ANALYSIS OF EMOTION RECOGNITION BASED ON DEEP CONVOLUTIONAL NEURAL NETWORK MODELS
https://doi.org/10.37493/2307-910X.2023.1.24
Abstract
Interest in facial emotion recognition is increasing and new algorithms and methods are being introduced. Recent advances in supervised and unsupervised machine learning have led to breakthroughs in research, and more and more accurate systems are emerging every year. However, despite significant progress, emotion detection remains a very challenging task. Experimental studies of emotional processes are usually based on the observation of images with affective content, including facial expressions. This paper presents the implementation of an emotional expression classifier by training a face detection algorithm on a dataset of AKDEF frontal face images (N = 4,900). The trained convolutional The purpose of the study was to present normative data regarding the recognition of six facial expressions with emotional content as well as neutral facial expressions. using a forced-choice task. In this study, agreement in recognition between the expressions depicted and chosen by the participants ranged from 70% (for anger) to 76% (for happiness). Overall, the results show a high level of recognition of the facial expressions presented, suggesting that the AKDEF provides adequate stimuli for studies examining the recognition of facial expressions of emotion. Participant gender and age had limited impact on emotion recognition, but model gender and age require additional consideration.
About the Authors
V. M. Goryaev
Kalmyk State University named after B.B. Gorodovikov
Russian Federation
Russian Federation
Vladimir M. Goryaev, Cand. Sci. (Pedag.), Associate Professor
358000, Republic of Kalmykia, Elista, Pushkin str., 11
G. A. Mankaeva
Kalmyk State University named after B.B. Gorodovikov
Russian Federation
Russian Federation
Galina A. Mankaeva, Senior Lecturer
358000, Republic of Kalmykia, Elista, Pushkin str., 11
T. B. Ochir-Goryaeva
Kalmyk State University named after B.B. Gorodovikov
Russian Federation
Russian Federation
Tamara B. Ochir-Goryaeva, Cand. Sci. (Econ.), Associate Professor
358000, Republic of Kalmykia, Elista, Pushkin str., 11
A. B. Mantusov
Kalmyk State University named after B.B. Gorodovikov
Russian Federation
Russian Federation
Anatoliy B. Mantusov, Cand. Sci. (Pedag.), Associate Professor
358000, Republic of Kalmykia, Elista, Pushkin str., 11
V. V. Lidji-Garyaev
Kalmyk State University named after B.B. Gorodovikov
Russian Federation
Russian Federation
358000, Republic of Kalmykia, Elista, Pushkin str., 11
A. B. Kornyakov
Kalmyk State University named after B.B. Gorodovikov
Russian Federation
Russian Federation
358000, Republic of Kalmykia, Elista, Pushkin str., 11
References
1. Liu Yisi, Sourina Olga and Nguyen Minh Khoa, ―Real-Time EEG-Based Emotion Recognition and Its Applications‖, Transactions on Computational Science XII: Special Issue on Cyberworlds, 2011. Рp. 256-277.
2. Stickel Christian, Ebner Martin, Steinbach-Nordmann Silke, Searle Gig and Holzinger Andreas, ―Emotion Detection: Application of the Valence Arousal Space for Rapid Biological Usability Testing to Enhance Universal Access‖, Lecture Notes in Computer Science, 2009. Vol. 5614. Рp. 615-624.
3. Aleksandrov A.A., Kirpichnikov A.P., Lyasheva S.A., Shleimovich M.P. Analiz ehmotsional'nogo sostoyaniya cheloveka na izobrazhenii // Vestnik tekhnologicheskogo universiteta. 2019. Vol. 22, No. 8. P. 120-123.
4. D. Galati , R. Miceli and B. Sini, ―Judging and coding facial expression of emotions in congenitally blind children‖, International Journal of Behavioral Development, 2001.Vol. 25, No. 3. Рp. 268-278.
