Recognition of facial mikrovyraziv human face

Authors

  • A. A. Yarovyi Vinnytsia National Technical University
  • S. H. Kashubin Google Switzerland GmbH, Switzerland
  • O. O. Kulyk Vinnytsia National Technical University

Keywords:

neural networks, image processing, pattern recognition, facial mikrovyrazy human face

Abstract

The particular approaches to neural network recognition of human facial microexpression are investigated. The methods combination of facial microexpression recognition using neural networks and modification of the known process of deep neural network training with restricted Boltzmann machines used to pretrain are implemented. The methods combination and proposed modification increases the recognition precision. The intelligent system, which allows neural network system training and facial microexpression recognition in real time, was developed.

Author Biographies

A. A. Yarovyi, Vinnytsia National Technical University

Dr. Sc. (Eng.), Professor, Professor of Computer Science

S. H. Kashubin, Google Switzerland GmbH, Switzerland

Master of Information Technology, Software Engineer

O. O. Kulyk, Vinnytsia National Technical University

student of Computer Science

References

1. Yang Ming-Hsuan. Detecting Faces in Images: a Survey / Yang Ming-Hsuan // IEEE Trans. Pattern Analysis and Machine Intelligence — 2002. — № 11. — P. 34—58.
2. P. Ekman. Telling Lies: Clues to Deceit in the Marketplace, Politics, and Marriage / P. Ekman. — New York: W. W. Norton & Company, 2009. — 416 p.
3. D.A. Forsyth. Computer Vision: A Modern Approach / D. A. Forsyth, J. Ponce. — New Jersey: Pearson Education, 2011. — 792 p.
4. Экман П. Психология эмоций [Emotions Revealed: Recognizing Faces and Feelings to Improve Communication and Emotional Life] / Экман П. — СПб. : Питер, 2011. — 336 с.
5. P. Ekman. Facial Action Coding System: A Technique for the Measurement of Facial Movement / P. Ekman, W. Friesen — Palo Alto: Consulting Psychologists Press, 1978. — 117 p.
6. T. Kanade. Comprehensive database for facial expression analysis / T. Kanade, J. F. Cohn, Y. Tian // Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition (FG'00) — 2000. — № 5. — P. 46—53.
7. P. Lucey. The Extended CohnKanade Dataset (CK+): A complete expression dataset for action unit and emotion-specified expression / P. Lucey, J. F. Cohn, T. Kanade, J. Saragih, Z. Ambadar,
I. Matthews // Proceedings of the Third International Workshop on CVPR for Human Communicative Behavior Analysis (CVPR4HB 2010). — 2010. — № 3. — P. 94—101.
8. V. Jain. The Indian Face Database / Vidit Jain, Amitabha Mukherjee. — Kanpur : Indian Institute of Technology Kanpur , 2002. — 25 p.
9. S. O. Haykin Neural Networks and Learning Machines, Third Edition, / S. O. Haykin. – Prentice Hall, 2009. — 936 p.
10. S. Wermter Artificial Neural Networks and Machine Learning / S. Wermter, C. Weber, W. Duch,
T. Honkela, and more — ICANN 2014: 24th International Conference on Artificial Neural Networks, Hamburg, Germany, Springer, 2014, 852 p.
11. A. A. Yarovyy Parallel-Hierarchical Computing System for Multi-Level Transformation of Masked Digital Signals / A. A. Yarovyy, L. I. Timchenko, N. I. Kokriatskaia // Advances in Electrical and Computer Engineering. — 2012. = vol. 12, no. 3. — pp. 13—20.
12. Л.И. Тимченко Теоретические и прикладные аспекты параллельно-иерархического многоуровневого преобразования цифровых сигналов / Л.И. Тимченко, А.А. Яровой, Н.И. Кокряцкая // Электронное моделирование. – 2013. – Т.35. – №2. – С. 35-54.
13. A. Yarovyy Organization of High-Performance Parallel-Hierarchical Computing Processes for Classification of Laser Beam Images. / A. Yarovyy, L. Timchenko, N. Kokriatskaia, S. Nakonechna, M. Mateichuk – Development and application systems : Proceedings of the 12th International Conference on DAS-2014, May 15-17, 2014, Suceava, Romania – Suceava, Universitatea Stefan cel Mare Suceava, 2014 – p. 192-197.
14. D. M. W. Powers Evaluation: from Precision, Recall and F-Measure to ROC, Informedness, Markedness and Correlation / D. M. W. Powers // International Journal of Machine Learning Technology, 2011, vol. 2, no. 1, pp. 37—63.
15. T. McLaughlin Emotion Recognition with Deep-Belief Networks / T. McLaughlin, M. Le,
N. Bayanbat // Stanford CS 229 Machine Learning Final Projects. — 2010. — pp. 62—66.
16. Y. Bengio. Learning Deep Architectures for AI / Y. Bengio. – Montreal: Université de Montréal, 2009. — 130 р.
17. G. E. Hinton Learning Multiple Layers of Representation / G. E. Hinton // Trends in Cognitive Sciences. — 2007. — № 11. — Р. 428—434.
18. R. R. Salakhutdinov An Efficient Learning Procedure for Deep Boltzmann Machines /
R. R. Salakhutdinov, G. E. Hinton // Neural Computation. — 2012. — Р. 1967—2006.
19. Інтелектуальна система нейромережевого розпізнавання мімічних мікровиразів обличчя людини / Кашубін С., Яровий А.: Збірник праць IX Міжнародної науково-практичної конференції [Інтернет — Освіта — Наука (ІОН-2014)], (Вінниця, 14—17 жовтня 2014 р.) — Вінниця, ВНТУ, 2014. — с. 60—62.
20. Яровий А. А. Розпізнавання мімічних мікровиразів обличчя людини на основі Time Delay Neural Network / Яровий А. А., Кашубін С. Г., Кулик О. О., Липкань І. М.// Вісник Хмельницького національного університету. Технічні науки. — 2015. — № 1. — С. 122—126.
21. A. Waibel Phoneme Recognition Using Time-Delay Neural Networks / A. Waibel, T. Hanazawa,
G. Hinton, K. Shikano, and K. Lang — IEEE Transactions on Acoustics, Speech and Signal Processing, 1989, vol. 37, no. 3, pp. 328—339.
22. S. J. Russel Artificial Intelligence: A Modern Approach / S. J. Russel, P. Norvig. — New Jersey: Pearson Education, 2010. — 1132 р.

Downloads

Abstract views: 392

Published

2015-07-20

How to Cite

[1]
A. A. Yarovyi, S. H. Kashubin, and O. O. Kulyk, “Recognition of facial mikrovyraziv human face”, Опт-ел. інф-енерг. техн., vol. 29, no. 1, pp. 76–83, Jul. 2015.

Issue

Section

Systems Of Technical Vision And Artificial Intelligence, Image Processing And Pattern Recognition

Metrics

Downloads

Download data is not yet available.

Most read articles by the same author(s)

<< < 1 2