![](bga.png)
current stage of the respective method development
into account. According to the subjective rankings
of results and in contrast to the computed confi-
dence score, the VF2 exact matching method was
the best one in the overall rating. This fact sup-
ports the assumption that exact matching is a better
method for determination of isomorphism in graph-
based datasets, where a set of tolerable technical lim-
itations is given.
5 CONCLUSION AND FUTURE
WORK
In this paper, we introduced Archistant, a complete
end-to-end system for search and retrieval of sim-
ilar floor plans for architects. By using this sys-
tem, we now have a complete automated pipeline
for sketching architectural concepts and searching for
similar ideas. We showed the capabilities of the im-
plemented retrieval techniques by means of both a
boundary test study (in order to show fundamental
performance capabilities and limitations of the meth-
ods) and a qualitative study (in order to show that the
methods produce reasonable results). In the boundary
test study, the VF2-based and MetisCBR replied flaw-
lessly and the index-based method at least answered
most queries without errors. In the qualitative anal-
ysis, each method showed at least in some situation
good performances. The currently implemented fin-
gerprints mainly take graph-based floor-ground prop-
erties into account. Geometric properties are not con-
sidered. But these information have a big potential for
making search results more accurate. A large-scale
user study resulting in a big ground-truth database
may be conducted in future and may hereby lead to
the deployment of machine learning for automatically
selecting the best approach for every search scenario
in future.
REFERENCES
Ahmed, S., Weber, M., Liwicki, M., Langenhan, C., Den-
gel, A., and Petzold, F. (2014). Automatic analysis
and sketch-based retrieval of architectural floor plans.
Pattern Recognition Letters, 35:91–100.
Ayzenshtadt, V., Langenhan, C., Bukhari, S. S., Althoff,
K.-D., Petzold, F., and Dengel, A. (2015). Dis-
tributed domain model for the case-based retrieval
of architectural building designs. In Petridis, M.,
Roth-Berghofer, T., and Wiratunga, N., editors, Pro-
ceedings of the 20th UK Workshop on Case-Based
Reasoning. UK Workshop on Case-Based Reason-
ing (UKCBR-2015), located at SGAI International
Conference on Artificial Intelligence, December 15-
17, Cambridge, United Kingdom. School of Com-
puting, Engineering and Mathematics, University of
Brighton, UK.
Ayzenshtadt, V., Langenhan, C., Bukhari, S. S., Althoff, K.-
D., Petzold, F., and Dengel, A. (2016a). Thinking with
containers: A multi-agent retrieval approach for the
case-based semantic search of architectural designs.
In Filipe, J. and van den Herik, J., editors, Proceed-
ings of the 8th International Conference on Agents
and Artificial Intelligence. International Conference
on Agents and Artificial Intelligence (ICAART-2016),
February 24-26, Rome, Italy. SCITEPRESS.
Ayzenshtadt, V., Langenhan, C., Roth, J., Bukhari, S. S.,
Althoff, K.-D., Petzold, F., and Dengel, A. (2016b).
Comparative evaluation of rule-based and case-based
retrieval coordination for search of architectural build-
ing designs. In Goel, A., Roth-Berghofer, T., and
Diaz-Agudo, B., editors, Case-based Reasoning in
Research and Development. International Conference
on Case-Based Reasoning (ICCBR-16), 24th Interna-
tional Conference on Case Based Reasoning, October
31 - November 2, Atlanta,, Georgia, USA. Springer,
Berlin, Heidelberg.
Bayer, J., Bukhari, S. S., Langenhan, C., Eichenberger-
Liwicki, M., Althoff, K.-D., Petzold, F., and Den-
gel, A. (2015). Migrating the classical pen-and-paper
based conceptual sketching of architecture plans to-
wards computer tools - prototype design and evalua-
tion.
Bengoetxea, E. (2002). Inexact graph matching using es-
timation of distribution algorithms. Ecole Nationale
Sup
´
erieure des T
´
el
´
ecommunications, Paris, 2:4.
Cavieres, A., Bhatia, U., Joshi, P., Zhao, F., and Ram, A.
(2011). CBArch: A Case-Based Reasoning Frame-
work for Conceptual Design of Commercial Build-
ings. Artificial Intelligence and Sustainable Design
– Papers from the AAAI 2011 Spring Symposium (SS-
11-02), pages 19–25.
Chen, C., Yan, X., Yu, P. S., Han, J., Zhang, D.-Q., and
Gu, X. (2007). Towards graph containment search
and indexing. In Proceedings of the 33rd international
conference on Very large data bases, pages 926–937.
VLDB Endowment.
Cheng, J., Ke, Y., Ng, W., and Lu, A. (2007). Fg-
index: towards verification-free query processing on
graph databases. In Proceedings of the 2007 ACM
SIGMOD international conference on Management of
data, pages 857–872. ACM.
Cordella, L. P., Foggia, P., Sansone, C., and Vento, M.
(2004). A (sub) graph isomorphism algorithm for
matching large graphs. Pattern Analysis and Machine
Intelligence, IEEE Transactions on, 26(10):1367–
1372.
Foggia, P., Sansone, C., and Vento, M. (2001). A perfor-
mance comparison of five algorithms for graph iso-
morphism. In Proceedings of the 3rd IAPR TC-15
Workshop on Graph-based Representations in Pattern
Recognition, pages 188–199.
Giugno, R. and Shasha, D. (2002). Graphgrep: A fast
and universal method for querying graphs. In Pattern
Semantic Pattern-based Retrieval of Architectural Floor Plans with Case-based and Graph-based Searching Techniques and their Evaluation
and Visualization
59