Edge-respecting brushes

Digital paint is one of the more successful interactive applications of computing. Brushes that apply various effects to an image have been central to this success. Current painting techniques ignore the underlying image. By considering that image we can help the user paint more effectively. There are algorithms that assist in selecting regions to paint including flood fill, intelligent scissors and graph cut. Selected regions and the algorithms to create them introduce conceptual layers between the user and the painting task. We propose a series of "edge-respecting brushes" that spread paint or other effects according to the edges and texture of the image being modified. This restores the simple painting metaphor while providing assistance in working with the shapes already in the image. Our most successful fill brush algorithm uses competing least-cost-paths to identify what should be selected and what should not.