Abstract
Retrieval of similar scenes in ancient murals research is an important but time-consuming job for researchers. However, content-based image retrieval (CBIR) systems cannot fully deal with such issues since they lack of the abilities to handle complex semantic and image composition queries. In this paper, we introduce a new semantic scene-retrieval approach for ancient murals. Our method can retrieve related scenes according to both their content elements and their composition through a two-phase procedure. Then, retrieved scenes are ranked according to composition-based criterion that incorporates the relevance of semantic content and visual structures with scene compactness ratio. Hence, the sorted results are tailored to the real intent of query. The experiments demonstrate the efficiency and effectiveness of our approach to reduce the semantic gap of visual information retrieval. Furthermore, the retrieval results for Dunhuang murals suggest the potential applications for general paintings retrieval and personalized publishing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Academy, D.: Chinese Grotto-Dunhuang Grotto. Cultural Relic Publishing House, Beijing (1987) (in Chinese)
Heng, F., Chua, T.S.: A boostrapping approach to annotating large image collection. In: Workshop on Multimedia Information Retrieval in ACM Multimedia, pp. 55–620. ACM Press, New York (2003)
Hu, T.Q.: An introduction to dunhuang grotto art. Dunhuang Research (3), 16–34 (1993) (in Chinese)
Jin, W., Shi, R., Chua, T.S.: A semi-naive bayesian method incorporating clustering with pair-wise constraints for auto image annotation. In: ACM Multimedia, pp. 336–339. ACM Press, New York (2004)
Johnson, M.: Semantic Segmentation and Image Search. Phd thesis, University of Cambridge (2008)
Leacock, C., Chodorow, M.: Combining local context and wordnet similarity for word sense identification. In: WordNet: A Lexical Reference System and Its Application, pp. 265–283. MIT Press, Cambridge (1998)
Li, X., Lu, D.M., Pan, Y.H.: Color restoration and image retrieval for dunhuang fresco preservation. IEEE MultiMedia 7(2), 38–42 (2000)
Li, Y., Bilmes, J., Shapiro, L.: Object class recognition using images of abstract regions. In: International Conference on Pattern Recognition, pp. 40–43. IEEE Press, Washington (2004)
Lu, D.M., Pan, Y.H.: Image and semantic feature based dunhuang mural retrieval. Chinese Journal of Computers 21(11), 1022–1026 (1998) (in Chinese)
Lu, Y., Hu, C., Zhu, X., Zhang, H., Yang, Q.: A unified framework for semantics and feature based relevance feedback in image retrieval systems. In: ACM Multimedia, pp. 31–37. ACM Press, New York (2000)
Mezaris, V., Kompatsiaris, I., Strintzis, M.G.: An ontology approach to object-based image retrieval. In: ICIP, pp. 511–514. IEEE Press, Washington (2003)
Natsev, A., Haubold, A., Tešić, J., Xie, L., Yan, R.: Semantic concept-based query expansion and re-ranking for multimedia retrieval. In: The 15th international conference on Multimedia, pp. 991–1000. ACM Press, New York (2007)
Peterson, B.F.: Learning to See Creatively. Amphoto Press, New York (2003)
Tatatinov, I., Viglas, S.D., Beyer, K., et al.: Storing and querying ordered xml using a relational database system. In: Proceedings of the 21th ACM SIGMOD International Conference on Management of Data, pp. 204–215. ACM Press, New York (2002)
Tsugunari, K., Akira, Y. (tr.).: The Lotus Sutra. Numata Center for Buddhist Translation and Research, 2nd edn., Berkeley, Calif. (2007)
Vogel, J., Schiele, B.: Natural scene retrieval based on a semantic modeling step. In: Enser, P.G.B., Kompatsiaris, Y., O’Connor, N.E., Smeaton, A., Smeulders, A.W.M. (eds.) CIVR 2004. LNCS, vol. 3115, pp. 207–215. Springer, Heidelberg (2004)
Zhang, C., Jiang, J., Pan, Y.: Dunhuang frescoes retrieval based on similarity calculation of color and texture features. In: The IEEE Conference on Information Visualisation, pp. 96–100. IEEE Press, Washington (1997)
Zhang, Y.L.: Iconographical study of the two buddhas sitting together at dunhuang, from the northern dynasties to the sui dynasty. Dunhuang Research (4), 24–32 (2009) (in chinese)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, Q., Lu, D., Zhang, H. (2010). Composition Based Semantic Scene Retrieval for Ancient Murals. In: Qiu, G., Lam, K.M., Kiya, H., Xue, XY., Kuo, CC.J., Lew, M.S. (eds) Advances in Multimedia Information Processing - PCM 2010. PCM 2010. Lecture Notes in Computer Science, vol 6297. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15702-8_1
Download citation
DOI: https://doi.org/10.1007/978-3-642-15702-8_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15701-1
Online ISBN: 978-3-642-15702-8
eBook Packages: Computer ScienceComputer Science (R0)