Realizace inteligentního biometrického systému pro detekci obličeje

Abstract

The master thesis deals with the design and implementation of an intelligent biometric system enabling detection and recognition of a person's face from static image data. The theoretical part of the thesis is focused on the characteristics of biometrics and biometric systems for security identification and user verification, as well as on the description of algorithms for detection and recognition of human face. The practical part of the thesis is developed in MATLAB programming language and is primarily focused on the realization of the biometric system using Viola-Jones algorithms and convolutional neural network with pre-trained GoogLeNet. In conclusion, the robustness and effectiveness of the designed intelligent biometric system is objectively evaluated.