Transforming images into different artistic styles

• Developed an algorithm to convert photographs into images that have a ‘hand-painted’ appearance. • Image was built in a series of layers, from a rough sketch painted over with progressively smaller brush strokes. • Implemented using PyCairo, brush strokes were matched to colors in the source image and aligned in a direction normal to the image gradients.

Algorithm

1.We “painted” an image with a series of brush strokes.

2.Brush strokes were chosen to match the colors in the source image.

3.The image was built up in a series of layers, starting with a rough sketch drawn with a large brush. The sketch is then painted over with progressively smaller brushes, but only in areas where the sketch differs from the blurred source image.

4.Thus, visual emphasis in the painting corresponds roughly to the spatial energy (e.g. edges) present in the source image.

Long curved brush strokes were used for painting along image contours.