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 194
- Downloads 0
IMPACT OF GREEN GUIDE ON DESIGN
This manuscript will introduce a set of analysis established for the sake of design changes of a customary swimming pool and leisure facility. The classification of design changes are manipulated by The Green Guide for...
THE COMPLEMENT METRIC DIMENSION OF GRAPHS AND ITS OPERATIONS
Let G be a connected graph with vertex set V(G) and edge set E(G). The distance between vertices u and v in G is denoted by d(u, v), which serves as the shortest path length from u to v. Let be an ordered set, and v is...
VALUES, ATTITUDE TO CHANGE, AND LEADERSHIP EFFECTIVENESS OF EXECUTIVE OFFICER IN SOUTHERN SUMATRA
This study aimed to determine the influence of leadership values on the leader attitude to change and the leadership effectiveness. The population in this study were 334 large-scale manufacturing industries in Southern...
FUZZY KNOWLEDGE BASE SYNTHESIS OF THE EXPERIENCE LEVEL CLASSIFICATION OF AVIATION SECURITY SCREENERS USING SUB-TRACTIVE CLUSTERING AND ANFIS-TRAINING
This paper describes a new approach to the estimate reliability improvement of the competence related to the visual searching for prohibited items by aviation security screeners consisting in the application of fuzzy k...
EFFECT OF USING BANANA FIBRE AND ZEOLITE AS AN ADDITIVE ON THE ENGINEERING PROPERTIES OF BITUMINOUS CONCRETE
Generally, bitumen mix comprises of coarse aggregate, fine aggregate, filler and binder material but in order to improve the engineering properties of the mix, the need for the suitable material arises which enhance th...