Non-photorealistic rendering
Inspired by famous artists such as Matisse and Warhol, Paul Rosin and Yu-kun Lai in Cardiff have developed a novel non-photorealistic rendering technique. These techniques are often used to produce artistic effects from images. In addition, however, to simply use these techniques to make photographs more artistically pleasing, there are many other practical applications such as scientific visualisation, film production special effects and technical illustration.
The team in Cardiff have developed their approach using computer vision techniques to produce a combination of lines and tonal blocks (black and also white for highlighting) to create an abstracted artistic rendering. The success is in achieving a minimal rendering, where the number of tones as well as the number and complexity of the primitive used for rendering is minimised, whilst at the same time, retaining sufficient elements from the original image to make the results instantly recognisable.
Whilst there is a trade-off between reducing the amount of information and the ability to represent the shape and details of the original images, judging the level of abstraction is semantic-based. This basic method can be fully automated and does not require any high-level knowledge.