Embrace by Anargyros Sarafopoulos   EVOWORKSHOPS:   EVOMUSART2004

2nd European Workshop on Evolutionary Music and Art


EvoMUSART2004 is the second workshop of the EvoNet working group on evolutionary music and art. The application of Evolutionary Computation (EC) techniques for the development of creative systems is a new, exciting and significant area of research. There is a growing interest in the application of these techniques in fields such as: art and music generation, analysis and interpretation; architecture; and design. The goal of evoMUSART2004 is to bring together researchers that are using EC in this context, providing the opportunity to promote, present and discuss ongoing work on the area. Each accepted paper will be presented orally at the conference and published by Springer as part of EvoWorkshops2004 in the Lecture Notes in Computer Science series. Springer Lecture Notes in Computer Science series

LNCS 3005, the EvoWorkshops2004 proceedings, is now available online


Workshop PAPERS:

Swarm Granulator
Tim Blackwell, Michael Young

This paper describes a Swarm Granulator, a new application of particle swarms to sound synthesis. Granulation, an established technique in sound synthesis, depends on many parameters which are non-intuitive and hard to control from a human perspective. It is proposed here that a particle swarm can organize these parameters and produce musically interesting and novel timbres. A crucial element of the system is the self-organization of grain parameters around attractors which themselves represent musical events and textures in an external environment. This means that Swarm Granulator is interactive, and not merely reactive.

Generative Art: Fuzzy Polygon Clipping in Program Generated Line Oriented Drawings
Hans Eberhardt Dehlinger

The paper addresses aspects of Generative Art with a focus on algorithmically generated drawings of high density, executed on pen-plotters. Special attention is given to the concept of fuzzy clipping, extending the classical approaches to the clipping of line drawings. Strategies for fuzzy clipping are discussed and illustrated. The generating program is regarded as a personal vehicle designed for experiments of an artist. It supports the pursued intentions on the basis of defined preferences. The universe of hand-generated drawings is compared to the universe of program-generated drawings. It is argued that the richness of the universe of program generated drawings reveals aesthetic properties, which rival those of the universe of hand drawings. Examples of generated drawings are used to demonstrate the range of variety in the output of the generator.

The Virtual Ecosystem As Generative Electronic Art
Alan Dorin

This paper proposes four desirable attributes of processes to be applied in generative electronic art. By example, it then demonstrates that the virtual ecosystem in its entirety is a process with many of these desirable attributes. The paper contrasts this process with the use of cellular automata. It outlines a number of generative artworks with which the author has been involved that utilize the virtual ecosystem, and discusses their pros and cons in the context of generative art. The paper suggests means by which the application of the four desirable attributes may extend the creative possibilities for these works.

Tilings of Sequences of Co-evolved Images
Gary Greenfield

Sims' well-known technique for using evolving expressions to generate abstract images is paired with a co-evolutionary hosts and parasites fitness scheme to instantiate an evolutionary simulation. An added twist is that image populations are completely replaced after each generation. The goal is to identify evolutionary epochs where significant aesthetic themes emerge so that sequences of maximally fit images can be culled. Culled sequences are used to construct tilings. The technique yields abstract tilings where the interplay between creation, competition, and cooperation of visual themes combine to produce some surprising aesthetic results.

Aesthetic Video Filter Evolution in an Interactive Real-time Framework
Matthew Lewis

A data-flow network-based interactive evolutionary design framework is presented which will provide a testbed for the development and exploration of a diverse range of visual artistic design spaces. The domain of real-time layered video filters is focused on as the primary example. The system supports both real-time video streams and prerecorded video. Issues of stylistic signature, GA vs. GP-based approaches, rapid tuning of fitness distributions, and desirable traits of generic evolutionary design systems are discussed.

Adaptive Critics for Evolutionary Artists
Penousal Machado, Juan Romero, María Luisa Santos, Amílcar Cardoso, Bill Manaris

We focus on the development of artificial art critics. These systems analyze artworks, extracting relevant features, and produce an evaluation of the perceived pieces. The ability to perform aesthetic judgments is a desirable characteristic in an evolutionary artificial artist. As such, the inclusion of artificial art critics in these systems may improve their artistic abilities. We propose artificial art critics for the domains of music and visual arts, presenting a comprehensive set of experiments in author identification tasks. The experimental results show the viability and potential of our approach.

Aesthetic Evolution of L-systems Revisited
Jon McCormack

Methods for evolving Lindenmayer systems (L-systems) have been discussed in the literature for more than 10 years. This paper revisits one of the first published methods on the application of interactive evolution of L-systems for creative purposes, using aesthetic selection. An epilogue surveys the techniques and applications of evolutionary L-system methods since the original publication by the author in 1993. Conclusions are drawn about the utility and difficulties associated with evolving L-system productions, and aesthetic evolution in general, particularly with application to design and creative process.

Improvisational Media Space :: Architecture and Strategies for Evolution
Paul Nemirovsky, Rebecca Luger-Guillaume

This paper presents the current state in an ongoing development of the Emonic Environment (EE): a real-time improvisational system employing evolutionary principles for the mutation of media space. We position the associated problems in the context of user interaction, provide eight principles essential for creating an improvisational media environment, follow with a description of how the EE implements these principles, and conclude with a description of the evolutionary algorithms' functionality.

