RECOGNITION OF EMOTIONS BY FACIAL GEOMETRY USING A CAPSULE NEURAL NETWORK
Journal Title: International Journal of Civil Engineering and Technology - Year 2019, Vol 10, Issue 3
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.
Authors and Affiliations
LIUDMYLA TEREIKOVSKA, IHOR TEREIKOVSKYI, SHYNAR MUSSIRALIYEVA, GULMARAL AKHMED, AIMAN BEKETOVA and AIZHAN SAMBETBAYEVA
Keywords
Related Articles
- EP ID EP46644
- DOI -
- Views 192
- Downloads 0
MODELLING OF CRYSTAL GROWTH IN PEAT SOIL STABILIZED WITH MIXING OF LIME CACO3 AND FLY ASH
Peat soil stabilization produces improved parameters because of the admixture added to form crystals that fill the pore and wrap the peat soil. Crystal growth is strongly influenced by the filtration of water from its...
WOMEN AGAINST CEMENT: ENVIRONMENTAL ACTIVISM IN THE KENDENG MOUNTAIN RANGE OF CENTRAL JAVA INDONESIA
This article seeks to discuss the women’s environmental activism as manifested in their involvement in the contemporary anti-cement movement in the Kendeng Mountain Range of Central Java. Three major issues are dealt w...
USE OF MERAUKE FINE AGGREGATE AND DIGOEL BOVEN COARSE AGGREGATE ON CONCRETE COMPRESSIVE STRENGTH
The increasing development needs in the construction sector indirectly require the availability of substantial material in the area. The use of concrete materials in Merauke Regency is currently increasing, so that the...
COMPARATIVE ANALYSIS OF COVENTIONAL AND NITRILE BUTADIENE RUBBER MODIFIED BITUMINIOUS MIX
High vehicular traffic and various climatic conditions brings damage to bituminous pavements design with conventional bituminous materials. To tackle the adverse deterioration of pavement, best coherent method is alter...
STRENGTH CHARACTERISTICS OF ALCCOFINE BASED LIGHT WEIGHT CONCRETE
Concrete being an important material for construction of various structures has severe demand in the present trend of construction industry. Aggregate occupies the major quantity (70% approx.) of concrete based on whic...