Recognition of Emotions by Facial Geometry Using a Capsule Neural Network

International Journal of Civil Engineering and Technology, 10(3), 2019,pp. 1424-1434

11 Pages Posted: 2 Oct 2019

See all articles by Liudmyla Tereikovska

Liudmyla Tereikovska

Kyiv National University of Construction and Architecture, Kyiv, Ukraine

Ihor Tereikovskyi

Faculty of Applied Mathematics, National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", Kyiv, Ukraine

Shynar Mussiraliyeva

Department of Information Systems, Al-Farabi Kazakh National University, Almaty, Kazakhstan

Gulmaral Akhmed

Department of Information Systems, Al-Farabi Kazakh National University, Almaty, Kazakhstan

Aiman Beketova

Department of Information Systems, Al-Farabi Kazakh National University, Almaty, Kazakhstan

Aizhan Sambetbayeva

Department of Information Systems, Al-Farabi Kazakh National University, Almaty, Kazakhstan

Date Written: September 20, 2019

Abstract

The article is devoted to the problem of improving the efficiency of neural network means of emotion recognition by the geometry of the human face. It is shown that one of the most significant drawbacks of modern neural network means of emotion recognition, which are used in General-purpose information systems, is the lack of recognition accuracy under the influence of characteristic interference. It is proposed to improve the accuracy of recognition through the use of capsule neural network model, which has increased adaptability to the analysis of noisy images. As a result of the research, a neural network model of the CapsNet type was developed, designed to recognize basic emotions taking into account such interference as face rotation. It is shown experimentally that in the analysis of undistorted images CapsNet slightly exceeds the accuracy of the classical convolutional neural network type LaNet, which is approximately equal to its resource intensity. The accuracy of CapsNet recognition of undistorted images is somewhat inferior to modern types of convolution networks, which have a much higher resource consumption compared to it. When detecting emotions on rotated images, the accuracy of CapsNet is comparable with the accuracy of modern types of convolution networks and significantly exceeds the accuracy of LaNet. Prospects for further research in the field of neural network recognition of emotions on the geometry of the face can be associated with the improvement of architectural solutions of the capsule neural network in the direction of reducing the number of training iterations while ensuring acceptable recognition accuracy.

Keywords: neural network model, recognition of emotions, a capsule of neural network, face geometry, convolutional neural network

Suggested Citation

Tereikovska, Liudmyla and Tereikovskyi, Ihor and Mussiraliyeva, Shynar and Akhmed, Gulmaral and Beketova, Aiman and Sambetbayeva, Aizhan, Recognition of Emotions by Facial Geometry Using a Capsule Neural Network (September 20, 2019). International Journal of Civil Engineering and Technology, 10(3), 2019,pp. 1424-1434. Available at SSRN: https://ssrn.com/abstract=3457106

Liudmyla Tereikovska

Kyiv National University of Construction and Architecture, Kyiv, Ukraine ( email )

Ulitsa Vladimirskaya, 60
Kyiv, 01601
Ukraine

Ihor Tereikovskyi

Faculty of Applied Mathematics, National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", Kyiv, Ukraine ( email )

Ukraine

Shynar Mussiraliyeva (Contact Author)

Department of Information Systems, Al-Farabi Kazakh National University, Almaty, Kazakhstan ( email )

Almaty
Kazakhstan

Gulmaral Akhmed

Department of Information Systems, Al-Farabi Kazakh National University, Almaty, Kazakhstan ( email )

Almaty
Kazakhstan

Aiman Beketova

Department of Information Systems, Al-Farabi Kazakh National University, Almaty, Kazakhstan ( email )

Almaty
Kazakhstan

Aizhan Sambetbayeva

Department of Information Systems, Al-Farabi Kazakh National University, Almaty, Kazakhstan ( email )

Almaty
Kazakhstan

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
36
Abstract Views
164
PlumX Metrics