• DocumentCode
    1627910
  • Title

    A rough set approach to extract painting composition rules

  • Author

    Ohira, Tomomi ; Nakamura, Tsuyoshi ; Kanoh, Masayoshi ; Kunitachi, Tsutomu ; Itoh, Hidenori

  • Author_Institution
    Grad. Sch. of Eng., Nagoya Inst. of Technol., Nagoya, Japan
  • fYear
    2009
  • Firstpage
    1574
  • Lastpage
    1578
  • Abstract
    Non-photorealistic rendering (NPR) is a technique used in the field of computer graphics. Here, we restrict our attention to the subset of NPR developed to synthesize drawing and painting techniques. Specifically, we focus on the style of Cubist art, such as the works of Picasso. First, we examine the actual works of Picasso in order to understand and improve the qualities of Cubist style rendering. As a result, the painting composition rules are expected to be extracted from the analysis of Picasso´s works. In the present paper, we propose a Cubist style rendering based on the analysis of painting compositions. The present paper describes the proposed method by which to construct a painting composition database and illustrates the rules extracted from the database. We use rough set theory to extract the rules, and using these rules; we render and illustrate a sample image in Cubist style.
  • Keywords
    rendering (computer graphics); rough set theory; visual databases; Cubist art; Cubist style rendering; Picasso; computer graphics; nonphotorealistic rendering; painting composition analysis; painting composition database; painting composition rule extraction; rough set theory; Art; Computer graphics; Data visualization; Eyes; Image databases; Mouth; Nose; Painting; Rendering (computer graphics); Set theory;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Fuzzy Systems, 2009. FUZZ-IEEE 2009. IEEE International Conference on
  • Conference_Location
    Jeju Island
  • ISSN
    1098-7584
  • Print_ISBN
    978-1-4244-3596-8
  • Electronic_ISBN
    1098-7584
  • Type

    conf

  • DOI
    10.1109/FUZZY.2009.5277283
  • Filename
    5277283