Adapting models of visual aesthetics for personalized content creation

Antonios Liapis, Georgios N. Yannakakis, Julian Togelius

    Research output: Contribution to journalArticle

    Abstract

    This paper introduces a search-based approach to personalized content generation with respect to visual aesthetics. The approach is based on a two-step adaptation procedure where: 1) the evaluation function that characterizes the content is adjusted to match the visual aesthetics of users; and 2) the content itself is optimized based on the personalized evaluation function. To test the efficacy of the approach, we design fitness functions based on universal properties of visual perception, inspired by psychological and neurobiological research. Using these visual properties, we generate aesthetically pleasing 2-D game spaceships via neuroevolutionary constrained optimization and evaluate the impact of the designed visual properties on the generated spaceships. The offline generated spaceships are used as the initial population of an interactive evolution experiment in which players are asked to choose spaceships according to their visual taste: the impact of the various visual properties is adjusted based on player preferences and new content is generated online based on the updated computational model of visual aesthetics of the player. Results are presented that show the potential of the approach in generating content which is based on subjective criteria of visual aesthetics.

    Original languageEnglish (US)
    Article number6185648
    Pages (from-to)213-228
    Number of pages16
    JournalIEEE Transactions on Computational Intelligence and AI in Games
    Volume4
    Issue number3
    DOIs
    StatePublished - 2012

    Fingerprint

    Function evaluation
    Constrained optimization
    Experiments

    Keywords

    • Computational aesthetics
    • constrained optimization
    • experience-driven procedural content generation (EDPCG)
    • interactive evolution

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Software
    • Control and Systems Engineering
    • Electrical and Electronic Engineering

    Cite this

    Adapting models of visual aesthetics for personalized content creation. / Liapis, Antonios; Yannakakis, Georgios N.; Togelius, Julian.

    In: IEEE Transactions on Computational Intelligence and AI in Games, Vol. 4, No. 3, 6185648, 2012, p. 213-228.

    Research output: Contribution to journalArticle

    Liapis, Antonios ; Yannakakis, Georgios N. ; Togelius, Julian. / Adapting models of visual aesthetics for personalized content creation. In: IEEE Transactions on Computational Intelligence and AI in Games. 2012 ; Vol. 4, No. 3. pp. 213-228.
    @article{412ad621a46041b68d44ad826ff7bf20,
    title = "Adapting models of visual aesthetics for personalized content creation",
    abstract = "This paper introduces a search-based approach to personalized content generation with respect to visual aesthetics. The approach is based on a two-step adaptation procedure where: 1) the evaluation function that characterizes the content is adjusted to match the visual aesthetics of users; and 2) the content itself is optimized based on the personalized evaluation function. To test the efficacy of the approach, we design fitness functions based on universal properties of visual perception, inspired by psychological and neurobiological research. Using these visual properties, we generate aesthetically pleasing 2-D game spaceships via neuroevolutionary constrained optimization and evaluate the impact of the designed visual properties on the generated spaceships. The offline generated spaceships are used as the initial population of an interactive evolution experiment in which players are asked to choose spaceships according to their visual taste: the impact of the various visual properties is adjusted based on player preferences and new content is generated online based on the updated computational model of visual aesthetics of the player. Results are presented that show the potential of the approach in generating content which is based on subjective criteria of visual aesthetics.",
    keywords = "Computational aesthetics, constrained optimization, experience-driven procedural content generation (EDPCG), interactive evolution",
    author = "Antonios Liapis and Yannakakis, {Georgios N.} and Julian Togelius",
    year = "2012",
    doi = "10.1109/TCIAIG.2012.2192438",
    language = "English (US)",
    volume = "4",
    pages = "213--228",
    journal = "IEEE Transactions on Computational Intelligence and AI in Games",
    issn = "1943-068X",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    number = "3",

    }

    TY - JOUR

    T1 - Adapting models of visual aesthetics for personalized content creation

    AU - Liapis, Antonios

    AU - Yannakakis, Georgios N.

    AU - Togelius, Julian

    PY - 2012

    Y1 - 2012

    N2 - This paper introduces a search-based approach to personalized content generation with respect to visual aesthetics. The approach is based on a two-step adaptation procedure where: 1) the evaluation function that characterizes the content is adjusted to match the visual aesthetics of users; and 2) the content itself is optimized based on the personalized evaluation function. To test the efficacy of the approach, we design fitness functions based on universal properties of visual perception, inspired by psychological and neurobiological research. Using these visual properties, we generate aesthetically pleasing 2-D game spaceships via neuroevolutionary constrained optimization and evaluate the impact of the designed visual properties on the generated spaceships. The offline generated spaceships are used as the initial population of an interactive evolution experiment in which players are asked to choose spaceships according to their visual taste: the impact of the various visual properties is adjusted based on player preferences and new content is generated online based on the updated computational model of visual aesthetics of the player. Results are presented that show the potential of the approach in generating content which is based on subjective criteria of visual aesthetics.

    AB - This paper introduces a search-based approach to personalized content generation with respect to visual aesthetics. The approach is based on a two-step adaptation procedure where: 1) the evaluation function that characterizes the content is adjusted to match the visual aesthetics of users; and 2) the content itself is optimized based on the personalized evaluation function. To test the efficacy of the approach, we design fitness functions based on universal properties of visual perception, inspired by psychological and neurobiological research. Using these visual properties, we generate aesthetically pleasing 2-D game spaceships via neuroevolutionary constrained optimization and evaluate the impact of the designed visual properties on the generated spaceships. The offline generated spaceships are used as the initial population of an interactive evolution experiment in which players are asked to choose spaceships according to their visual taste: the impact of the various visual properties is adjusted based on player preferences and new content is generated online based on the updated computational model of visual aesthetics of the player. Results are presented that show the potential of the approach in generating content which is based on subjective criteria of visual aesthetics.

    KW - Computational aesthetics

    KW - constrained optimization

    KW - experience-driven procedural content generation (EDPCG)

    KW - interactive evolution

    UR - http://www.scopus.com/inward/record.url?scp=84866478526&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84866478526&partnerID=8YFLogxK

    U2 - 10.1109/TCIAIG.2012.2192438

    DO - 10.1109/TCIAIG.2012.2192438

    M3 - Article

    VL - 4

    SP - 213

    EP - 228

    JO - IEEE Transactions on Computational Intelligence and AI in Games

    JF - IEEE Transactions on Computational Intelligence and AI in Games

    SN - 1943-068X

    IS - 3

    M1 - 6185648

    ER -