Інтелектуальні технології розпізнавання емоцій за зображенням обличчя з використанням CNN

Abstract

This work is devoted to the development of an intelligent emotion recognition system based on facial images using convolutional neural networks. The main stages of data preprocessing, CNN architecture design and model training are considered. A comparative analysis of the quality of emotion classification using different model configurations and training parameters is carried out. The results show that the proposed approach provides stable recognition accuracy on the test dataset and can be used as a basis for human-computer interaction systems