Detection and Classification of Facades

Panagiotis Panagiotopoulos, Anastasios Delopoulos


This paper presents a framework that exploits the expressive power of probabilistic geometric grammars to cope with the task of facade classification. In particular, we work on a dataset of rectified facades and we attempt to discover the origin of a number of query facade segments, contaminated with noise. The building block of our description are the windows of the facade. To this direction we develop an algorithm that achieves to accurately detect them. Our core contribution though, lies on the probabilistic manipulation of the geometry of the detected windows. In particular, we propose a simple probabilistic grammar to model this geometry and we propose a methodology for learning the parameters of the grammar from a single instance of each facade through a MAP estimation procedure. The produced generative model is essentially a detector of the particular facade. After producing one model per facade in our dataset, we proceed with the classification of the query segments. Promising results indicate that the simultaneous use of an appearance model together with our geometric formulation always achieved superior classification rates than the exclusive use of the appearance model itself, justifying the value of probabilistic geometric grammars for the task of facade classification.


  1. Baumann, S. (1995). A simplified attribute graph grammar for high level music recognition. In ICDAR, volume 2, pages 1080-1083. IEEE.
  2. Felzenszwalb, P. and Huttenlocher, D. P. (2005). Pictorial structures for object recognition. IJCV, 61(1):55-79.
  3. Felzenszwalb, P. and Schwartz, J. (2007). Hierarchical matching of deformable shapes. In CVPR. IEEE.
  4. Feng, H. and Zhu, S. C. (2005). Bottom-up/top-down image parsing by attribute graph grammar. In ICCV, 10, pages 1778-1785. IEEE.
  5. Fergus, R., Perona, P., and Zisserman, A. (2006). Weakly supervised scale-invariant learning of models for visual recognition. IJCV, 71:273-303.
  6. Fu, K. S. (1981). Syntactic Pattern Recognition and Applications. Prentice Hall.
  7. Holliday, D. J. and Samal, A. (1994). Recognizing plants using stochastic l-systems. In ICIP, volume 1, pages 183-187. IEEE.
  8. Holliday, D. J. and Samal, A. (1995). A stochastic grammar of images. Object recognition using L-system fractals, 16:33-42.
  9. Komodakis, N., Paragios, N., and Tziritas, G. (2008). Clustering via lp-based stabilities. In NIPS.
  10. Lewis, H. R. and Papadimitriou, D. (1998). Elements of the Theory of Computation. Prentice Hall.
  11. Liu, Y., Collins, R., and Tsin, Y. (2004). A computational model for periodic pattern perception based on frieze and wallpaper groups. Transactions on PAMI, 26(3):354-371.
  12. Lowe, D. G. (2004). Distinctive image features from scaleinvariant keypoints. IJCV, 2(60):91-110.
  13. Muller, P., Wonka, P., Haegler, S., Ulmer, A., and Gool, L. V. (2006). Procedural modeling of buildings. ACM Transactions on Graphics, Proceedings of ACM SIGGRAPH, 25:614-623.
  14. Rekers, J. and Schurr, A. (1997). Defining and parsing visual languages with layered graph grammars. Journal of Visual Language and Computing, 8(1):27-55.
  15. Ripperda, N. and Brenner, C. (2009). Application of a formal grammar to facade reconstruction in semiautomatic and automatic environments. In 12th AGILE Conference on GIScience.
  16. Rosten, E., Porter, R., and Drummond, T. (2009). Faster and better: A machine learning approach to corner detection. Transactions on PAMI, 32(1):105-119.
  17. Schindler, G., Krishnamurthy, P., Lublinerman, R., Liu, Y., and Dellaert, F. (2008). Detecting and matching repeated patterns for automatic geo-tagging in urban environments. In CVPR. IEEE.
  18. Teboul, O. (2011). Shape Grammar Parsing: Application to Image-based Modeling. PhD thesis, Ecole Centrale Paris.
  19. Teboul, O. (2012). Ecole Centrale Paris Facades Database.
  20. Teboul, O., Kokkinos, I., Simon, L., Koutsourakis, P., and Paragios, N. (2011). Shape grammar parsing via reinforcement learning. In CVPR. IEEE.
  21. Teboul, O., Simon, L., Koutsourakis, P., and Paragios, N. (2010). Segmentation of building facades using procedural shape prior. In CVPR. IEEE.
  22. Voorhees, E. M. (1999). Trec-8 question answering track report. In 8th Text Retrieval Conference.
  23. Wonka, P., Wimmer, M., Sillon, F., and Ribarsky, W. (2003). Instant architecture. ACM Transactions on Graphics, 22(3):669-677.
  24. Wu, C., Frahm, J., and Pollefeys, M. (2010). Detecting large repetitive structures with salient boundaries. In ECCV. Springer.
  25. You, F. and Fu, K. S. (1979). A syntactic approach to shape recognition using attributed grammars. Transactions on SMC, 9:334-345.
  26. Zhu, L., Chen, Y., Freeman, W., and Yuille, A. (2010a). Latent hierarchical structural learning for object detection. In CVPR. IEEE.
  27. Zhu, L., Chen, Y., Torralba, A., Freeman, W., and Yuille, A. (2010b). Part and appearance sharing: Recursive compositional models for multi-view multi-object detection. In CVPR. IEEE.

Paper Citation

in Harvard Style

Panagiotopoulos P. and Delopoulos A. (2013). Detection and Classification of Facades . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-47-1, pages 641-650. DOI: 10.5220/0004283506410650

in Bibtex Style

author={Panagiotis Panagiotopoulos and Anastasios Delopoulos},
title={Detection and Classification of Facades},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)},

in EndNote Style

JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)
TI - Detection and Classification of Facades
SN - 978-989-8565-47-1
AU - Panagiotopoulos P.
AU - Delopoulos A.
PY - 2013
SP - 641
EP - 650
DO - 10.5220/0004283506410650