Year: 2001
Type: article
Abstract: This paper describes a new method for creating visually realistic moving facial image sequences that retain an actor's personality (individuality, expression and characteristic movements) while altering the\nfacial appearance along a certain specified facial dimension. We combine two existing technologies, facial feature tracking and facial image transformation, to create the sequences. Examples are given of\ntransforming the apparent age, race and gender of a face. We also create 'virtual cartoons' by transforming image sequences into the style of famous artists. The results show that static 2D face models can be used to create realistic transformations of sequences that include changes in pose, expression and mouth shape.
Authors: Bernard Tiddeman, David I. Perrett
Institution: University of St Andrews
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W152609174
