Study and Evaluation Facial Expressions Recognition Methods

Abstract
Authors
Keywords
Conclusion
References

In recent years, facial expressions recognition has automatically attracted attention in car vision and non-linguistic communications due to its extremely important applications. The reason of the popularity is extensive applications in various fields. As a result, the implementation of Facial expressions recognition system is very important. For this purpose, various methods such as neural network, neural-Fuzzy network, fuzzy algorithms, deep learning, etc can be used. Various simulations provide different accuracy of facial expressions recognition. In this paper, different ways to identify facial expressions recognition are examined and compared in two ways, quantitative (accuracy of each method) and qualitative (statistical society, advantages, disadvantages, goals and obtained results from the method). This study can help researchers choose the best method for their research and can be familiar with the advantages and disadvantages in each method.

Published In : IJCSN Journal Volume 6, Issue 5

Date of Publication : October2017

Pages : 599-614

Figures :16

Tables : 05

Mahsa Naeeni Davarani : Department of Computer Engineering, Islamic Azad University, Central Tehran Branch, Tehran, Iran.

Touraj Banirostam : Department of Computer Engineering, Islamic Azad University, Central Tehran Branch, Tehran, Iran.

Hayedeh Saberi : Department of Psychology, Islamic Azad University, Roudehen Branch, Roudehen, Iran.

Facial expressions recognition, image based methods, feature-based methods, EEG-based methods

In this study, different techniques of face recognition and feature extraction are discussed. Pattern based methods are implemented easily but don't provide general structure of face. Appearance based methods show optimal feature points that can indicate general structure of face. Geometry based methods such as face feature extraction present stable features.

[1] M. K. Mandal, A. Awasthi, "Facial expressions to emotions: A study of computational paradigms for facial emotion recognition,"Springer Science, Chapter 9, pp. 173-198, 2015. [2] F. Song, Z. Guo, and D. Mei, "Feature selection using principal component analysis,"in System Science, Engineering Design and Manufacturing Informatization (ICSEM), International Conference on, pp. 27-30, 2010. [3] N. Sharma, India , and K. Saroha, "Study of dimension reduction methodologies in data mining,"presented at the Computing, Communication & Automation (ICCCA), International Conference on, Noida, 2015. [4] D. Deodhare, "Facial Expressions to Emotions: A Study of Computational Paradigms for Facial Emotion Recognition," Springer India, Chapter 9, pp. 173-196, 2015. [5] I. Ahmad, M. Hussain, A. Alghamdi, and A. Alelaiwi, "Enhancing SVM performance in intrusion detection using optimal feature subset selection based on genetic principal components," Neural Computing and Applications, vol. 24, pp. 1671-1682, 2014. [6] D. Suryakumar, A. H. Sung, Q. Liu," Dependence of Critical Dimension on Learning Machines and Ranking Methods," IEEE IRI, pp. 738-739, 2012. [7] U. Bakshi, R. Singhal, "A Survey on face detection methods and feature extraction techniques of face recognition,"International Journal of Emerging Trends & Technology in Computer Science, Volume 3, Issue 3, ISSN 2278-6856, 2014. [8] T. Sakai, M. Nagao, T.Kanade, " Computer analysis and classification of photographs of human face," First USA Japan Computer Conference, 1972. [9] Craw, I., Ellis, H. and Lishman, " Automatic extraction of face feature," Pattern Recog, Lett, 183-187 1987. [10] T. D. Ngo, T. H. Nhan, V. H. Nguyen, "Improving simulation of continuous emotional facial expressions by analyzing videos of human facial activities," Springer Science, LNAI 8861, pp. 222–237, 2014. [11] D. Ghimire, J. Lee, " Geometric Feature-Based Facial Expression Recognition in Image Sequences Using Multi-Class AdaBoost and Support Vector Machines,"Sensors 13, 7714–7734, 2013. [12] Rao, K.S., Saroj, V.K., Maity, S., Koolagudi, S.G.:" Recognition of emotions from video using neural network models,"Expert Systems with Applications 38, 13181–13185, 2011. [13] G. Palestra, A. Pettinicchio, M. D. Coco, "Improved performance in facial expression recognition using 32 geometric features," Springer Science, LNCS 9280, pp. 518–528, 2015. [14] Sh. Tayal, S. Vijay, "Human emotion recognition and classification from digital color images using fuzzy and PCA approach,"Springer Science, Advances in Computer Science, Eng. & Appl., AISC 167, pp. 1033–1040, 2012. [15] k. azadmanesh, R. javidan, S. E. Alavi, "Improvement of facial emotion recognition using skin color and face components,"International journal of Computer Science & Network Solutions, Volume 2, No4, ISSN 2345-3397, 2014. [16] I. Perikos, E. Ziakopoulos, I. Hatzilygeroudis, "Recognize emotions from facial expressions using a SVM and neural network schema,"Springer Science, CCIS 517, pp. 265–274, 2015. [17] M. M. Javaid, M. A.Yousaf, "Real-time EEG-based human emotion recognition,"Springer Science, LNCS 9492, pp. 182–190, 2015. [18] J. Russell, " Affective space is bipolar," Pers, Soc, Psychol 37, 345–356, 1979.