Development of a WEB Service for Emotional Expression Recognition

This diploma thesis deals with the development of a web application for recognizing emotions in images and videos. The purpose of the work is to develop a convenient distributed microservice system with a graphical interface that allows users to explore information about the dataset on which the model was trained, start the process of recognizing emotions in images or videos, train a new neural network model with specified hyperparameters and monitor metrics during this process. During the thesis work, existing face analysis solutions were analyzed, methods for face analysis and emotion recognition were studied, and the solution architecture of the application as a whole was defined. The result of the work is a web application with a graphical interface with the above-mentioned features. Further research on the thesis may include additional research to improve the quality of face detection, emotion recognition, as well as the development of the solution architecture. From the additional functionality in the aftermath of those studies, emotion recognition based on webcam stream can be added.