“Improved Automatic Caricature by Feature Normalization and Exaggeration” by Mo, Neumann and Lewis

  • ©Zhenyao Mo and Ulrich Neumann




    Improved Automatic Caricature by Feature Normalization and Exaggeration



    This sketch presents an improved formalization of automatic caricature that extends a standard approach to account for the population variance of facial features. Caricature is generally considered a rendering that emphasizes the distinctive features of a particular face. A formalization of this idea, which we term “Exaggerating the Difference from the Mean” (EDFM), is widely accepted among caricaturists [Redman 1984] and was first implemented in a groundbreaking computer program by [Brennan 1985]. Brennan’s “Caricature generator” program produced caricatures by manually defining a polyline drawing with topology corresponding to a frontal, mean, face-shape drawing, and then displacing the vertices by a constant factor away from the mean shape. Many psychological studies have applied the “Caricature Generator” or EDFM idea to investigate caricature- related issues in face perception [Rhodes 1997].


    Brennan, S. E. 1985. Caricature generator: the dynamic exaggeration of faces by computer. Leonardo 18, 3, 170–178.
    Lee, D-D. and Seung, H-S. 1999. Learning the parts of objects by non-negative matrix factorization. Nature 401, 788–791.
    Redman, L. 1984. How to draw caricatures. Contemporary Books


ACM Digital Library Publication:

Overview Page: