Statistical segmentation and structural recognition for floor plan interpretation

A generic method for floor plan analysis and interpretation is presented in this article. The method, which is mainly inspired by the way engineers draw and interpret floor plans, applies two recognition steps in a bottom-up manner. First, basic building blocks, i.e., walls, doors, and windows are detected using a statistical patch-based segmentation approach. Second, a graph is generated, and structural pattern recognition techniques are applied to further locate the main entities, i.e., rooms of the building. The proposed approach is able to analyze any type of floor plan regardless of the notation used. We have evaluated our method on different publicly available datasets of real architectural floor plans with different notations. The overall detection and recognition accuracy is about 95 %, which is significantly better than any other state-of-the-art method. Our approach is generic enough such that it could be easily adopted to the recognition and interpretation of any other printed machine-generated structured documents.

[1]  Marcus Liwicki,et al.  a.SCAtch - A Sketch-Based Retrieval for Architectural Floor Plans , 2010, 2010 12th International Conference on Frontiers in Handwriting Recognition.

[2]  Laurent Wendling,et al.  Integrating vocabulary clustering with spatial relations for symbol recognition , 2013, International Journal on Document Analysis and Recognition (IJDAR).

[3]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[4]  Ernest Valveny,et al.  Notation-Invariant Patch-Based Wall Detector in Architectural Floor Plans , 2011, GREC.

[5]  Ihsin T. Phillips,et al.  Empirical Performance Evaluation of Graphics Recognition Systems , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Sergio Escalera,et al.  Circular Blurred Shape Model for symbol spotting in documents , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[7]  Joe Marks,et al.  Semi-automatic delineation of regions in floor plans , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[8]  Yasuhiro Aoki,et al.  A prototype system for interpreting hand-sketched floor plans , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[9]  Philippe Dosch,et al.  Reconstruction of the 3D structure of a building from the 2D drawings of its floors , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

[10]  Ernest Valveny,et al.  Unsupervised and Notation-Independent Wall Segmentation in Floor Plans Using a Combination of Statistical and Structural Strategies , 2013, GREC.

[11]  Christian Ah-Soon,et al.  Variations on the analysis of architectural drawings , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[12]  Osamu Hori,et al.  Raster-to-vector conversion by line fitting based on contours and skeletons , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[13]  Kin Hong Wong,et al.  Highly Automatic Approach to Architectural Floorplan Image Understanding & Model Generation , 2005 .

[14]  Gemma Sánchez,et al.  And-Or Graph Grammar for Architectural Floor Plan Representation, Learning and Recognition. A Semantic, Structural and Hierarchical Model , 2011, IbPRIA.

[15]  Bart Lamiroy,et al.  Text/Graphics Separation Revisited , 2002, Document Analysis Systems.

[16]  Nicholas M. Patrikalakis,et al.  Knowledge-based interpretation of architectural drawings , 1992 .

[17]  Charles Elkan,et al.  Using the Triangle Inequality to Accelerate k-Means , 2003, ICML.

[18]  Ernest Valveny,et al.  A system to detect rooms in architectural floor plan images , 2010, DAS '10.

[19]  S. M. Lo,et al.  A graph-based algorithm for extracting units and loops from architectural floor plans for a building evacuation model , 2003, Comput. Aided Des..

[20]  Karl Tombre,et al.  The Search for Genericity in Graphics Recognition Applications: Design Issues of the Qgar Software System , 2004, Document Analysis Systems.

[21]  Tong Lu,et al.  Automatic analysis and integration of architectural drawings , 2007, International Journal of Document Analysis and Recognition (IJDAR).

[22]  Marcus Liwicki,et al.  Improved Automatic Analysis of Architectural Floor Plans , 2011, 2011 International Conference on Document Analysis and Recognition.

[23]  Ernest Valveny,et al.  Unsupervised Wall Detector in Architectural Floor Plans , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[24]  Marcus Liwicki,et al.  Automatic analysis and sketch-based retrieval of architectural floor plans , 2014, Pattern Recognit. Lett..

[25]  Reinhard Klein,et al.  The Room Connectivity Graph: Shape Retrieval in the Architectural Domain , 2008 .

[26]  Jaime López-Krahe,et al.  A system to understand hand-drawn floor plans using subgraph isomorphism and Hough transform , 1997, Machine Vision and Applications.

[27]  Umapada Pal,et al.  Symbol Spotting in Line Drawings through Graph Paths Hashing , 2011, 2011 International Conference on Document Analysis and Recognition.

[28]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[29]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[30]  Christian Ah-Soon,et al.  A complete system for the analysis of architectural drawings , 2000, International Journal on Document Analysis and Recognition.

[31]  Marcus Liwicki,et al.  Automatic Room Detection and Room Labeling from Architectural Floor Plans , 2012, 2012 10th IAPR International Workshop on Document Analysis Systems.

[32]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[33]  Salvatore Tabbone,et al.  Impact of a codebook filtering step on a galois lattice structure for graphics recognition , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[34]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[35]  Ernest Valveny,et al.  Wall Patch-Based Segmentation in Architectural Floorplans , 2011, 2011 International Conference on Document Analysis and Recognition.

[36]  Josep Lladós,et al.  A String Based Method to Recognize Symbols and Structural Textures in Architectural Plans , 1997, GREC.

[37]  Horst Bunke,et al.  An optimal algorithm for extracting the regions of a plane graph , 1993, Pattern Recognit. Lett..