The method of basis vectors for recognition sign language by using sensor KINECT

Authors

  • S. A. Kudubayeva A.Baitursynov Kostanay state university
  • D. A. Ryumin A.Baitursynov Kostanay state university
  • M. U. Kalzhanov Kostanay state pedagogical university
        89 51

Keywords:

Kazakh Sign Language, dactyl, image recognition, segmentation, video file

Abstract

For signs recognition different methods, such as the method of reference vectors, hidden Markov models, fuzzy models, the model of artificial neuron, image difference method are used. The tasks of recognition of gestural speech of any language are characterized by many parameters. First of all this is characteristics of the transmission channel of gestural speech, recognition vocabulary scope, the variability of gestures, etc. Besides technical and economic problems Kazakh speech technologies development, among which there is Sign language recognition, are firstly influenced by peculiarities of the Kazakh Language and speech (many rules of word formation, seven cases of nouns, territorial varieties of the Kazakh language and speech) causing difficulties in automatic processing. The development of Kazakh Sign Language database consisting of 42 gestures is the first step in designing the system of automatic recognition of separate hand gestures. For gestures recognition Kinect sensor, hand skeleton coordinates obtained via it and key characteristics processed through XML files via tools and mathematic calculations in MATLAB are used. Gestures recognition objects in this article are letters, digits and some gestures in static form.

References

[1] Kotelnikov Ye.V. Parallel Implementation of Reference Vectors Machine Using Clustering Method / Ye.V. Kotelnikov, А.V. Kozvonina // Proceedings of the international scientific conference "Parallel Computing Technologies". – St. Petersburg , 2008.
[2] Kudubayeva S., Yermagambetova G. "Parametric representation of the Kazakh gestural speech" Lectures Notes in Artificial Intelligence in Bioinformatics, SPECOM-2014.
[3] Krak Iu, Kudubayeva S. "System for Sign Language Modeling and Learning" 8Th IEEE International Conference on Application of Information Technology, Astana, 2014.
[4] Farkhadov M.P., Kudubayeva S.A., Ermagambetova G.N. Theory of Hidden Markov Models and its Implementation for Speech Recognition // science journal "Herald of L.N Gumilyov ENU" , Astana, November 2013.
[5] Farkhadov M.P., Kudubayeva S.A., Ermagambetova G.N. Acoustic simulator for the hearing impaired people // American International Journal of Contemporary Research, USA, Vol. 3 No. 11; November 2013.
[6] Kudubayeva S.A., Ermagambetova G.N. To the problem of speech recognition // American International Journal of Contemporary Research, USA, Vol. 3 No. 11; November 2013.
[7] Kudubayeva S.A., Ermagambetova G.N. Problem of Kazakh Gestural Speech Recognition// International Satpaev Readings – 2014 "Role and Place of Young Scientists in Implementation of "Kazakhstan-2050" Strategy" dedicated to 80 th anniversary of K.I. Satpaev KazNTU, Almaty, April 11-12, 2014.
[8] Krak Yu., Kudubayeva S., Ermagambetova G. Sing Language and Problems of its Recognition // Proceedings of IV International scientific theoretical conference "The Role of Physical Mathematical Sciences in Modern Educational Space" , Kh. Dosmukhamedov Atyrau state university, Atyrau, April 24-25, 2014.
[9] Fissenko V.Т., Fissenko Т.Yu. Computer Processing and Image Recognition / V.Т. Fissenko, Т.Yu. Fissenko // Manual, Spb SRU IТМО, 2008. – P. 68-71. 192 p.
[10] MathWorks - Makers of MATLAB and Simulink [Electronic resource] – Access mode: http://www.mathworks.com (reference date: 20.03.2016).
[11] OpenGL - The Industry Standard for High Performance Graphics [Electronic resource] – Access mode: https://www.opengl.org (reference date: 20.02.2016).
[12] OpenCV [Electronic resource] – Access mode: http://opencv.org (reference date обращения: 20.04.2016).
[13] Kinect for Windows SDK 2.0 [Electronic resource] – Access mode: https://www.microsoft.com/en-us/download/details.aspx?id=44561 (reference date: 20.01.2016).
[14] https://www.surdo.kz

Downloads

How to Cite

Kudubayeva, S. A., Ryumin, D. A., & Kalzhanov, M. U. (2018). The method of basis vectors for recognition sign language by using sensor KINECT. Journal of Mathematics, Mechanics and Computer Science, 91(3), 86–96. Retrieved from https://bm.kaznu.kz/index.php/kaznu/article/view/541