IEEE Transactions on Image Processing, Vol 26, Issue 1 (TIP)

Data-Driven Synthesis of Cartoon Faces Using Different Styles

Given a portrait photo, we decompose the face into individual components and search for the corresponding cartoon candidates for each component in a database by feature matching. We then obtain the best combination of these candidates using a Bayesian network and compose the selected components together to synthesize a cartoon face. We can generate cartoon faces in different styles using our framework. The left is an example of the B&W style and the right is an example of FASHION style.


This paper presents a data-driven approach for automatically generating cartoon faces in different styles from a given portrait image. Our stylization pipeline consists of two steps: an offline analysis step to learn about how to select and compose facial components from the databases; a runtime synthesis step to generate the cartoon face by assembling parts from a database of stylized facial components. We propose an optimization framework that, for a given artistic style, simultaneously considers the desired image-cartoon relationships of the facial components and a proper adjustment of the image composition. We measure the similarity between facial components of the input image and our cartoon database via image feature matching, and introduce a probabilistic framework for modeling the relationships between cartoon facial components. We incorporate prior knowledge about image-cartoon relationships and the optimal composition of facial components extracted from a set of cartoon faces to maintain a natural, consistent and attractive look of the results. We demonstrate generality and robustness of our approach by applying it to a variety of portrait images and compare our output with stylized results created by artists via a comprehensive user study.


Cartoon face, stylization, data-driven synthesis, component-based modeling


paper thumbnail