Understanding aesthetic evaluation using deep learning

Jon McCormack, Andy Lomas

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

3 Citations (Scopus)

Abstract

A bottleneck in any evolutionary art system is aesthetic evaluation. Many different methods have been proposed to automate the evaluation of aesthetics, including measures of symmetry, coherence, complexity, contrast and grouping. The interactive genetic algorithm (IGA) relies on human-in-the-loop, subjective evaluation of aesthetics, but limits possibilities for large search due to user fatigue and small population sizes. In this paper we look at how recent advances in deep learning can assist in automating personal aesthetic judgement. Using a leading artist’s computer art dataset, we use dimensionality reduction methods to visualise both genotype and phenotype space in order to support the exploration of new territory in any generative system. Convolutional Neural Networks trained on the user’s prior aesthetic evaluations are used to suggest new possibilities similar or between known high quality genotype-phenotype mappings.

Original languageEnglish
Title of host publicationArtificial Intelligence in Music, Sound, Art and Design
Subtitle of host publication9th International Conference, EvoMUSART 2020 Held as Part of EvoStar 2020 Seville, Spain, April 15–17, 2020 Proceedings
EditorsJuan Romero, Anikó Ekárt, Tiago Martins, João Correia
Place of PublicationCham Switzerland
PublisherSpringer
Pages118-133
Number of pages16
ISBN (Print)9783030438586
DOIs
Publication statusPublished - 2020
EventEuropean Conference on Artificial Intelligence in Music, Sound, Art and Design 2020: held as part of EvoStar 2020 - Seville, Spain
Duration: 15 Apr 202017 Apr 2020
Conference number: 9th
https://www.springer.com/gp/book/9783030438586?utm_campaign=3_pier05_buy_print&utm_content=en_08082017&utm_medium=referral&utm_source=google_books#otherversion=9783030438593 (Proceedings)
http://www.evostar.org/2020/ (Conference website)

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume12103
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceEuropean Conference on Artificial Intelligence in Music, Sound, Art and Design 2020
Abbreviated titleEvoMUSART 2020
CountrySpain
CitySeville
Period15/04/2017/04/20
Internet address

Keywords

  • Aesthetic measure
  • Aesthetics
  • Convolutional Neural Networks
  • Dimension reduction
  • Evolutionary art
  • Morphogenesis

Cite this