Caricature Of US President Barack Hussein Obama II

On the other hand, Liang et al. argue that caricature varies depending on the artist and cannot be captured in a single definition. Their system uses machine learning techniques to automatically learn and mimic the style of a particular caricature artist, given training data in the form of a number of face photographs and the corresponding caricatures by that artist. The results produced by computer graphic systems are arguably not yet of the same quality as those produced by human artists. For example, most systems are restricted to exactly frontal poses, whereas many or even most manually produced caricatures (and face portraits in general) choose an off-center "three-quarters" view. Brennan's caricature drawings were frontal-pose line drawings. More recent systems can produce caricatures in a variety of styles, including direct geometric distortion of photographs.
The science of caricature
Leopold et al. found that individual face-recognizing neurons in the inferotemporal cortex respond more strongly to caricatured faces than to the veridical representations of the same face, and suggest that the visual brain may code faces relative to a prototypical face, consistent with Brennan's formalization.