Evolutionary automated recognition and characterization of an individual's artistic style

Taras Michael Kowaliw, Jon Paul McCormack, Alan Dorin

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

    Abstract

    In this paper, we introduce a new image database, consisting of examples of artists' work. Successful classification of this database suggests the capacity to automatically recognize an artist's aesthetic style. We utilize the notion of Transform-based Evolvable Features as a means of evolving features on the space, these features are then evaluated through a standard classifier. We obtain recognition rates for our six artistic styles - relative to images by the other artists and images randomly downloaded from a search engine - of a mean true positive rate of 0.946 and a mean false positive rate of 0.017. Distance metrics designed to indicate the similarity between an arbitrary greyscale image and one of the artistic styles are created from the evolved features. These metrics are capable of ranking control images so that artist-drawn instances appear at the front of the list. We provide evidence that other images ranked as similar by the metric correspond to naïve human notions of similarity as well, suggesting the distance metric could serve as a content-based aesthetic recommender. © 2010 IEEE.

    Original languageEnglish
    Title of host publicationProceedings of the 2010 IEEE Congress on Evolutionary Computation (IEEE CEC 2010)
    EditorsPilar Sobrevilla, Gary Fogel, Hisao Ishibuchi
    Place of PublicationPiscataway NJ USA
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages2234 - 2241
    Number of pages8
    ISBN (Print)9781424469109
    DOIs
    Publication statusPublished - 2010
    EventIEEE Congress on Evolutionary Computation 2010 - Barcelona Spain, Piscataway NJ USA
    Duration: 1 Jan 2010 → …

    Conference

    ConferenceIEEE Congress on Evolutionary Computation 2010
    Abbreviated titleIEEE CEC
    CityPiscataway NJ USA
    Period1/01/10 → …

    Cite this

    Kowaliw, T. M., McCormack, J. P., & Dorin, A. (2010). Evolutionary automated recognition and characterization of an individual's artistic style. In P. Sobrevilla, G. Fogel, & H. Ishibuchi (Eds.), Proceedings of the 2010 IEEE Congress on Evolutionary Computation (IEEE CEC 2010) (pp. 2234 - 2241). [5585975] Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CEC.2010.5585975
    Kowaliw, Taras Michael ; McCormack, Jon Paul ; Dorin, Alan. / Evolutionary automated recognition and characterization of an individual's artistic style. Proceedings of the 2010 IEEE Congress on Evolutionary Computation (IEEE CEC 2010). editor / Pilar Sobrevilla ; Gary Fogel ; Hisao Ishibuchi. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2010. pp. 2234 - 2241
    @inproceedings{16c0e6a857384ac0b0ca058a056f7de7,
    title = "Evolutionary automated recognition and characterization of an individual's artistic style",
    abstract = "In this paper, we introduce a new image database, consisting of examples of artists' work. Successful classification of this database suggests the capacity to automatically recognize an artist's aesthetic style. We utilize the notion of Transform-based Evolvable Features as a means of evolving features on the space, these features are then evaluated through a standard classifier. We obtain recognition rates for our six artistic styles - relative to images by the other artists and images randomly downloaded from a search engine - of a mean true positive rate of 0.946 and a mean false positive rate of 0.017. Distance metrics designed to indicate the similarity between an arbitrary greyscale image and one of the artistic styles are created from the evolved features. These metrics are capable of ranking control images so that artist-drawn instances appear at the front of the list. We provide evidence that other images ranked as similar by the metric correspond to na{\"i}ve human notions of similarity as well, suggesting the distance metric could serve as a content-based aesthetic recommender. {\circledC} 2010 IEEE.",
    author = "Kowaliw, {Taras Michael} and McCormack, {Jon Paul} and Alan Dorin",
    year = "2010",
    doi = "10.1109/CEC.2010.5585975",
    language = "English",
    isbn = "9781424469109",
    pages = "2234 -- 2241",
    editor = "Pilar Sobrevilla and Gary Fogel and Hisao Ishibuchi",
    booktitle = "Proceedings of the 2010 IEEE Congress on Evolutionary Computation (IEEE CEC 2010)",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    address = "United States",

