Gentropy: evolving 2D textures

Aus de_evolutionary_art_org
Version vom 30. Januar 2015, 01:51 Uhr von Gbachelier (Diskussion | Beiträge)

(Unterschied) ← Nächstältere Version | Aktuelle Version (Unterschied) | Nächstjüngere Version → (Unterschied)
Wechseln zu: Navigation, Suche


Wiens, A.L., Brian J. Ross: Gentropy: evolving 2D textures. Computers and Graphics Journal 26, 75–88 (2002)



Gentropy is a genetic programming system that evolves two-dimensional procedural textures. It synthesizes textures by combining mathematical and image manipulation functions into formulas. A formula can be reevaluated with arbitrary texture-space coordinates, to generate a new portion of the texture in texture space. Most evolutionary art programs are interactive, and require the user to repeatedly choose the best images from a displayed generation. Gentropy uses an unsupervised approach, where one or more target texture image is supplied to the system, and represent the desired texture features, such as colour, shape and smoothness (contrast). Then, Gentropy evolves textures independent of any further user involvement. The evolved texture will not be identical to the target texture, but rather, will exhibit characteristics similar to it. When more than one texture is supplied as a target, multi-objective feature analysis is performed. These feature tests may be combined and given different priorities during evaluation. It is therefore possible to use several target images, each with its own fitness function measuring particular visual characteristics. Gentropy also permits the use of multiple subpopulations, each of which may use its own texture evaluation criteria and target texture.

Extended Abstract


Used References

[1] Ebert DS, Musgrave FK, Peachey D, Perlin K, Worley S. Texturing and modeling: a procedural approach. Toronto: Academic Press, 1994.

[2] Watt A, Watt M. Advanced animation and rendering techniques: theory and practice. New York: ACM Press, 1992.

[3] Holland JH. Adaptation in natural and artificial systems. Cambridge, MA: MIT Press, 1992.

[4] Goldberg DE. Genetic algorithms in search, optimization and machine learning. Reading, MA: Addison Wesley, 1989.

[5] Koza JR. Genetic programming: on the programming of computers by means of natural selection. Cambridge, MA: MIT Press, 1992.

[6] Rooke S. The genetic-evolutionary art process of Steven Rooke, 1993 / (April 11 2001).

[7] Sims K. Interactive evolution of equations for procedural models. The Visual Computer 1993;9:466–76.

[8] Abadia JL. Gaia: generating new images using genetic algorithms, 1997. / (April 11 2001).

[9] Rowbottom A. Evolutionary art and form. In: Peter Bentley, editor. Evolutionary design by computers. San Francisco: Morgan Kaufmann, 1999.

[10] Ibrahim AE. Genshade: an evolutionary approach to automatic and interactive procedural texture generation. Doctoral thesis, College of Architecture, A&M University, Texas, 1998.

[11] Whitley D. Proceedings of the Genetic Evolution, Com- putation Conference (GECCO 2000). San Francisco: Morgan Kaufmann, 2000.

[12] Elias H. Cloud cover, 2000. / clouds.htmS (April 11 2001).

[13] Koza J. Genetic programming III: Darwinian invention and problem solving. San Francisco: Morgan Kaufmann, 1999.

[14] Smith JR. Integrated spatial and feature image systems: retrieval, analysis and compression. Doctoral thesis (JRS97), Center for Telecommunications Research, Grad- uate School of Arts and Sciences, Columbia University, 1997.

[15] Smith JR, Chang S-F. Visual SEEk: a fully automated content-based image query system, 1996. / (April 11 2001).

[16] Stollnitz E, Derose T, Salesin D. Wavelets for computer graphics: theory and applications. San Francisco: Morgan Kaufmann, 1996.

[17] Luke S. Patched lil-gp kernel. Computer Software, University of Maryland at College Park, 1997. / (April 112001).


Full Text

intern file

Sonstige Links