Browse > Article
http://dx.doi.org/10.7780/kjrs.2018.34.4.11

A Method for Text Information Separation from Floorplan Using SIFT Descriptor  

Shin, Yong-Hee (Department of Civil and Environmental Engineering, Seoul National University)
Kim, Jung Ok (Institute of Construction and Environmental Engineering, Seoul National University)
Yu, Kiyun (Department of Civil and Environmental Engineering, Seoul National University)
Publication Information
Korean Journal of Remote Sensing / v.34, no.4, 2018 , pp. 693-702 More about this Journal
Abstract
With the development of data analysis methods and data processing capabilities, semantic analysis of floorplans has been actively studied. Therefore, studies for extracting text information from drawings have been conducted for semantic analysis. However, existing research that separates rasterized text from floorplan has the problem of loss of text information, because when graphic and text components overlap, text information cannot be extracted. To solve this problem, this study defines the morphological characteristics of the text in the floorplan, and classifies the class of the corresponding region by applying the class of the SIFT key points through the SVM models. The algorithm developed in this study separated text components with a recall of 94.3% in five sample drawings.
Keywords
Floorplan; SIFT Descriptor; Connected Components; Support Vector Machine Model;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Ahmed, S., M. Liwicki, M. Weber, and A. Dengel, 2011.Text/graphics segmentation in architectural floor plans, Proc. of 2011 Document Analysis and Recognition (ICDAR) International Conference on IEEE, Beijing, China, Sep.18-21, pp.734-738.
2 Cortes, C. and V. Vapnik, 1995. Support-vector networks, Machine learning, 20(3): 273-297.   DOI
3 Csurka, G., C. Dance, L. Fan, J. Willamowski, and C. Bray, 2004. Visual categorization with bags of keypoints, Proc. of 2004 Workshop on statistical learning in computer vision, 8th European Conference on Computer Vision, Prague, Czech Republic, May 10-16, vol. 1, pp. 1-22.
4 Lam, O., F. Dayoub, R. Schulz, and P. Corke, 2015. Automated topometric graph generation from floor plan analysis, Proc. of 2015 Australasian Conference on Robotics and Automation, ACRA, Canberra, Australia, Dec. 2-4, pp. 1-8.
5 de las Heras, L. P., S.Ahmed, M. Liwicki, E. Valveny, and G. Sanchez, 2014. Statistical segmentation and structural recognition for floor plan interpretation, International Journal on Document Analysis and Recognition, 17(3): 221-237.   DOI
6 Fletcher, L.A. and R. Kasturi, 1988. Arobust algorithm for text string separation from mixed text/ graphics images, IEEE transactions on pattern analysis and machine intelligence, 10(6): 910-918.   DOI
7 Hoang, T. V. and S. Tabbone, 2010. Text extraction from graphical document images using sparse representation, Proc. of 2010 Document Analysis Systems (DAS), 9th IAPR international workshop on document analysis systems, Cambridge, USA, Jun. 9-11, pp. 143-150.
8 Le, D. X., G. R. Thoma, and H. Wechsler, 1995. Classification of binary document images into textual or nontextual data blocks using neural network models, Machine Vision and Applications, 8(5): 289-304.   DOI
9 Lowe, D. G., 2004. Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, 60(2): 91-110.   DOI
10 Roy, P. P., U. Pal, and J. Llados, 2009. Touching text character localization in graphical documents using SIFT, Proc.of 2009 International Workshop on Graphics Recognition, Springer, LaRochelle, France, Jul. 22-23, pp. 199-211.
11 Tombre, K., S. Tabbone, L. Pélissier, B. Lamiroy, and P. Dosch, 2002. Text/graphics separation revisited, Proc. of 2002 International Workshopon Document Analysis Systems, Springer, Princeton, NJ, USA, Aug. 19-21, pp. 200-211.