Synthesis of Exaggerative Line-drawing Caricature

We developed a novel system consisting of two modules, statistics-based synthesis and nonphotorealistic rendering (NPR), to synthesize caricatures of exaggerative facial features and other particular characteristics, such as beards or nevus. The statistics-based synthesis module can exaggerate shapes and positions of facial features based on non-linear exaggerative rates determined automatically. Instead of comparing only the facial features with average face, our synthesis module also considers the geometric condition of the facial features itself ,such as the width or the length,. Subsequently, the NPR module generates the line-drawing sketch of original face, and then the sketch is warped to an exaggerative style with synthesized shape points. The experimental results demonstrate that our system can automatically and effectively exaggerate facial features, and generate corresponding facial caricatures.