Scientific and Technical Journal

ELECTROTECHNIC AND COMPUTER SYSTEMS

ISSN Print 2221-3937
ISSN Online 2221-3805
WEIGHTED OPTICAL FLOW MODEL FOR VISEMES RECOGNITION IN SIGN LANGUAGE TUTORING SOFTWARE
Abstract:
The problem of viseme recognition in video stream is considered. The problem arises as a part of sign language understanding and translation process. An approach that uses only dynamic viseme features is proposed. A weighted optical flow model is developed for modeling these features. Initialization, join, and distance operators are defined on weighted optical flow models for training and recognition purposes. The performance of the developed method was evaluated on a database of 119 visemas that belong to five classes. The recognition rate 69% was achieved for single 
user recognition.
Authors:
Keywords
DOI
References

1. Ipsic I. Speech and Language Technologies, Rijeka, Croatia: InTech, 2011, ISBN : 978-953-307-322-4. – 344 p. (In English).

2. Davydov M.V., Nikol'skii Yu.V. and  Tikhanskii S.M. The Method for Viseme Identification in Articulation of Ukrainian Sign Language Gestures [Metod identifikatsii vizem po artikulyatsii v sostave zhesta ukrainskoi zhestovogo yazyka], Informatsionnye sistemy i seti, Vestnik National University «L'vovskaya politekhnika», Lviv, Ukraine, 2011, No 699, pp. 302-312 (In Ukrainian).

3. Patil R.A. a. and Mandal A.S.b. Features Classification Using Support Vector Machine for a Facial Expression Recognition System, Journal of Electronic Imaging. SSN: 10179909 – 2012. – 21 (4), art. no. 043003, doi: 10.1117/1.JEI.21.4.043003 (In English).4. Huang X.a.b., Zhao G.a., Zheng W.b. and others. Towards a Dynamic Expression Recognition System under Facial occlusion, Pattern Recognition Letters, 2012, 33 (16), pp. 2181-2191 (In English), ISSN: 01678655, doi: 10.1016/j.patrec.2012.07.015. 1.          Belhumeur P.N., Hespanha J.P. and Kriegman D.J. Eigenfaces vs. Fisher-Faces: Recognition Using Class Specific Linear Projection, IEEE Transactions on Pattern Analysis and Machine Intelligence,1997, 19 (7), pp. 711-720, ISSN: 01628828 (In English),doi: 10.1109/34.598228.

6. Glenn A. Martin. Lipreading by Optical Flow Correlation, Technical Report. Compute Science Department University of Central Florida, 1995, 7 p. (In English).

7. Liu J.a.b., Li T.a. and Yang J.a. Human Action Recognition Based on Latent Author-Action Models, Journal of Computational Information Systems, pp. 10485 -10492 (In English), ISSN: 15539105 (2012) 8 (24).

8. Alin G., Rothkrantz L., Wojdel J. and others. Comparison Between Different Feature Extraction Techniques for Audio-Visual Speech Recognition, Journal on Multimodal User Interfaces, Springer, 2007, pp. 7-20 (In English).

9. Karlsson S.M. andBigun J.Lip-Motion Events Analysis and Lip Segmentation Using Optical Flow,Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE Com. Soc. Conference on2012 IEEE Computer Society Conference on.16-21 June 2012, pp.138-145(In English).

10. Paul Viola andMichael Jones.Robust Real-time Object Detection, International Journal of Computer Vision (2001), Citeseer,Vol. 57, Iss. 2, pp. 137-154(In English).

11. Schneiderman H. and H.T. Kanade. A Statistical Method for 3D Object Detection Applied to Faces and Cars, Computer Vision and Pattern Recognition, 2000. – IEEE Conf. on, Vol. 1, pp. 746-751 (In English).

12. Cheng Y. Mean Shift, Mode Seeking, and Clustering, Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol. 17, Iss. 8, 1995, pp. 790-799 (In English).

13. Shrinivasa Maika C.L., Vibhor Nikhra, Shashishekha R. Jha and others. An Intelligent Face Tracking System for Human-Robot Interaction Using Camshift Tracking Algorithm, International Journal of Machine Intelligence. Vol. 3, Iss. 4, 2011, pp. 263-267 (In English). ISSN : 0975–2927 & E-ISSN: 0975–9166. 

14. Liu H., Chellappa R. and Rosenfeld A. Accurate Dense Optical Flow Estimation Using Adaptive Structure Tensors and a Parametric Model, Image Processing, IEEE Transactions on, Vol. 12, No. 10, Oct. 2003, pp. 1170-1180 (In English).

15. Lucas B. D. and Kanade T. An Iterative Image Registration Technique with an Application to Stereo Vision, Proceedings of Imaging Understanding Workshop, 1981, pp. 121-130 (In English).

16. JianboShi and Carlo Tomasi.Good Features To Track, IEEE Conference on Computer Vision and Pattern Recognition Seattle, June 1994, pp. 593-600(In English).

17. Krak Yu. andTernov A.A.Synthesis of Mimicry and Emotions is on Face of Man for the Design of Gesture Language, [Sintez mimiki i emotsii na litse cheloveka dlya modelirovaniya zhestovogo yazyka],  Vestnik Kievskogo natsional'nogo universiteta im. Tarasa Shevchenko. Kibernetika. Proceedings of Taras Shevchenko National University of Kyiv, Cybernetics,Kyiv University, Kyiv, Ukraine, No 10, 2010, pp.52-55 (In Ukrainian), ISSN: 1728-2276.

Published:
Last download:
2017-11-22 15:37:15

[ © KarelWintersky ] [ All articles ] [ All authors ]
[ © Odessa National Polytechnic University, 2014. Any use of information from the site is possible only under the condition that the source link! ]
Яндекс.Метрика