Abstract

Domes are architectural structural elements characteristicfor ecclesiastical and secular monumental buildings, like churches, basilicas,mosques, capitols and city halls. In the scope of building facadearchitectural style classification the current paper addresses the problemof architectural style classification of facade domes. Building facadeclassification by architectural styles is achieved by classification and votingof separate architectural elements, like domes, windows, towers, etc.Typical forms of the structural elements bear the signature of each architecturalstyle. Our approach classifies domes of three architectural styles- Renaissance, Russian and Islamic. We present a three-step approach,which in the first step analyzes the height and width of the dome for theidentification of Islamic saucer domes, in the second step detects goldencolor in YCbCr color space to determine Russian golden onion domesand in the third step performs classification based on dome shapes, usingclustering and learning of local features. Thus we combine three features- the relation of dome width and height, color and shape, in a singlemethodology to achieve high classification rate.

Reference

Shalunts, G., Haxhimusa, Y., & Sablatnig, R. (2012). Architectural Style Classification of Domes. In Advances in Visual Computing (pp. 420–429). Springer 2012. https://doi.org/10.1007/978-3-642-33191-6_41