Lip information extraction based on the fusion of geometry and motion features
作者： Yingjie Meng , Haiyan Zhang , Yingjie Hu , Li Jinyang
DOI: 10.1109/FSKD.2011.6019998
关键词:
摘要: Lip feature information extraction decides the recognition effect in speaker identification based on shape of lip. To solve problems less useful and low rate, this paper proposed a new method lip which is fusion geometry motion features. Firstly, key points sequence images were tracked located. Then basis, characteristics extracted. Finally was got by features, result chosen similarity comparison identified. The experiment indicates that features has more comprehensive higher rate.
sci-hub.se 参考文章(8)
Kenji Mase, Alex Pentland, Automatic lipreading by optical-flow analysis Systems and Computers in Japan. ,vol. 22, pp. 67- 76 ,(1991) , 10.1002/SCJ.4690220607
Juergen Luettin, Neil A. Thacker, Speechreading using Probabilistic Models Computer Vision and Image Understanding. ,vol. 65, pp. 163- 178 ,(1997) , 10.1006/CVIU.1996.0570
T.F. Cootes, C.J. Taylor, A mixture model for representing shape variation Image and Vision Computing. ,vol. 17, pp. 567- 573 ,(1999) , 10.1016/S0262-8856(98)00175-9
Zhaoxia Li, Zhihua Guo, Yingjie Meng, Yingjie Hu, Haiyan Zhang, Feature Mouth Shapes Extraction Based on Contour of Internal Lips international conference on wireless communications, networking and mobile computing. pp. 1- 5 ,(2010) , 10.1109/WICOM.2010.5600687
G.I. Chiou, Jenq-Neng Hwang, Lipreading from color video IEEE Transactions on Image Processing. ,vol. 6, pp. 1192- 1195 ,(1997) , 10.1109/83.605417
Meng Li, Yiu-ming Cheung, A Novel Motion Based Lip Feature Extraction for Lip-Reading computational intelligence and security. ,vol. 1, pp. 361- 365 ,(2008) , 10.1109/CIS.2008.214
H.E. Cetingul, Y. Yemez, Engin Erzin, A.M. Tekalp, Discriminative Analysis of Lip Motion Features for Speaker Identification and Speech-Reading IEEE Transactions on Image Processing. ,vol. 15, pp. 2879- 2891 ,(2006) , 10.1109/TIP.2006.877528
Jing Li, Fang Zheng, J Zhang, Context dependent initial/final acoustic modeling for continuous Chinese speech recognition Journal of Tsinghua University. ,(2004)