Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Experimental Results
Experimental Setup
Analysis of the Ec Results
Conclusions
References
All Topics
Computer Science
Artificial Intelligence

Experiments in computational aesthetics

Profile image of Bill ManarisBill Manaris

2008

https://doi.org/10.1007/978-3-540-72877-1_18
visibility

…

description

36 pages

link

1 file

Abstract

A novel approach to the production of evolutionary art is presented. This approach is based on the promotion of an arms race between an adaptive classifier and an evolutionary computation system. An artificial neural network is trained to discriminate among images previously created by the evolutionary engine and famous paintings. Once training is over, evolutionary computation is used to generate images that the neural network classifies as paintings. The images created throughout the evolutionary run are added to the training set and the process is repeated. This iterative process leads to the refinement of the classifier and forces the evolutionary algorithm to explore new paths. The experimental results attained across iterations are presented and analyzed. Validation tests were conducted in order to assess the changes induced by the refinement of the classifier and to identify the types of images that are difficult to classify. Taken as a whole, the experimental results show the soundness and potential of the proposed approach.

Related papers

Incorporating characteristics of human creativity into an evolutionary art algorithm (journal article)
Liane Gabora

2009

A perceived limitation of evolutionary art and design algorithms is that they rely on human intervention; the artist selects the most aesthetically pleasing variants of one generation to produce the next. This paper discusses how computer generated art and design can become more creatively human-like with respect to both process and outcome. As an example of a step in this direction, we present an algorithm that overcomes the above limitation by employing an automatic fitness function. The goal is to evolve abstract portraits of Darwin, using our 2nd generation fitness function which rewards genomes that not just produce a likeness of Darwin but exhibit certain strategies characteristic of human artists. We note that in human creativity, change is less choosing amongst randomly generated variants and more capitalizing on the associative structure of a conceptual network to hone in on a vision. We discuss how to achieve this fluidity algorithmically.

View PDFchevron_right
Incorporating characteristics of human creativity into an evolutionary art algorithm
Steve DiPaola

2009

Abstract A perceived limitation of evolutionary art and design algorithms is that they rely on human intervention; the artist selects the most aesthetically pleasing variants of one generation to produce the next. This paper discusses how computer generated art and design can become more creatively human-like with respect to both process and outcome. As an example of a step in this direction, we present an algorithm that overcomes the above limitation by employing an automatic fitness function.

View PDFchevron_right
Evolving creative portrait painter programs using Darwinian techniques with an automatic fitness function
Steve DiPaola

2005

Abstract: We experiment with computer creativity by employing and modifying techniques from evolutionary computation to create a related family of abstract portrait painter programs. In evolutionary art, most systems evolve paintings by allowing the artist to selectively breed the artwork'by hand'from a selection of the currently evolved population. Our system differs in that it uses an automatic'creative fitness function'which allows the evolutionary process to run without stopping for'creative human intervention'.

View PDFchevron_right
Using aesthetic measures to evolve art
Eelco den Heijer

2010

In this paper we investigate and compare three aesthetic measures within the context of evolutionary art. We evolve visual art with an unsupervised evolutionary art system using genetic programming and an aesthetic measure as the fitness function. We perform multiple experiments with different aesthetic measures and examine their influence on the evolved images. Additionally, we perform a cross-evaluation by calculating the aesthetic value of images evolved by measure i according to measure j. This way we investigate the flexiblity of each aesthetic measure (i.e., whether the aesthetic measure appreciates different types of images). Last, we perform an image analysis using a fixed set of image statistics functions. The results show that aesthetic measures have a rather clear 'style' and that these styles can be very different. Furthermore we find that some aesthetic measures show little flexibility and appreciate only a limited set of images. The images in this paper might only be in color in the electronic version.

