A System to Detect Rooms in Architectural Floor Plan Images

Abstract : In this article, a system to detect rooms in architectural floor plan images is described. We first present a primitive extraction algorithm for line detection. It is based on an original coupling of classical Hough transform with image vectorization in order to perform robust and efficient line detection. We show how the lines that satisfy some graphical arrangements are combined into walls. We also present the way we detect some door hypothesis thanks to the extraction of arcs. Walls and door hypothesis are then used by our room segmentation strategy; it consists in recursively decomposing the image until getting nearly convex regions. The notion of convexity is difficult to quantify, and the selection of separation lines between regions can also be rough. We take advantage of knowledge associated to architectural floor plans in order to obtain mostly rectangular rooms. Qualitative and quantitative evaluations performed on a corpus of real documents show promising results.
Type de document :
Communication dans un congrès
IAPR International Workshop on Document Analysis Systems - DAS 2010, Jun 2010, Boston, MA, United States. ACM, pp.167-174, 2010, ACM International Conference Proceedings Series
Liste complète des métadonnées

https://hal.inria.fr/inria-00493393
Contributeur : Hervé Locteau <>
Soumis le : vendredi 18 juin 2010 - 16:24:17
Dernière modification le : mardi 24 avril 2018 - 13:37:28

Identifiants

  • HAL Id : inria-00493393, version 1

Collections

Citation

Sébastien Macé, Hervé Locteau, Ernest Valveny, Salvatore Tabbone. A System to Detect Rooms in Architectural Floor Plan Images. IAPR International Workshop on Document Analysis Systems - DAS 2010, Jun 2010, Boston, MA, United States. ACM, pp.167-174, 2010, ACM International Conference Proceedings Series. 〈inria-00493393〉

Partager

Métriques

Consultations de la notice

283