Animated drawings rendered by genetic programming

ABSTRACT

We describe an approach to generating animations of drawings that start as a random collection of strokes and gradually resolve into a recognizable subject. The strokes are represented as tree based genetic programs. An animation is generated by rendering the best individual in a generation as a frame of a movie. The resulting animations have an engaging characteristic in which the target slowly emerges from a random set of strokes. We have generated two qualitatively different kinds of animations, ones that use grey level straight line strokes and ones that use binary Bezier curve stokes. Around 100,000 generations are needed to generate engaging animations. Population sizes of 2 and 4 give the best convergence behaviour. Convergence can be accelerated by using information from the target in drawing a stroke. Our approach provides a large range of creative opportunities for artists. Artists have control over choice of target and the various stroke parameters.

REFERENCES

• 1: Kasao, A. and Miyata, K., Algorithmic Painter -- a NPR method to generate various styles of painting. The Visual Computer, 2005.
• 2: Baker, E. and Seltzer, M., Evolving Line Drawings. Graphics Interface, pages 91--99, 1994.
• 3: William Baxter , Jeremy Wendt , Ming C. Lin, IMPaSTo: a realistic, interactive model for paint, Proceedings of the 3rd international symposium on Non-photorealistic animation and rendering, June 07-09, 2004, Annecy, France [doi>10.1145/987657.987665]
• 4: Samuel R. Buss, 3D Computer Graphics: A Mathematical Introduction with OpenGL, Cambridge University Press, New York, NY, 2003
• 5: Camhy, S. W., Art of the Pencil: A Revolutionary Look at Drawing, Painting, and the Pencil. Watson-Guptill, 1997.
• 6: Chakraborty, U. K. and Kang, H. W., Stroke-based rendering by evolutionary algorithm. India Annual Conference, 2004. Proceedings of the IEEE INDICON 2004. First, 2004.
• 7: Nicolas Chaumont , Richard Egli , Christoph Adami, Evolving Virtual Creatures and Catapults, Artificial Life, v.13 n.2, p.139-157, Spring 2007 [doi>10.1162/artl.2007.13.2.139]
• 8: Nelson S.-H. Chu , Chiew-Lan Tai, MoXi: real-time ink dispersion in absorbent paper, ACM SIGGRAPH 2005 Papers, July 31-August 04, 2005, Los Angeles, California
• 9: Vic Ciesielski , Marsha Berry , Karen Trist , Daryl D'Souza, Evolution of Animated Photomosaics, Proceedings of the 2007 EvoWorkshops 2007 on EvoCoMnet, EvoFIN, EvoIASP,EvoINTERACTION, EvoMUSART, EvoSTOC and EvoTransLog: Applications of Evolutionary Computing, April 11-13, 2007, Valencia, Spain [doi>10.1007/978-3-540-71805-5_55]
• 10: Collomosse, J. P. and Hall, P. M., Genetic Paint: A search for salient paintings. Applications of Evolutionary Computing, EvoWorkshops, pages 437--447, 2005.
• 11: Gathercole, C. and Ross, P., Small Populations over Many Generations can beat Large Populations over Few Generations in Genetic Programming. Genetic Programming 1997: Proceedings of the Second Annual Conference, pages 111--118, 1997.
• 12: Wijesinghe, G., Mat Sah, S. B. and Ciesielski, V., Grid vs. Arbitrary Placement of Tiles for Generating Animated Photomosaics. 2008 World Congress on Computational Intelligence, 2008.
• 13: Gershon Elber , Elaine Cohen, Probabilistic silhouette based importance toward line-art non-photorealistic rendering, The Visual Computer: International Journal of Computer Graphics, v.22 n.9, p.793-804, September 2006 [doi>10.1007/s00371-006-0065-8]
• 14: Goldberg, D. E., Korb, B. and Deb, K., Messy Genetic Algorithms: Motivation, Analysis, and First Results. Complex Systems 3(5), pages 493--530, 1989.
• 15: Paul Haeberli, Paint by numbers: abstract image representations, ACM SIGGRAPH Computer Graphics, v.24 n.4, p.207-214, Aug. 1990
• 16: David A. Hart, Toward Greater Artistic Control for Interactive Evolution of Images and Animation, Proceedings of the 2007 EvoWorkshops 2007 on EvoCoMnet, EvoFIN, EvoIASP,EvoINTERACTION, EvoMUSART, EvoSTOC and EvoTransLog: Applications of Evolutionary Computing, April 11-13, 2007, Valencia, Spain [doi>10.1007/978-3-540-71805-5_58]
• 17: Aaron Hertzmann, Tutorial: A Survey of Stroke-Based Rendering, IEEE Computer Graphics and Applications, v.23 n.4, p.70-81, July 2003 [doi>10.1109/MCG.2003.1210867]
• 18: Karl Sims, Artificial evolution for computer graphics, Proceedings of the 18th annual conference on Computer graphics and interactive techniques, p.319-328, July 1991
• 19: John R. Koza, Genetic programming: on the programming of computers by means of natural selection, MIT Press, Cambridge, MA, 1992
• 20: Lewis, M., Evolutionary Visual Art and Design. The Art of Artificial Evolution, 2008.
• 21: Penousal Machado , Amílcar Cardoso, All the Truth About NEvAr, Applied Intelligence, v.16 n.2, p.101-118, March-April 2002 [doi>10.1023/A:1013662402341]
• 22: McCormack, J., Interactive evolution of L--system grammars for computer graphics modelling. Complex Systems: from Biology to Computation, pages 118--138, 1993.
• 23: McCormack, J., Turbulence: An Interactive Installation Exploring Artificial Life. Visual Proceedings: The Art and Interdisciplinary Programs of SIGGRAPH 94, pages 182--183, 1994.
• 24: Neufeld, C., Ross, B. and Ralph, W., The Evolution of Artistic Filters. The Art of Artificial Evolution, pages 335--356, 2008.
• 25: Juan Romero , Penousal Machado, The Art of Artificial Evolution: A Handbook on Evolutionary Art and Music (Natural Computing Series), 2007
• 26: Semet, Y., O'Reilly, U.-M. and Durand, F., An Interactive Artifical Ant Approach To Non-Photorealistic Rendering. Lecture Notes In Computer Science: GECCO 2004, 2004.
• 27: Sousa, M. C. and Buchanan, J. W., Computer-Generated Pencil Drawing. Western Computer Graphics Symposium 1(2), 1999.
• 28: Suguru Saito , Akane Kani , Youngha Chang , Masayuki Nakajima, Curvature-based stroke rendering, The Visual Computer: International Journal of Computer Graphics, v.24 n.1, p.1-11, November 2007 [doi>10.1007/s00371-007-0165-0]
• 29: Unemi, T., SBART 2.4: breeding 2D CG images and movies and creating a type of collage. Knowledge-Based Intelligent Information Engineering Systems, 1999. Third International Conference, pages 288--291, 1999.
• 30: Georges Winkenbach , David H. Salesin, Computer-generated pen-and-ink illustration, Proceedings of the 21st annual conference on Computer graphics and interactive techniques, p.91-100, July 1994 [doi>10.1145/192161.192184]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.2 Automatic Programming

Additional Classification:
  I. Computing Methodologies
  I.3 COMPUTER GRAPHICS
      I.3.6 Methodology and Techniques

General Terms:
Algorithms

Keywords:
evolutionary search, evolved art, genetic art, non-photorealistic rendering