View PDFchevron_right
Evolving Art Using Multiple Aesthetic Measures
Eelco den Heijer

Lecture Notes in Computer Science, 2011

In this paper we investigate the applicability of Multi-Objective Optimization (MOO) in Evolutionary Art. We evolve images using an unsupervised evolutionary algorithm and we use two aesthetic measures as fitness functions concurrently. We use three different pairs from a set of three aesthetic measures and we compare the output of each pair to the output of other pairs, and to the output of experiments with a single aesthetic measure (non-MOO). We investigate 1) whether properties of aesthetic measures can be combined using MOO and 2) whether the use of MOO in evolutionary art results in different images, or perhaps "better" images. All images in this paper can be viewed in colour at

View PDFchevron_right
Feature Selection and Novelty in Computational Aesthetics
Adrian Carballal

Lecture Notes in Computer Science, 2013

An approach for exploring novelty in expression-based evolutionary art systems is presented. The framework is composed of a feature extractor, a classifier, an evolutionary engine and a supervisor. The evolutionary engine exploits shortcomings of the classifier, generating misclassified instances. These instances update the training set and the classifier is retrained. This iterative process forces the evolutionary algorithm to explore new paths leading to the creation of novel imagery. The experiments presented and analyzed herein explore different feature selection methods and indicate the validity of the approach.

View PDFchevron_right
Fitness and Novelty in Evolutionary Art
João Correia

Lecture Notes in Computer Science, 2016

In this paper the effects of introducing novelty search in evolutionary art are explored. Our algorithm combines fitness and novelty metrics to frame image evolution as a multi-objective optimisation problem, promoting the creation of images that are both suitable and diverse. The method is illustrated by using two evolutionary art engines for the evolution of figurative objects and context free design grammars. The results demonstrate the ability of the algorithm to obtain a larger set of fit images compared to traditional fitness-based evolution, regardless of the engine used.

View PDFchevron_right

References (45)

