采用非对称唇形轮廓模型提高汉语唇形识别效果

李 刚; 王蒙军; 林 凌

doi:null

您当前的位置：

首页 >

文章列表页 >

采用非对称唇形轮廓模型提高汉语唇形识别效果

更新时间：2020-08-12

- 采用非对称唇形轮廓模型提高汉语唇形识别效果
- Improving Chinese lip-reading recognizing rate by unsymmetrical lip contour model
- 光学精密工程 2006年14卷第3期页码：473-476
- 作者机构：
  
  天津大学精密仪器与光电子工程学院天津,300072
- 作者简介：
- 基金信息：
- DOI：
  中图分类号： TP391.43
- 收稿日期：2005-12-20，
  
  修回日期：2006-02-14，
  
  网络出版日期：2006-06-30，
  
  纸质出版日期：2006-06-30
- 稿件说明：
移动端阅览
李刚, 王蒙军, 林凌. 采用非对称唇形轮廓模型提高汉语唇形识别效果[J]. 光学精密工程, 2006,14(3):473-476.

LI Gang, WANG Meng-jun, LIN Ling. Improving Chinese lip-reading recognizing rate by unsymmetrical lip contour model[J]. Optics and precision engineering, 2006, 14(3): 473-476.
李刚, 王蒙军, 林凌. 采用非对称唇形轮廓模型提高汉语唇形识别效果[J]. 光学精密工程, 2006,14(3):473-476. DOI：

LI Gang, WANG Meng-jun, LIN Ling. Improving Chinese lip-reading recognizing rate by unsymmetrical lip contour model[J]. Optics and precision engineering, 2006, 14(3): 473-476. DOI：

摘要

通过分析人脸正面和侧面图像的特点

建立起一种新的唇形轮廓描述模型

能够提取出嘴唇的突出度信息

同时通过计算部分参数对时间的导数

来获得唇形轮廓的动态信息。通过对小词库试验

对比单纯采用正面图像轮廓的描述方法

该方法能够将识别效果平均提高25%以上

克服了以往对唇形轮廓提取时

通常都采用人脸的正面图像

不能反映出嘴唇的突出度信息的局限。

Abstract

Based on analyzing the side-face image and full-face image

a new model was presented to extract the degree of pouting from a lip contour. At the same time

the differential coefficient of some parameters to describe dynamic characteristic of the lip contour were calculated. Experimental results based on a small database of Chinese words show that the parameters from unsymmetrical lip contour model improve the recognizing rate in more than 25%

which is superior to those of the traditional symmetrical lip contour model.

关键词

Keywords

references

. 梁毅雄,龚卫国,潘英俊,等. 基于奇异值分解的人脸识别方法[J]. 光学精密工程,2004,12(5):543-549. LIANG Y X,GONG W G,PAN Y J,et al.Singular value decomposition-based approach for face recognition[J].Optics and Precision Engineering, 2004, 12(5):543-549.(in Chinese)

. WANG R,YAO H X,GAO W.Recognition of sequence lip images and its application . IEEE Fourth International Conference on Signal Processing, 1998, (Ⅰ):849-854.

. MATTHEWS I,COOTES T F,BANGHAM J A,et al.Extraction of visual features for lip reading[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24 (2):198-213.

. SCANLON P,REILLY R.Feature analysis for automatic speech reading .IEEE Fourth Workshop on Multimedia Signal Processing, 2001, Page(s):625-630.

. ZHANG X,MERSEREAU R M,CLEMENTS M,et al.Visual speech feature extraction for improved speech recognition . Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, 2002, 2:1993-1996.

. 王志明,蔡莲红. 汉语语音视位的研究[J]. 应用声学,2002.21(3):29-34. WANG Z M,CAI L H.Study of Chinese viseme[J].Applied Acoustics, 2002, 21(3):29-34.(in Chinese)

. SEGUIER R, CLADEL N.Multiobjectives genetic snakes: application on audio-visual speech recognition . Fourth EURASIP Conference focused on Video/Image Processing and Multimedia Communications, 2003:625-630.

. 姚鸿勋,高文,李静梅,等. 用于口形识别的实时唇定位方法[J]. 软件学报,2000.11(8):1126-1132. YAO H X, GAO W, LI J M, et al.Real-time lip locating method for lip-movement recognition[J].Journal of Software, 2000, 11(8):1126-1132.(in Chinese)

. CHANDRAMOHAN D, SILSBEE P L.A multiple deformable template approach for visual speech recognition . Fourth International Conference on Spoken Language, 1996, 1:50-53.

. 王磊,莫玉龙,戚飞虎. 基于于弹性模板的嘴巴轮廓提取[J]. 上海大学学报(自然科学版),1998,4(5):579-585. WANG L, MO Y L, QI F H.Mouth feature extraction based on deformable template .Journal of Shanghai University (Natural Science),1998,4(5):579-585.(in Chinese)

. 晏洁. 文本驱动的唇动合成系统[J]. 计算机工程与设计,1998.19(1):31-34. YAN J.Text-driven lip motion synthesis system[J].Computer Engineering and Design, 1998, 19(1):31-34. (in Chinese)

. 王波波,来忠信,黄廉卿,等. 基于多尺度隐马尔可夫模型的CR影像降噪方法研究[J]. 光学精密工程,2000.10(2):188-193. WANG B B,LAI Z X,HUANG L Q,et al.MHMM-based computed radiography image-denoising method[J].Optics and Precision Engineering, 2002, 10(2):188-193.(in Chinese)

浏览量

259

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

视觉驱动的语音合成系统中唇形轮廓的正交变换描述