High-level feature aggregation for fine-grained architectural floor plan retrieval

Divya Sharma; Chiranjoy Chattopadhyay

High-level feature aggregation for fine-grained architectural floor plan retrieval

View Fulltext

Author(s): Divya Sharma¹ and Chiranjoy Chattopadhyay¹
- Affiliations: 1: Department of Computer Science and Engineering , Indian Institute of Technology Jodhpur, Jodhpur , India
Source: Volume 12, Issue 5, August 2018, p. 702 – 709
DOI: 10.1049/iet-cvi.2017.0581 , Print ISSN 1751-9632, Online ISSN 1751-9640

Received 23/11/2017, Accepted 12/03/2018, Revised 15/02/2018, Published 14/03/2018

Due to the massive growth of real estate industry, there is an increase in the number of online platforms designed for finding homes/furnished properties. Instead of descriptive words, query by example is always a preferred method for retrieval. Floor plans are the basic 2D representation giving an idea about the building structure at a particular level. The authors propose a framework for the retrieval of similar architectural floor plans under the query by example paradigm. They propose a novel algorithm to extract high-level semantic features from an architectural floor plan. Fine-grained retrieval using weighted sum of the features is proposed, where a feature can be given more preference over others, during retrieval. Experiments were performed on publicly available dataset containing 510 floor plans and compared with existing state-of-the-art techniques. Their proposed method outperforms others both in qualitative and quantitative terms.

References

1. 1)
  - 12. Sharma, D., Chattopadhyay, C., Harit, G.: ‘A unified framework for semnatic matching of architectural floorplans’. Int. Conf. Pattern Recognition (ICPR), Cancun, Mexico, 2016.
2. 2)
  - 3. Dutta, A., Lladós, J., Bunke, H., et al: ‘Near convex region adjacency graph and approximate neighborhood string matching for symbol spotting in graphical documents’. Int. Conf. Document Analysis and Recognition (ICDAR), Washington DC, USA, 2013.
3. 3)
  - 21. Lazebnik, S., Schmid, C., Ponce, J.: ‘Beyond bags of features: spatial pyramid matching for recognizing natural scene categories’. Computer Vision and Pattern Recognition (CVPR), New York, NY, USA, 2006.
4. 4)
  - 6. Aoki, Y., Shio, A., Arai, H., et al: ‘A prototype system for interpreting hand-sketched floor plans’. Int. Conf. Pattern Recognition (ICPR), Vienna, Austria, 1996.
5. 5)
  - 4. Ahmed, S., Liwicki, M., Weber, M., et al: ‘Automatic room detection and room labeling from architectural floor plans’. Document Analysis Systems (DAS), Queensland, Australia, 2012.
6. 6)
  - 16. Rusiñol, M., Borràs, A., Lladós, J.: ‘Relational indexing of vectorial primitives for symbol spotting in line-drawing images’, Phys. Rev. Lett., 2010, 31, (3), pp. 188–201.
7. 7)
  - 13. Delalandre, M., Valveny, E., Pridmore, T., et al: ‘Generation of synthetic documents for performance evaluation of symbol recognition and spotting systems’, Int. J. Doc. Anal. Recognit. (IJDAR), 2010, 13, (3), pp. 187–207.
8. 8)
  - 8. Ahmed, S., Liwicki, M., Weber, M., et al: ‘Improved automatic analysis of architectural floor plans’. Int. Conf. Document Analysis and Recognition (ICDAR), Beijing, China, 2011.
9. 9)
  - 11. Ahmed, S., Weber, M., Liwicki, M., et al: ‘Automatic analysis and sketch-based retrieval of architectural floor plans’, Phys. Rev. Lett., 2014, 35, pp. 91–100.
10. 10)
  - 19. Chechik, G., Shalit, U., Sharma, V., et al: ‘An online algorithm for large scale image similarity learning’. Neural Information Processing Systems (NIPS), Vancouver, Canada, 2009.
11. 11)
  - 14. Bannister, A.: ‘Elements of civil engineering’ (Pearson Education,India, 2010).
12. 12)
  - 5. Bay, H., Ess, A., Tuytelaars, T., et al: ‘Speeded-up robust features (SURF)’, Computer Vision and Image Understanding (CVIU), 2008, 110, (3), pp. 346–359.
13. 13)
  - 18. Levenshtein, V.I.: ‘Binary codes capable of correcting deletions, insertions and reversals’, Sov. Phys.-Dokl., 1966, 10, p. 707.
14. 14)
  - 1. Lambert, G., Gao, H.: ‘Line moments and invariants for real time processing of vectorized contour data’. Indian Academy of Pediatrics (IAP), San Remo, Italy, 1995.
15. 15)
  - 15. de las Heras, L.-P., Terrades, O.R., Robles, S., et al: ‘CVC-FP and SGT:A new database for structural floor plan analysis and its groundtruthing tool’, Int. J. Doc. Anal. Recognit. (IJDAR), 2015, 18, (1), pp. 15–30.
16. 16)
  - 7. Lladós, J., López-Krahe, J., Martí, E.: ‘A system to understand hand-drawn floor plans using subgraph isomorphism and hough transform’, Motor Vehicle Administration (MVA), 1997, 10, (3), pp. 150–158.
17. 17)
  - 10. Qiu, H., Hancock, E.R.: ‘Graph matching and clustering using spectral partitions’, PR, 2006, 39, (1), pp. 22–34.
18. 18)
  - 17. Sharma, D., Gupta, N., Chattopadhyay, C., et al: ‘DANIEL: A deep architecture for automatic analysis and retrieval of building floor plans’. Int. Conf. Document Analysis and Recognition (ICDAR), Kyoto, Japan, 2017.
19. 19)
  - 20. de las Heras, L.-P., Fernández, D., Fornés, A., et al: ‘Runlength histogram image signature for perceptual retrieval of architectural floor plans’. Graphics Recognition (GREC), Bethlehem, PA, USA, 2013.
20. 20)
  - 9. Bunke, H.: ‘Graph matching: theoretical foundations, algorithms, and applications’, Proc. VI, 2000, 2000, pp. 82–88.
21. 21)
  - 2. Dutta, A., Llados, J., Pal, U.: ‘Symbol spotting in line drawings through graph paths hashing’. Int. Conf. Document Analysis and Recognition (ICDAR), Beijing, China, 2011.

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

High-level feature aggregation for fine-grained architectural floor plan retrieval

References

Related content