  1. Machado, P., Cardoso, A. (1997). Model proposal for a constructed artist. In Callaos, N., Khoong, C., Cohen, E., eds.: First World Multiconference on Systemics, Cybernetics and Informatics, SCI97/ISAS97. Caracas, Venezuela, 521-528
  2. Romero, J. (2002). Metodología Evolutiva para la Construcción de Modelos Cognitivos Complejos. Exploración de la Creatividad Artificial en Composición Musical. PhD thesis. University of Corunha. Corunha, Spain (in Spanish)
  3. Romero, J., Machado, P., Santos, A., Cardoso, A. (2003). On the development of critics in evolutionary computation artists. In Günther, R., et al., eds.: Applica- tions of Evolutionary Computing, EvoWorkshops 2003: EvoBIO, EvoCOMNET, EvoHOT, EvoIASP, EvoMUSART, EvoSTOC. Vol. 2611 of LNCS. Essex, UK. Springer
  4. Manaris, B., Purewal, T., McCormick, C. (2002). Progress towards recognizing and classifying beautiful music with computers -MIDI-encoded music and the Zipf-Mandelbrot law. In: Proceedings of the IEEE SoutheastCon. Columbia, SC
  5. Manaris, B., Romero, J., Machado, P., Krehbiel, D., Hirzel, T., Pharr, W., Davis, R. (2005). Zipf's law, music classification and aesthetics. Computer Music Journal, 29(1): 55-69
  6. Manaris, B., Roos, P., Machado, P., Krehbiel, D., Pellicoro, L., Romero, J. (2007). A corpus-based hybrid approach to music analysis and composition. In: Proceedings of the 22nd Conference on Artificial Intelligence (AAAI 07). Vancouver, BC
  7. Machado, P., Romero, J., Santos, A., Cardoso, A., Manaris, B. (2004). Adaptive critics for evolutionary artists. In Günther, R., et al., eds.: Applications of Evo- lutionary Computing, EvoWorkshops 2004: EvoBIO, EvoCOMNET, EvoHOT, EvoIASP, EvoMUSART, EvoSTOC. Vol. 3005 of LNCS. Coimbra, Portugal. Springer, 435-444
  8. Machado, P., Romero, J., Cardoso, A., Santos, A. (2005). Partially interactive evolutionary artists. New Generation Computing -Special Issue on Interactive Evolutionary Computation, 23(42): 143-155
  9. Machado, P. (2007). Inteligência Artificial e Arte. PhD thesis. University of Coimbra. Coimbra, Portugal (in Portuguese)
  10. Machado, P., Cardoso, A. (1998). Computing aesthetics. In Oliveira, F., ed.: Proceedings of the XIVth Brazilian Symposium on Artificial Intelligence: Advances in Artificial Intelligence. Vol. 1515 of LNCS. Porto Alegre, Brazil. Springer, 219-229
  11. Taylor, R.P., Micolich, A.P., Jonas, D. (1999). Fractal analysis of Pollock's drip paintings. Nature, 399: 422
  12. Saunders, R. (2001). Curious Design Agents and Artificial Creativity -A Syn- thetic Approach to the Study of Creative Behaviour. PhD thesis. University of Sydney, Department of Architectural and Design Science Faculty of Architec- ture. Sydney, Australia
  13. Manaris, B.Z., Vaughan, D., Wagner, C., Romero, J., Davis, R.B. (2003). Evo- lutionary music and the Zipf-Mandelbrot law: Developing fitness functions for pleasant music. In Günther, R., et al., eds.: Applications of Evolutionary Computing, EvoWorkshop 2003: EvoBIO, EvoCOP, EvoIASP, EvoMUSART, EvoROB, and EvoSTIM. Vol. 2611 of LNCS. Springer, 522-534
  14. Machado, P., Romero, J., Manaris, B., Santos, A., Cardoso, A. (2003). Power to the critics -A framework for the development of artificial art critics. In: IJCAI 2003 Workshop on Creative Systems. Acapulco, Mexico
  15. Manaris, B., Machado, P., McCauley, C., Romero, J., Krehbiel, D. (2005). Devel- oping fitness functions for pleasant music: Zipf's law and interactive evolution systems. In Rothlauf, F., et al., eds.: Applications of Evolutionary Comput- ing, EvoWorkshops 2005: EvoBIO, EvoCOMNET, EvoHOT, EvoIASP, Evo- MUSART, EvoSTOC. Vol. 3449 of LNCS. Lausanne, Switzerland. Springer, 498-507
  16. Sims, K. (1991). Artificial evolution for computer graphics. ACM Computer Graphics, 25: 319-328
  17. Machado, P., Cardoso, A. (2002). All the truth about NEvAr. Applied Intelli- gence, Special Issue on Creative Systems, 16(2): 101-119
  18. Greenfield, G. (2002). Color dependent computational aesthetics for evolving expressions. In Sarhangi, R., ed.: Bridges: Mathematical Connections in Art, Music, and Science; Conference Proceedings 2002. Winfield, Kansas. Central Plains Book Manufacturing, 9-16
  19. Greenfield, G. (2003). Evolving aesthetic images using multiobjective optimiza- tion. In McKay, B., et al., eds.: Congress on Evolutionary Computation, CEC 2003. Vol. 3. Canberra, Australia. IEEE Press, 1903-1909
  20. Svangård, N., Nordin, P. (2004). Automated aesthetic selection of evolutionary art by distance based classification of genomes and phenomes using the universal similarity metric. In Günther, R., et al., eds.: Applications of Evolutionary Computing, EvoWorkshops 2004: EvoBIO, EvoCOMNET, EvoHOT, EvoIASP, EvoMUSART, EvoSTOC. Vol. 3005 of LNCS. Coimbra, Portugal. Springer, 445- 454
  21. Baluja, S., Pomerlau, D., Todd, J. (1994). Towards automated artificial evolu- tion for computer-generated images. Connection Science, 6(2): 325-354
  22. Greenfield, G.R. (2002). On the co-evolution of evolving expressions. Interna- tional Journal of Computational Intelligence and Applications, 2(1): 17-31
  23. Todd, P.M., Werner, G.M. (1999). Frankensteinian approaches to evolutionary music composition. In Griffith, N., Todd, P.M., eds.: Musical Networks: Parallel Distributed Perception and Performance. MIT Press, 313-340
  24. Birkhoff, G. (1933). Aesthetic Measure. Harvard University Press
  25. Moles, A. (1958). Théorie de L'Information et Perception Esthétique. Denoel
  26. Arnheim, R. (1956). Art and Visual Perception, a Psychology of the Creative Eye. Faber and Faber. London
  27. Arnheim, R. (1966). Towards a Psychology of Art/Entropy and Art -An Essay on Disorder and Order. The Regents of the University of California
  28. Arnheim, R. (1969). Visual Thinking. University of California Press. Berkeley, CA
  29. Bense, M. (1965). Aesthetica. Einführung in die neue Aesthetik. Agis (reprinted by Baden-Baden, 1982)
  30. Shannon, C.E. (1951). Prediction and entropy of printed english. Bell System Technical Journal, (30): 50-64
  31. Staudek, T. (2002). Exact Aesthetics. Object and Scene to Message. PhD thesis. Faculty of Informatics, Masaryk University of Brno
  32. Staudek, T., Linkov, V. (2004). Personality characteristics and aesthetic pref- erence for chaotic curves. Journal of Mathematics and Design, 4(1): 297-304
  33. Graves, M. (1948). Design Judgement Test. The Psychological Corporation. New York
  34. Datta, R., Joshi, D., Li, J., Wang, J.Z. (2006). Studying aesthetics in photo- graphic images using a computational approach. In: Computer Vision -ECCV 2006, 9th European Conference on Computer Vision, Part III. LNCS. Graz, Austria. Springer, 288-301
  35. Aks, D., Sprott, J.C. (1996). Quantifying aesthetic preference for chaotic pat- terns. Empirical Studies of the Arts, 14: 1-16
  36. Spehar, B., Clifford, C.W.G., Newell, N., Taylor, R.P. (2003). Universal aesthetic of fractals. Computers and Graphics, 27(5): 813-820
  37. Wannarumon, S., Bohez, E.L.J. (2006). A new aesthetic evolutionary approach for jewelry design. Computer-Aided Design & Applications, 3(1-4): 385-394
  38. Wertheimer, M. (1939). Laws of organization in perceptual forms. In Ellis, W.D., ed.: A Source Book of Gestalt Psychology. Harcourt Brace. New York, 71-88
  39. Tyler, C.W., ed. (2002). Human Symmetry Perception and Its Computational Analysis. Lawrence Erlbaum Associates
  40. Field, D.J., Hayes, A., Hess, R.F. (2000). The roles of polarity and symmetry in the perceptual grouping of contour fragments. Spatial Vision, 13(1): 51-66
  41. Cope, D. (1992). On the algorithmic representation of musical style. In Laske, O., ed.: Understanding Music with AI: Perspectives on Music Cognition. MIT Press. Cambridge, Massachusetts, 354-363
  42. Zipf, G.K. (1949). Human Behaviour and the Principle of Least Effort: An Introduction to Human Ecology. Addison-Wesley
  43. Kittler, J. (1983). On the accuracy of the Sobel edge detector. Image Vision Computing, 1(1): 37-42
  44. Zell, A., Mamier, G., Vogt, M., Mache, N., Hübner, R., Döring, S., Herrmann, K.U., Soyez, T., Schmalzl, M., Sommer, T., et al. (2003). SNNS: Stuttgart Neural Network Simulator User Manual, Version 4.2. Technical Report 3/92. University of Stuttgart. Stuttgart
  45. Directmedia (2002). 10000 Meisterwerke der Malerei -von der Antike bis zum Beginn der Moderne. DVD-ROM

