• DocumentCode
    2212269
  • Title

    Classification of gothic and baroque architectural elements

  • Author

    Shalunts, Gayane ; Haxhimusa, Yll ; Sablatnig, Robert

  • Author_Institution
    Comput. Vision Lab., Vienna Univ. of Technol., Vienna, Austria
  • fYear
    2012
  • fDate
    11-13 April 2012
  • Firstpage
    316
  • Lastpage
    319
  • Abstract
    Architectural elements are the components and details of buildings. Their unique set, combination, design, construction technique form the architectural style of buildings. Building facade classification by architectural styles is viewed as a task of classifying separate architectural structural elements. In the scope of building facade architectural style classification the current paper targets the problem of classification of Gothic and Baroque architectural elements called tracery, pediment and balustrade. Since certain gradient directions dominate on the shape of each architectural element, discrimination between dominating gradients means classification of architectural elements and thus architectural styles. We use local features to describe gradient directions. Our approach is based on clustering and learning of local features and yields a high classification rate.
  • Keywords
    image classification; learning (artificial intelligence); pattern clustering; structural engineering computing; architectural structural element classification; balustrade; baroque architectural elements; building facade architectural style classification; dominating gradients; gothic classification; gradient directions; local feature clustering; pediment; tracery; Computer vision; Histograms; Shape; Three dimensional displays; Visualization; Windows; Architectural styles; classification; clustering; local features; structural elements;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Systems, Signals and Image Processing (IWSSIP), 2012 19th International Conference on
  • Conference_Location
    Vienna
  • ISSN
    2157-8672
  • Print_ISBN
    978-1-4577-2191-5
  • Type

    conf

  • Filename
    6208137