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 199
- Downloads 0
THE DAMASCENE ARCHITECTURE OF THE POST-OTTOMAN PERIOD AND THE INFLUENCE OF EUROPEAN CULTURE (BAROQUE STYLE) ON THE DAMASCENE TRADITIONAL HOUSE (POST-NINETEENTH CENTURY - THE BEGINNING OF THE TWENTIETH CENTURY)
In the subsequent period of the Ottoman Empire between both the nineteenth and twentieth century's, Syria undertook substantial changes, which led to the emergence and development of European forms in art and architect...
DESIGN OF A BEVERAGE CAN CRUSHER: A LEAN THINKING SOLUTION FOR ENVIRONMENTAL SUSTAINABILITY IN FOOD AND BEVERAGE INDUSTRIES
The study focused on the design of an aluminium can crusher that can be used domestically to crush empty beverage can and return them to the industry in order to encourage sustainability in the beverage manufacturing s...
INFLUENCE OF LECTURERS PERCEPTION IN PRACTICING OF WORK MOTIVATION IN SMART CAMPUS UNIVERSITY
This study aims to look at the lecturers’ perception of the dimension of the study centers chairperson's leadership style. Therefore, this study seeks to identify two dimensions of chairperson’s leadership style, namel...
IMPLEMENTING THE ELEMENT OF ISLAMIC PERSPECTIVE VIEW IN MENTAL HEALTH PROBLEMS
Scholars emphasized that the practice of the riya’will be punished and even the nature riya’itself will bring the anger and torment of Allah S.W.T. The nature of riya depends on the quality, purity, and sincerity of th...
ALGORITHM OF FORMING KNOWLEDGEBASE FOR DECISION TAKING SUPPORT SYSTEMS IN CYBER SECURITY TASKS
In the article herein, we offer the total structure of modular decision taking support system in cyber security tasks. There is described the model for fuzzy inference subsystem. Being based on the fuzzy inference rule...