Automated Aesthetic Selection of Evolutionary Art by Distance Based Classification of Genomes and Phenomes using the Universal Similarity Metric
Nils Svangaard, Peter Nordin

In this paper we present a new technique for automatically approximating the aesthetic fitness of evolutionary art. Instead of assigning fitness values to images interactively, we use the Universal Similarity Metric to predict how interesting new images are to the observer based on a library of aesthetic images. In order to approximate the Information Distance, and find the images most similar to the training set, we use a combination of zip-compression, for genomes, and jpeg-compression of the final images. We evaluated the prediction accuracy of our system by letting the user label a new set of images and then compare that to what our system classifies as the most aesthetically pleasing images. Our experiments indicate that the Uni-versal Similarity Metric can successfully be used to classify what images and genomes are aesthetically pleasing, and that it can clearly distinguish be-tween "ugly" and "pretty" images with an accuracy better than the random baseline.

EvoMusArt programme committee:

Co-chair: Colin Johnson, University of Kent, UK <c.g.johnson@ukc.ac.uk>
Co-chair: Penousal Machado, University of Coimbra, Portugal <machado@dei.uc.pt>
Hans-Georg Beyer (Germany)
Mauro Annunziato, Plancton Art Studio (Italy)
Paul Brown, Birkbeck College, University of London, fineArt forum (Australia)
Amílcar Cardoso, Centre for Informatics and Systems, University of Coimbra (Portugal)
John Gero, Key Centre of Design Computing and Cognition, University of Sydney (Australia)
Andrew Gartland-Jones, University of Sussex (UK)
Carlos Grilo, School of Technology and Management of Leiria (Portugal)
Matthew Lewis, Ohio State University (USA)
Bill Manaris, College of Charleston (USA)
Eduardo R. Miranda, University of Plymouth (Brazil)
Ken Musgrave, Pandromeda, Inc. (USA)
Luigi Pagliarini, Academy of Fine Arts of Rome & University of Southern Denmark (Italy)
Juan Romero, Universidade da Coruña (Spain)
Celestino Soddu, Politecnico de Milano (Italy)
Tim Taylor, University of Edinburgh (UK)
Stephen Todd, IBM (UK)
Tatsuo Unemi, University of Zurich (Japan)
Geraint Wiggins, City University (UK)

EvoWorkshops chairs:

Günther Raidl, Vienna University of Technology <raidl@ads.tuwien.ac.at>
Stefano Cagnoni, Universita' di Parma <cagnoni@ce.unipr.it>
Local chair : Ernesto Costa, University of Coimbra <ernesto@dei.uc.pt>

Workshop Background:

EvoMUSART2004 is the second workshop of the EvoNet working group on evolutionary music and art. The application of Evolutionary Computation (EC) techniques for the development of creative systems is a new, exciting and significant area of research. There is a growing interest in the application of these techniques in fields such as: art and music generation, analysis and interpretation; architecture; and design.

The goal of evoMUSART2004 is to bring together researchers that are using EC in this context, providing the opportunity to promote, present and discuss ongoing work on the area. Accepted papers will be presented orally at the workshop and included in the EuroGP 2004 conference proceedings, published by Springer Verlag in their Lecture Notes in Computer Science series.

Topics of interest

The papers should include original and unpublished contributions, related with the use of EC in the scope of the analysis, generation and interpretation of art and music. Topics of interest include, but are not limited to:

  • Generation
    • Evolutionary Art
      Systems that create drawings, images, animations, sculptures, poetry, text, etc.;
    • Evolutionary Music
      Systems that create musical pieces, sounds, instruments, voices, etc.;
    • Robotic based Evolutionary Art and Music;
  • Analysis and Interpretation
    • Systems that resort to EC to perform the analysis of image, music, sound sculpture, or some other type of artistic object;
    • Systems in which the analysis of artworks is used in conjunction with EC techniques to produce novel objects;
  • Computer Aided Creativity
    • Systems in which EC is used to promote the creativity of a human user;
    • New ways of integrating the user in the evolutionary cycle;
    • Collaborative distributed environments;
  • Theory
    • Surveys of the current state-of-the-art in the area; identification of weaknesses and strengths; comparative analysis and classification;
    • Validation methodologies;
    • New models designed to promote the creative potential of EC;
    • Aesthetics, emotional response;
    • Studies on the applicability of these techniques to other creativity related areas;
Submission procedure (NOW CLOSED)

Submissions should be a maximum of ten A4 pages and they should be sent in postscript or PDF format. It is advisable that the papers conform to the Springer Lecture Notes in Computer Science format (http://www.springer.de/comp/lncs/authors.html).

The reviewing process is double blind. Authors should remove their names from submitted papers, and should take reasonable care that their identity is disguised. References to own work can be included in the paper, but should be referred to in the third person.

It is very important that the email accompanying submission should state ALL the authors, including ALL their email addresses. To avoid problems with electronic delivery, papers should be emailed to BOTH of the program chairs. A notification of receipt will be emailed a few days after the deadline.

Springer Lecture Notes in Computer Science series The EvoWorkshops2004 proceedings will be
published by Spinger as part of their
Lecture Notes in Computer Science series.