Facial motion capture with 3D active appearance models

Abstract

Motion detection and tracking of facial features usually use special markers placed assistance on the part of the facial features, there is making the actor became uncomfortable in the process of making motion are applied in the world of animation either games or animated movies. Facial motion captures without any marker or marker less is one of the new techniques in Computer Vision. In this study the method used is the Active Appearance Models (AAM), which aims to detect and track a set of facial features, a variety of expressions and poses of the human face, the face orientation and movement. The image used in this study would have to have depth information that represents a 3D image, hence capturing facial images in this study used a stereo camera. Stereo camera in this study replaced with cameras that provide the depth information of a digital image. Data depth of image a point cloud consisting of data from the XYZ coordinates of a 3D representation of the world, which can then be applied to move the 3D face model, so that the resulting motion is more natural, which in turn can be used in the game and the world of animation.