Abstract
With the widespread use of smart devices, finding effective and intuitive ways of interaction becomes a real challenge. One of the most relevant sources of information remains the facial expressions. Indeed, they provide various information related to the user such as his emotional state. In the last years, several methods of automatic facial expression recognition based on deep learning algorithms have been proposed. Even if they achieve high accuracy in terms of recognition, they require high-performance hardware and huge training datasets. In this paper, we propose an automatic facial expression recognition approach based on the Histogram of Oriented Gradients along with two distinct dimensionality reduction techniques namely Principal Component Analysis and Autoencoder. The proposed approach allows recognizing the six basic emotions using a multi-class Support Vector Machine. We evaluated its performance with three facial expression datasets namely JAFFE, RaFD and KDEF. The obtained results attest to its efficiency with \(93.75\%\), \(87.26\%\), and \(96.27\%\), respectively.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ali, A.M., Zhuang, H., Ibrahim, A.K.: An approach for facial expression classification. IJBM 9(2), 96–112 (2017)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Schmid, C., Soatto, S., Tomasi, C. (eds.) CVPR vol. 1, pp. 886–893. IEEE Computer Society (Jun 2005)
Ekman, P., Friesen, W.V.: Constants across cultures in the face and emotion. J. Pers. Soc. Psychol. 17(2), 124–129 (1971)
González-Hernández, F., Zatarain-Cabada, R., Barrón-Estrada, M.L., Rodríguez-Rangel, H.: Recognition of learning-centered emotions using a convolutional neural network. JIFS 34(5), 3325–3336 (2018)
Happy, S., Routray, A.: Robust facial expression classification using shape and appearance features. In: ICAPR, pp. 1–5. IEEE (2015)
Kazemi, V., Sullivan, J.: One millisecond face alignment with an ensemble of regression trees. In: CVPR, pp. 1867–1874 (2014)
Langner, O., Dotsch, R., Bijlstra, G., Wigboldus, D.H., Hawk, S.T., Van Knippenberg, A.: Presentation and validation of the radboud faces database. Cogn. Emot. 24(8), 1377–1388 (2010)
Liu, Y., Li, Y., Ma, X., Song, R.: Facial expression recognition with fusion features extracted from salient facial areas. Sensors 17(4), 712 (2017)
Liu, Z.T., Li, S.H., Cao, W.H., Li, D.Y., Hao, M., Zhang, R.: Combining 2d gabor and local binary pattern for facial expression recognition using extreme learning machine. JACIII 23(3), 444–455 (2019)
Lundqvist, D., Flykt, A., Öhman, A.: The karolinska directed emotional faces - kdef, cd rom from department of clinical neuroscience, psychology section, karolinska institutet (1998)
Lyons, M., Akamatsu, S., Kamachi, M., Gyoba, J.: Coding facial expressions with gabor wavelets. In: AFGR, pp. 200–205. IEEE (1998)
Meena, H.K., Joshi, S.D., Sharma, K.K.: Facial expression recognition using graph signal processing on hog. IETE J. Res., 1–7 (2019)
Mehrabian, A.: Communication without words, pp. 51–52. Transaction Publishers, 2 edn. (1968)
Nurzynska, K.: Emotion recognition: the influence of texture’s descriptors on classification accuracy. In: BDAS, pp. 427–438. Springer (2017)
Olivares-Mercado, J., Toscano-Medina, K., Sanchez-Perez, G., Portillo-Portillo, J., Perez-Meana, H., Benitez-Garcia, G.: Analysis of hand-crafted and learned feature extraction methods for real-time facial expression recognition. In: IWBF, pp. 1–6. IEEE (2019)
Yaddaden, Y., Adda, M., Bouzouane, A., Gaboury, S., Bouchard, B.: Facial expression recognition from video using geometric features. In: ICPRS, pp. 1–6. IET (2017)
Yaddaden, Y., Adda, M., Bouzouane, A., Gaboury, S., Bouchard, B.: Facial sub-regions for automatic emotion recognition using local binary patterns. In: SIVA, pp. 1–6. IEEE (2018)
Yaddaden, Y., Adda, M., Bouzouane, A., Gaboury, S., Bouchard, B.: Hybrid-based facial expression recognition approach for human-computer interaction. In: MMSP, pp. 1–6. IEEE (2018)
Yaddaden, Y., Adda, M., Bouzouane, A., Gaboury, S., Bouchard, B.: One-class and bi-class SVM classifier comparison for automatic facial expression recognition. In: ICASS, pp. 1–6. IEEE (2018)
Yaddaden, Y., Adda, M., Bouzouane, A., Gaboury, S., Bouchard, B.: User action and facial expression recognition for error detection system in an ambient assisted environment. ESWA 112, 173–189 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yaddaden, Y., Adda, M., Bouzouane, A. (2021). A Study of Dimensionality Reduction for Facial Expression Recognition. In: Senouci, M.R., Boudaren, M.E.Y., Sebbak, F., Mataoui, M. (eds) Advances in Computing Systems and Applications. CSA 2020. Lecture Notes in Networks and Systems, vol 199. Springer, Cham. https://doi.org/10.1007/978-3-030-69418-0_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-69418-0_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-69417-3
Online ISBN: 978-3-030-69418-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)