Abstract: This paper presents a new CBIR system which consists of an image representation and a database structure. The main idea of our approach is based on a new object representation which consists of approximation of objects by a set of shapes, called primitives. Because storing images in the multimedia database is a very demanding task, we propose a tree-based structure which consist of two types of nodes: common nodes and data nodes. Common nodes are used to organize graphs in the same parts of the tree, whereas data nodes are used to store graphs. The proposed multimedia database architecture allows easier queries for users, supporting both example image as a query and a sketch drawn by a user. The queries are processed without unnecessary graph comparisons which reduces the time of image retrieval. Another advantage is the ability to use different lower level data storage methods.
B I B L I O G R A F I ABielecka, M. Skomorowski, M. (2007) Fuzzy-aided Parsing for Pattern Recognition. Berlin, Heidelberg: Springer Berlin Heidelberg, 2007, pp. 313–318. ISBN 978-3-540-75175-5. [Online]. Available: http://dx.doi.org/10.1007/978-3-540-75175-5_39
Deniziak, R.S. Krechowicz, A. (2017): “New content based image retrieval database structure using query by approximate shapes,” in Communication Papers of the 2017 Federated Conference on Computer Science and Information Systems, M. Ganzha, L. Maciaszek, M. Paprzycki (eds). ACSIS, 13, pp. 177–182. doi: 10.15439/2017F195
Deniziak, R.S. Michno, T. (2015): Query by shape for image retrieval from multimedia databases. Kozielski, S., Mrozek, D., Kasprowski, P., Malysiak-Mrozek, B., Kostrzewa, D. (eds.) Beyond Databases, Architectures and Structures. CCIS, Springer, Ustroń, 521, pp. 377–386. doi: 10.1007/978-3-319-18422-7 33
Deniziak, R.S. Michno, T. (2015): Query-by-shape interface for content based image retrieval. 2015 8th International Conference on Human System Interaction (HSI), IEEE, Warsaw, pp. 108–114. doi: 10.1109/HSI.2015.7170652
Deniziak, R. S. Michno, T. (2016): Content based image retrieval using query by approximate shape. In: 2016 Federated Conference on Computer Science and Information Systems (FedCSIS), IEEE, Gdańsk, pp. 807–816. doi: 10.15439/2016f233
Deniziak, R. S. Michno, T. (2017): New content based image retrieval database structure using query by approximate shapes. 2017 Federated Conference on Computer Science and Information Systems (FedCSIS), IEEE, Prague, pp. 613–621. doi: 10.15439/2017F457
Deniziak, R.S. Michno, T.
Krechowicz, A. (2015): The scalable distributed two-layer content based image retrieval data store. 2015 Federated Conference on Computer Science and Information Systems (FedCSIS), IEEE, Lódź, pp. 827–832. doi: 10.15439/2015F272
Kato, T. Kurita, T. Otsu, N. Hirata, K. (1992): A sketch retrieval method for full color image database-query by visual example. 11th IAPR International Conference on Pattern Recognition, IEEE, The Hague, pp. 530-533. doi: 10.1109/ICPR.1992.2016167
Kiranyaz, S. Gabbouj, M. (2007): Hierarchical cellular tree: An efficient indexing scheme for content-based retrieval on multimedia databases. Multimedia, IEEE Transactions on, 9(1), pp. 102–119.
Kriegel, H. P. Kroger, P. Kunath, P. Pryakhin, A. (2006): Effective similarity search in multimedia databases using multiple representations. 2006 12th International Multi-Media Modelling Conference. IEEE, Beijing. doi:10.1109/MMMC.2006.1651355
Lalos, C. Doulamis, A. Konstanteli, K. Dellias, P. Varvarigou, T. (2008): An innovative content-based indexing technique with linear response suitable for pervasive environments. 2008 International Workshop on Content-Based Multimedia Indexing, IEEE, London (London), pp. 462–469. doi: 10.1109/CBMI.2008.4564983
Li, C.-Y. Hsu, C.-T. (2008): Image retrieval with relevance feedback based on graph-theoretic region correspondence estimation. IEEE Transactions on Multimedia, IEEE, 10(3), pp. 447-456., doi: 10.1109/tmm.2008.917421
Li, B. Lu, Y. Shen, J. (2016): A semantic tree-based approach for sketch-based 3d model retrieval. In 2016 23rd International Conference on Pattern Recognition (ICPR), EEE, Cancun, pp. 3880-3885. doi: 10.1109/ICPR.2016.7900240
Mocofan, M. Ermalai, I. Bucos, M. Onita, M. Dragulescu, B. (2011): Supervised tree content based search algorithm for multimedia image databases. 2011 6th IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI), IEEE, Timisoara, pp. 469-472. doi: 10.1109/SACI.2011.5873049
Qian, X. Tan, X. Zhang, Y. Hong, R. Wang, M. (2016): Enhancing sketch-based image retrieval by re-ranking and relevance feedback. IEEE Transactions on Image Processing, 25(1), pp. 195–208. doi: 10.1109/TIP.2015.2497145
Shih, T. K. (2002): Distributed multimedia databases, T. K. Shih, Ed. Hershey, PA, USA: IGI Global, 2002, ch. Distributed Multimedia Databases, pp. 2–12. ISBN 1-930708-29-7. [Online]. Available: http://dl.acm.org/citation.cfm?id=510695.510697
Sitek, P. Wikarek, J. (2016): A hybrid programming framework for modeling and solving constraint satisfaction and optimization problems. Scientific Programming, Article ID 5102616. (2016). doi:10.1155/2016/5102616
Śluzek, A. (2016): Machine vision in food recognition: Attempts to enhance CBVIR tools. Ganzha, M., Maciaszek, L. A., Paprzycki, M. (eds.) Position Papers of the 2016 Federated Conference on Computer Science and Information Systems, FedCSIS. PTI, Gdańsk (2016). doi: 10.15439/2016f579
Śluzek, A. (2005): On moment-based local operators for detecting image patterns. Image and Vision Computing, 23(3), pp. 287 – 298.
Wang, H. H. Mohamad, D. Ismail, N. A. (2010): Approaches, challenges and future direction of image retrieval. In: Journal of Computing, New York, 2(6).
Zhang, Y. Qian, X. Tan, X. Han, J. Tang, Y. (2016): Sketch-based image retrieval by salient contour reinforcement. IEEE Transactions on Multimedia, 18(8), pp. 1604–1615. doi: 10.1109/TMM.2016.2568138 
Pełny tekst