The process of creating nonphotorealistic rendering images and animations can be enjoyable if a useful method is involved.We use\nan evolutionary algorithmto generate painterly styles of images. Given an input image as the reference target, a cloud model-based\nevolutionary algorithm that will rerender the target image with nonphotorealistic effects is evolved. The resulting animations have\nan interesting characteristic inwhich the target slowly emerges froma set of strokes.Anumber of experiments are performed, aswell\nas visual comparisons, quantitative comparisons, and user studies. The average scores in normalized feature similarity of standard\npixel-wise peak signal-to-noise ratio, mean structural similarity, feature similarity, and gradient similarity based metric are 0.486,\n0.628, 0.579, and 0.640, respectively.The average scores in normalized aesthetic measures of Benford�s law, fractal dimension, global\ncontrast factor, and Shannon�s entropy are 0.630, 0.397, 0.418, and 0.708, respectively. Compared with those of similar method, the\naverage score of the proposed method, except peak signal-to-noise ratio, is higher by approximately 10%. The results suggest that\nthe proposedmethod can generate appealing images and animations with different styles by choosing different strokes, and it would\ninspire graphic designers who may be interested in computer-based evolutionary art.
Loading....