Scientist has now developed an Artificial Intelligence system which can sketch caricatures from a given portrait or a picture.
Caricature portrait drawing is a distinct art from where the artists draw a person’s face in an exaggerated manner, most of the times to elicit humor.
Automating this entire technique poses challenges due to the number of intricate details and shapes which is involved and the level of the professional skills as it takes to transform a person artistically from their real-life selves to a creatively exaggerated one.
“Compared to traditional graphics-based methods which define hand-crafted rules, our novel approach leverages big data and machine learning to synthesize caricatures from thousands of examples drawn by professional artists,” said Kaidi Cao, a graduate student at Stanford University in the US. “While existing style transfer methods have focused mainly on appearance style, our technique achieves both geometric exaggeration and appearance stylisation involved in caricature drawing,” said Cao, who conducted the work during his internship at Microsoft.
This method simply enables the users to automate the caricatures of the portraits can be applied to tasks such as creating caricatures avatars for the social media network and designing cartoon characters.
The technique also has some of the potential applications in advertising, journalism, and marketing. The researchers turned to a well-known technique in the field of machine learning, Generative Adversarial network for the unpaired photo to caricature translation to generate caricatures that preserve the identity of the portrait.
The AI which is called as “CariGAN’s”, the computational framework precisely models geometric exaggeration in images such as the shape of faces, specific angles and appearance stylization with the two algorithms the researchers have labeled, CariStyGAN, CariGeoGAN.
Yeah I saw that video of that elephant do his with the same result