Personal Style and Non-Negative Matrix Factorization Based Exaggerative Expressions of Face

An intriguing tactic for achieving facial expressions beyond realistic approaches has gradually drawn lots of attention in the fields of video games, avatars, teleconference, human-computer interface and computer animation. However, most researches on facial expressions tend to remain faithful to the trend in realistic expressions rather than exaggerating expressions to take into account personal styles. In the work presented here, we propose a method for exaggeration of facial expressions created by exaggeration mapping that transforms facial motions into exaggerated motions. The exaggeration mapping is derived from non-negative matrix factorization. As if each individual has an identical personality, a conceptual mapping of personal styles for exaggeration of facial expressions needs to be considered. By conducting experiments, we have shown the validity of the exaggeration mapping and simulations of facial expressions.