Related papers

Experiments in Computational Aesthetics An Iterative Approach to Stylistic Change in Evolutionary Art
Penousal Machado

A novel approach to the production of evolutionary art is presented. This approach is based on the promotion of an arms race between an adaptive classifier and an evolutionary computation system. An artificial neural network is trained to discriminate among images previously created by the evolutionary engine and famous paintings. Once training is over, evolutionary computation is used to generate images that the neural network classifies as paintings. The images created throughout the evolutionary run are added to the training set and the process is repeated. This iterative process leads to the refinement of the classifier and forces the evolutionary algorithm to explore new paths. The experimental results attained across iterations are presented and analyzed. Validation tests were conducted in order to assess the changes induced by the refinement of the classifier and to identify the types of images that are difficult to classify. Taken as a whole, the experimental results show the soundness and potential of the proposed approach.

View PDFchevron_right
Modeling and Evaluating the Process of Creating Paintings with Evolution Computing
yasuhiro SUZUKI

Artificial Life 14: Proceedings of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems, 2014

We have modeled the actual process of creating paintings using Evolutionary Computing. In general, an outline and a theme are decided at the beginning of creating a painting, and events are located by the theme, however we evolve initial images to the preselected theme image with this method. We conducted a questionnaire to make the images created by this method to evaluate, and researched which generation people were interested in. We found that the images that have high aesthetic evaluation and originality are created in early and middle generations.

