Raster graphics mapping on human face in augmented reality
Mapování rastrové grafiky na lidskou tvář ve smíšené realitě
Authors
Supervisors
Reviewers
Editors
Other contributors
Journal Title
Journal ISSN
Volume Title
Publisher
České vysoké učení technické v Praze
Czech Technical University in Prague
Czech Technical University in Prague
Date
Abstract
Táto práca sa zaoberá problematikou vytvárania jednoduchých tvárových filtrov za pomoci knižnice OpenCV. Cieľom je vytvoriť prototyp aplikácie schopnej tvorby a mapovania rastrovej grafiky na orientačné body tváre v zmiešanej realite. Na detekciu tvárí bola použitá Haar-like casscade detekcia a na tvárové črty algoritmus regresných lokálnych binárnych príznakov. Výsledkom je funkčná počítačová aplikácia pre systém Windows z jednoduchým užívateľským rozhraním. Umožňuje užívateľovi intuitívnu tvorbu jednoduchej grafiky, ktorú aplikácia následne pretransformuje a mapuje na črty tváre detekovanej vo vstupnom videu webkamery.
This work deals with the issue of creating simple face filters using the OpenCV library. The aim is to create a prototype application capable of creating and mapping raster graphics on the landmarks of the face in augmented reality. Haar-like casscade detection was used for face detection and a regression local binary features algorithm for facial landmarks. Currently, a Windows computer application with a simple user interface is fully functional. It provides the user with intuitive creation of simple graphics, which the application then transforms and maps onto facial features detected in the webcam's input video.
This work deals with the issue of creating simple face filters using the OpenCV library. The aim is to create a prototype application capable of creating and mapping raster graphics on the landmarks of the face in augmented reality. Haar-like casscade detection was used for face detection and a regression local binary features algorithm for facial landmarks. Currently, a Windows computer application with a simple user interface is fully functional. It provides the user with intuitive creation of simple graphics, which the application then transforms and maps onto facial features detected in the webcam's input video.