5. H. A. Elfenbein and N. Ambady, ―On the universality and cultural specificity of emotion recognition: A meta-analysis‖, Psychological Bulletin, 2002, Vol. 128, No. 2. Рp. 205-235.
6. Ryumina E.V., Karpov A.A. Analiticheskii obzor metodov raspoznavaniya ehmotsii po vyrazheniyam litsa cheloveka // Nauchno-tekhnicheskii vestnik informatsionnykh tekhnologii, mekhaniki i optiki. 2020. T. 20, No. 2. P. 163-176.
7. Stepanova O.A., Ivanovskii L.I., Khryashchev V.V. Ispol'zovanie glubokogo obucheniya i svertochnykh neironnykh setei dlya analiza vyrazheniya litsa // DSPA: Voprosy primeneniya tsifrovoi obrabotki signalov. 2018. Vol. 8, No. 4. P. 170-173.
8. Livingstone S.R., Russo F.A. The Ryerson audio-visual database of emotional speech and song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English // PLoS ONE. 2018. Vol. 13, No. 5. Pр.0196391. DOI: 10.1371/journal.pone.0196391.
9. Zangeneh Soroush, Morteza & Maghooli, Keivan & Setarehdan, Kamal & Motie Nasrabadi, Ali. (2017). A Review on EEG Signals Based Emotion Recognition. International Clinical Neuroscience Journal. 4. Рр. 118-129.
10. Vahid Kazemi and Josephine Sullivan, ―One millisecond face alignment with an ensemble of regression trees‖, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014. Рp. 1867-1874.
11. Bogdanova D. R., Akushev A. T. Raspoznavanie ehmotsii po rechevomu signalu // E-Scio. 2021. No. 6 (57). P. 43-52.
12. D. Bertero and P. Fung. A first look into a Convolutional Neural Network for speech emotion detection. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017. Рp. 5115-5119, DOI: 10.1109/ICASSP.2017.7953131.
13. Peres D. Emotional Thin-Slicing: A Proposal for a Short- and Long-Term Division of Emotional Speech. 2017. Рp. 591-595. 10.21437/Interspeech.2017-1719.
14. Goryaev V.M., Bembitov D.B. i dr. Prognozirovanie stepnykh pozharov s ispol'zovaniem dannykh distantsionnogo zondirovaniya vremennykh ryadov Sovremennye naukoemkie tekhnologii. 2020. No. 12-1. P. 15-19.
15. Baez John C., Dolan James. Higher-dimensional algebra and topological quantum field theory // Journal of Mathematical Physics. 995. Vol. 36, No 11. P. 6073-6105.
16. Aggarval CH. Neironnye seti i glubokoe obuchenie: uchebnyi kurs: Per. s angl. SPb.: OOO "Dialektika", 2020. 752 p.
17. Wang Kay Ngai et al. Emotion recognition based on convolutional neural networks and heterogeneous bio-signal data sources. Information Fusion. 2022. Vol. 77. Рр. 107-117.
18. Sikorskii O.S. Obzor svertochnykh neironnykh setei dlya zadachi klassifikatsii izobrazhenii // Novye informatsionnye tekhnologii v avtomatizirovannykh sistemakh. Moskva, 2017. No. 20. P. 37-42.
19. Goryaev V.M. et al. Development of a statistical forecast model to improve accuracy based on statistical analysis of weather historical data for the kalmyk region // IOP Conference Series: Earth and Environmental Science. International Symposium on Earth Sciences: History, Contemporary Issues and Prospects. 2019. Pp. 012058.
Review
For citations:
Goryaev V.M., Mankaeva G.A., Ochir-Goryaeva T.B., Mantusov A.B., Lidji-Garyaev V.V., Kornyakov A.B. ANALYSIS OF EMOTION RECOGNITION BASED ON DEEP CONVOLUTIONAL NEURAL NETWORK MODELS. Modern Science and Innovations. 2023;(1):207-219. (In Russ.) https://doi.org/10.37493/2307-910X.2023.1.24
Views:
255
Email this article 