View PDFchevron_right
On the development of evolutionary artificial artists
Penousal Machado

The creation and the evaluation of aesthetic artifacts are tasks related to design, music and art, which are highly interesting from the computational point of view. Nowadays, Artificial Intelligence systems face the challenge of performing tasks that are typically human, highly subjective, and eventually social. The present paper introduces an architecture which is capable of evaluating aesthetic characteristics of artifacts and of creating artifacts that obey certain aesthetic properties. The development methodology and motivation, as well as the results achieved by the various components of the architecture, are described. The potential contributions of this type of systems in the context of digital art are also considered. r

View PDFchevron_right
Evolving Art: Past, Present and Future
Penousal Machado

2019

Evolutionary Computation techniques have been applied to several fields in the Arts in recent years. This talk overviews how they have been used to create different types of artifacts, and how past developments relate to current approaches, trends and challenges. The focus is to address a main challenge in the field, fitness assignment, analyzing this from the perspective of the interplay between the evolutionary system and the user, and discussing how Machine Learning, Evolutionary Computation and HCI techniques can be combined to create Computer Aided Creativity systems that allow the users to express their artistic or aesthetic intentions.

View PDFchevron_right
Evolutionary computing in visual art and music
Colin Johnson

Leonardo, 2002

This paper is an introduction to the special section of Leonardo on Genetic Algorithms in Visual Art and Music, which arose from a workshop at the 2000 Genetic and Evolutionary Computing Conference. This introduction gives a background review of the area, takes a look at some open questions provoked by the workshop, and summarizes the papers in the section.

View PDFchevron_right

Related topics

  • Artificial Intelligence
  • Machine Learning
  • Evolutionary Computing
  • Evolutionary Algorithm
  • Arms Race

    • Cited by

    Detecting Bias on Aesthetic Image Datasets
    Adrian Carballal, Luz Castro

    International Journal of Creative Interfaces and Computer Graphics, 2014

    In recent years, there have been attempts to discover the principles that determine the value of aesthetics in the domain of computing. Many and diverse studies have tried in some way to capture these principles through technical characteristics. To this end, helped by the ease of Internet data acquisition, datasets of images have been published which were obtained online at random from websites and photography competitions. To guarantee the validity of a system of aesthetic image classification, one must first guarantee its capacity for generalization. This paper studies how the indiscriminate selection of images can affect the generalization capacity obtained by a binary classifier.

    View PDFchevron_right
    Conceptual Representations for Computational Concept Creation
    Alexandre Miguel Pinto

    ACM Computing Surveys

    Computational creativity seeks to understand computational mechanisms that can be characterized as creative. The creation of new concepts is a central challenge for any creative system. In this article, we outline different approaches to computational concept creation and then review conceptual representations relevant to concept creation, and therefore to computational creativity. The conceptual representations are organized in accordance with two important perspectives on the distinctions between them. One distinction is between

    View PDFchevron_right
    Evotype: Towards the Evolution of Type Stencils
    Ernesto Costa

    Lecture Notes in Computer Science, 2018

    Typefaces are an essential resource employed by graphic designers. The increasing demand for innovative type design work increases the need for good technological means to assist the designer in the creation of a typeface. We present an evolutionary approach for the automatic generation of type stencils to draw coherent glyphs for different characters. The proposed system employs a Genetic Algorithm to evolve populations of type stencils. The evaluation of each candidate stencil uses a hill climbing algorithm to search the best configurations to draw the target glyphs. We study the interplay between legibility, coherence and expressiveness, and show how our framework can be used in practice.

    View PDFchevron_right
    Adversarial Evolution and Deep Learning – How Does an Artist Play with Our Visual System?
    David Blair

    Computational Intelligence in Music, Sound, Art and Design, 2019

    We create artworks using adversarial coevolution between a genetic program (hercl) generator and a deep convolutional neural network (LeNet) critic. The resulting artificially intelligent artist, whimsically named Hercule LeNet, aims to produce images of low algorithmic complexity which nevertheless resemble a set of real photographs well enough to fool an adversarially trained deep learning critic modeled on the human visual system. Although it is not exposed to any pre-existing art, or asked to mimic the style of any human artist, nevertheless it discovers for itself many of the stylistic features associated with influential art movements of the 19th and 20th Century. A detailed analysis of its work can help us to better understand the way an artist plays with the human visual system to produce aesthetically appealing images.

    View PDFchevron_right
    580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved