Information Technology Reference
In-Depth Information
11.5 Conclusions
This chapter described the basic techniques and some fundamental prob-
lems for indexing and retrieving ubiquitous visual information. Section 11.2
introduced MEPG-7 visual descriptors and their similarity matching meth-
ods, with the focus on some basic visual features. Some experimental results
were presented to demonstrate the properties of various features that help
readers with some practical knowledge of their performance in potential
applications. Section 11.3 discussed two key problems of visual similarity of
images and visual feature aggregation techniques including linear weight-
ing and classifier combination. Experimental results were presented to show
how the aggregation strategy can improve the performance of retrieval. In
the last section, a practical system and user process was presented to show
how a system is constructed from techniques in this chapter.
References
1. ISO/IEC 15938-3:2002 Information technology: Multimedia content description
interface. Part 3: Visual.
2. ISO/IEC TR 15938-8:2002 Information technology: Multimedia content descrip-
tion interface. Part 8: Extraction and use of MPEG-7 descriptions.
3. T. E. Bjoerge, and E. Y. Chang. 2004, June. Why one example is not enough for an
image query. In IEEE International Conference on Multimedia and Expo., vol. 1,
27-30, 253-56.
4. G. Das, S. Ray, and C. Wilson. 2006. Feature re-weighting in content-based
image retrieval. In
Image and Video Retrieval, Proceedings,
ed. H. Sundaram et al.,
vol. 4071, 193-200.
5. R. Datta, J. Li, and J. Z. Wang. 2005, November. Content-based image retrieval:
Approaches and trends of the new age. In Proceedings of the 7th ACM SIGMM
International Workshop on Multimedia Information Retrieval, no. 253262,
Singapore.
6. H. Eidenberger. 2004. Statistical analysis of content-based mpeg-7 descriptors
for image retrieval.
Multimedia Systems
10:84-97.
7. Q. Iqbal and J. K. Aggarwal. 2003, September. Feature integration, multi-image
queries and relevance feedback in image retrieval. In the 6th International
Conference on Visual Information Systems (VISUAL 2003), 467-74, Miami, FL.
8. Michael S. Lew, ed. 2001.
Principles of Visual Information Retrieval.
Springer-
Verlag London Berlin.
9. Fenghui Ren. 2006. Multi-image query content-based image retrieval. Master's
thesis, University of Wollongong.
10. Y. Rui, T. S. Huang, M. Ortega, and S. Mehrotra. 1998, September. Relevance
feedback: A power tool for interactive content-based image retrieval.
IEEE
Transactions on Circuits and Systems for Video Technology
8 (5): 644-55.
