engleski

Localizing Facial Landmark Points with Pixel Intensity Comparisons Organized in Decision Trees

The main objective of this work is to develop a method that can accurately estimate the positions of relevant facial landmarks in real-time on hardware with limited processing power, such as modern mobile devices. This is achieved with a sequence of estimators based on ensembles of regression trees. The trees use simple pixel intensity comparisons in their internal nodes and this makes them able to process image regions very fast. We test the developed system on several publicly available datasets and analyse its processing speed on various devices.

facial landmark point ; face alignment

nije evidentirano