    }

    Kowaliw, TM, McCormack, JP & Dorin, A 2010, Evolutionary automated recognition and characterization of an individual's artistic style. in P Sobrevilla, G Fogel & H Ishibuchi (eds), Proceedings of the 2010 IEEE Congress on Evolutionary Computation (IEEE CEC 2010)., 5585975, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 2234 - 2241, IEEE Congress on Evolutionary Computation 2010, Piscataway NJ USA, 1/01/10. https://doi.org/10.1109/CEC.2010.5585975

    Evolutionary automated recognition and characterization of an individual's artistic style. / Kowaliw, Taras Michael; McCormack, Jon Paul; Dorin, Alan.

    Proceedings of the 2010 IEEE Congress on Evolutionary Computation (IEEE CEC 2010). ed. / Pilar Sobrevilla; Gary Fogel; Hisao Ishibuchi. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2010. p. 2234 - 2241 5585975.

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

    TY - GEN

    T1 - Evolutionary automated recognition and characterization of an individual's artistic style

    AU - Kowaliw, Taras Michael

    AU - McCormack, Jon Paul

    AU - Dorin, Alan

    PY - 2010

    Y1 - 2010

    N2 - In this paper, we introduce a new image database, consisting of examples of artists' work. Successful classification of this database suggests the capacity to automatically recognize an artist's aesthetic style. We utilize the notion of Transform-based Evolvable Features as a means of evolving features on the space, these features are then evaluated through a standard classifier. We obtain recognition rates for our six artistic styles - relative to images by the other artists and images randomly downloaded from a search engine - of a mean true positive rate of 0.946 and a mean false positive rate of 0.017. Distance metrics designed to indicate the similarity between an arbitrary greyscale image and one of the artistic styles are created from the evolved features. These metrics are capable of ranking control images so that artist-drawn instances appear at the front of the list. We provide evidence that other images ranked as similar by the metric correspond to naïve human notions of similarity as well, suggesting the distance metric could serve as a content-based aesthetic recommender. © 2010 IEEE.

    AB - In this paper, we introduce a new image database, consisting of examples of artists' work. Successful classification of this database suggests the capacity to automatically recognize an artist's aesthetic style. We utilize the notion of Transform-based Evolvable Features as a means of evolving features on the space, these features are then evaluated through a standard classifier. We obtain recognition rates for our six artistic styles - relative to images by the other artists and images randomly downloaded from a search engine - of a mean true positive rate of 0.946 and a mean false positive rate of 0.017. Distance metrics designed to indicate the similarity between an arbitrary greyscale image and one of the artistic styles are created from the evolved features. These metrics are capable of ranking control images so that artist-drawn instances appear at the front of the list. We provide evidence that other images ranked as similar by the metric correspond to naïve human notions of similarity as well, suggesting the distance metric could serve as a content-based aesthetic recommender. © 2010 IEEE.

    UR - http://www.scopus.com/inward/record.url?scp=79959415775&partnerID=8YFLogxK

    U2 - 10.1109/CEC.2010.5585975

    DO - 10.1109/CEC.2010.5585975

    M3 - Conference Paper

    SN - 9781424469109

    SP - 2234

    EP - 2241

    BT - Proceedings of the 2010 IEEE Congress on Evolutionary Computation (IEEE CEC 2010)

    A2 - Sobrevilla, Pilar

    A2 - Fogel, Gary

    A2 - Ishibuchi, Hisao

    PB - IEEE, Institute of Electrical and Electronics Engineers

    CY - Piscataway NJ USA

    ER -

    Kowaliw TM, McCormack JP, Dorin A. Evolutionary automated recognition and characterization of an individual's artistic style. In Sobrevilla P, Fogel G, Ishibuchi H, editors, Proceedings of the 2010 IEEE Congress on Evolutionary Computation (IEEE CEC 2010). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2010. p. 2234 - 2241. 5585975 https://doi.org/10.1109/CEC.2010.5585975