Atsushi Kasao

Algorithmic Painter: a NPR method to generate various styles of painting

This paper proposes Algorithmic Painter, an algorithm that can produce various styles of painting from source photos. Algorithmic Painter is created by enhancing Synergistic Image Creator, a painterly rendering method, so that it is highly expressive but still preserves the essential characteristics of the source photo. To achieve this, our method extracts three types of image segments automatically from a source photo by a newly proposed classification method: edge areas, homogeneous areas, and highly contrastive areas. Next, each obtained image segment is converted into a brushstroke. Finally, the target picture is rendered by assigning a color to each pixel. Furthermore, this method can control the curvy shapes of brushstrokes, so that the obtained image can incorporate not only various artistic touches but also natural touches. As an example, the paper describes the composition technique for three considerably different painting styles.

Enhanced SIC (synergistic image creator) for artistic use

We are studying non-photo realistic rendering (NPR) with the goal of developing an image expression tool to create artworks by the NPR technique. The purpose of most NPR researches is to simulate typical painting styles, so they focus on techniques to create brushstrokes. These superficially modified images cannot deviate far from the source photo. If a rendered image is seen from a distance, it is difficult to tell the difference from the source photo. This fact makes us realize that other important elements to add artistic expression to the photographs exist. We supposed that the distribution of bright and dark parts over the painting is essential and proposed the effective way to modify that. Our novel technique is based on knowledge about human optical illusions and basic visual design rules. We integrate this technique into our NPR system, which was used to make the artworks selected by SIGGRAPH 2002 2D art gallery. Furthermore, we present new features that allow artist to select appropriate area for extreme expressions, to create many types of brushstrokes, and to choose more than two types of brushstrokes for a single artwork.

Algorithmic painter: a NPR method to generate various styles of painting

This paper proposes Algorithmic Painter, an algorithm that can produce various styles of painting from source photos. Algorithmic Painter is created by enhancing Synergistic Image Creator, a painterly rendering method, so that it is highly expressive but still preserves the essential characteristics of the source photo. To achieve this, our method extracts three types of image segments automatically from a source photo by a newly proposed classification method: edge areas, homogeneous areas, and highly contrastive areas. Next, each obtained image segment is converted into a brushstroke. Finally, the target picture is rendered by assigning a color to each pixel. Furthermore, this method can control the curvy shapes of brushstrokes, so that the obtained image can incorporate not only various artistic touches but also natural touches. As an example, the paper describes the composition technique for three considerably different painting styles.

Enhanced synergistic image creator: an NPR method with natural curly brushstrokes

This paper proposes a non-photorealistic rendering (NPR) method for image creation which can produce various styles of painting. To create an expressive painting from a photograph, it is important to add artistic expression onto appropriate regions and to give viewers a natural impression. The proposed method introduces curly brushstroke generation for producing natural impression, and a new image merging technique for finding the appropriate regions in which to add artistic expressions.