitting. And the computational efficiency is improved compared with geometric distance fitting, and the goal of recognition in lip-reading system could also be archived. Experimental set was limited in sample space of specific speaker and in image sequence features of 403 speech video files, the recognition rate can get up to 90.9%.

Keywords

face recognition; feature extraction; image colour analysis; image segmentation; image sequences; least squares approximations; speaker recognition; algebraic distance fitting; background facial image; color space transformation; feature extraction; geometric distance fitting; image segmentation; image thresholding; least square fitting; lip-reading detection; two stage ellipse fitting; Feature extraction; Image color analysis; Image recognition; Image segmentation; Image sequences; Least squares methods; Pattern analysis; Pattern recognition; Space technology; Wavelet analysis; Least square fitting; Lip-reading; Two stage ellipse fitting;

fLanguage

English

Publisher

ieee

Conference_Titel

Wavelet Analysis and Pattern Recognition, 2008. ICWAPR '08. International Conference on

Conference_Location

Hong Kong

Print_ISBN

978-1-4244-2238-8

Electronic_ISBN

978-1-4244-2239-5

Type

conf

DOI

10.1109/ICWAPR.2008.4635770

Filename

4635770