Applications of Image Understanding in Semantics-Oriented
Multimedia Information Retrieval

Zhongfei (Mark) Zhang Rohini K. Srihari Aibing Rao
Computer Science Dept. Dept. of Comp. Sci. & Eng.
SUNY Binghamton SUNY Bu
alo
zhongfei@cs.binghamton.edu frohini,araog@cedar.buffalo.edu

Abstract
This paper focuses on research in development of
semantics-oriented multimedia information retrieval
techniques. Semantics-oriented information retrieval
addresses the effectiveness of the retrieval. With
the goal of significantly improving retrieval precision
and query capability, image understanding technologies 
are applied to develop effective retrieval techniques. 
Specifically, three techniques are developed by
combining IU technologies (i.e., face detection) with
other existing or developed techniques (i.e., text indexing, 
conventional similarity matching, and face
identification) for image retrieval. These techniques
are evaluated to demonstrate the significance of the
semantics-oriented multimedia information retrieval.


References
[1] D.A. Forsyth. Computer vision tools for finding
images and video sequences. Library Trends, Special Issue on Progress in Visual Information 
Access and Retrieval, 48(2):326{355, 1999.
[2] Z. Hong. Algebraic feature extraction of image for
recognition. Pattern Recognition, 24, 1991.
[3] S.Z. Li. Face recognition based on nearest linear
combinations. In Proc. CVPR. IEEE, 1998.
[4] H.A. Rowley, S. Baluja, and T. Kanade. Neural
network-based face detection. Trans. on PAMI,
20(1), 1998.
[5] G. Salton. Automatic text processing: the transformation, analysis, and retrieval of information
by computer. Addison Wesley, 1989.
[6] R.K. Srihari, Z. Zhang, and A. Rao. Image
background search: Combining object detection
techniques into content-based similarity image retrieval
(cbsir) systems. In Proc. of IEEE International 
Workshop on Content-Based Access of Image and Video Libraries. IEEE Press, June 1999.
[7] M. Turk and A. Pentland. Eigenfaces for recognition. Journal of Cognitive Neuroscience, 3(1),
1991.
[8] Z. Zhang and R.K. Srihari. Subspace morphing
theory for appearance based object identification.
In Proc. of International Conference on Advances
in Infrastructure for Electronic Business, Science,
and Education on the Internet, L'Aquila, Italy,
2000. Scuola Superiore G. Reiss Romoli.

