In this paper, we present a system that automatically generates caricatures from input face images. From example caricatures drawn by an artist, our caricature system learns how an artist draws caricatures. In our approach, we decouple the process of caricature generation into two parts, i.e., shape exaggeration and texture style transferring. The exaggeration of a caricature is accomplished by a prototype-based method that captures the artist?s nderstanding of what are distinctive features of a face and the exaggeration style. Such prototypes are learnt by analyzing the correlation between the image caricature pairs using partial least-squares (PLS). Experimental results demonstrate the effectiveness of our system.