Computer analysis of Van Gogh's complementary colours

Igor Berezhnoy*, Eric Postma, Jaap van den Herik

*Corresponding author for this work

    Research output: Contribution to journalArticleAcademicpeer-review

    Abstract

    Traditionally, the analysis of visual arts is performed by human art experts only. The availability of advanced artificial intelligence techniques makes it possible to support art experts in their judgement of visual art. In this article currently available image-analysis techniques are applied. Our aim is (1) to determine how successful the usage of complementary colours was in the oeuvre of Vincent Van Gogh and (2) whether this characteristic may make his paintings identifiable in time. It is commonly acknowledged that, especially in his French period, Van Gogh started employing complementary colours to emphasize contours of objects or parts of scenes. This article proposes a new method called MECOCO1 to measure complementary-colour usage in a painting by combining ail opponent-colour space representation with Gabor filtering. To achieve the aim, (1) we defined a novel measure called the opponency value that quantifies the usage of complementary-colour transitions in a painting and (2) we studied Van Gogh's painting style. MECOCO's analysis of a dataset of 145 digitised and colour-calibrated oil-on-canvas paintings confirms the global transition pattern of complementary colours in Van Gogh's paintings as generally acknowledged by art experts. In addition, MECOCO also provides an objective and quantifiable way to support the allalysis of colours in individual paintings. (c) 2006 Elsevier B.V. All rights reserved.

    Original languageEnglish
    Pages (from-to)703-709
    Number of pages7
    JournalPattern Recognition Letters
    Volume28
    Issue number6
    DOIs
    Publication statusPublished - 15 Apr 2007

    Keywords

    • linage analysis
    • color analysis
    • automatic painting analysis
    • Gabor filters
    • opponent colors
    • CIELab space
    • REPRESENTATION

    Cite this