*Project Title*
Incorporating Metric Access Methods to the CBISC

*Project Description* 

CBISC is a recently developed component that provides an easy-to-install search engine to query images by content. 
It can be  readily tailored for a particular collection by a domain expert, who carries out a clearly defined set of 
pilot experiments. It supports the use of different types of vector-based image descriptors (metric  and non-metric; 
color, texture, and shape descriptors; with different data structures to represent feature vectors), which can be chosen 
based on the pilot experiment, and then easily combined to yield improved effectiveness. Besides, it encapsulates a metric 
index structure to speed up the search process, that can be  easily configured for different image collections.

Currently, the CBISC allows indexing images by using a metric access method called M-tree. This project aims to incorporate 
other MAMs (e.g., Slim-tree) into CBISC.

*Language/technology skills*
Java

*Number of People*
1-2

*Project Resources*

1. R. da S. Torres, C. B. Medeiros, M. A. Goncalves, and E. A. Fox, A Digital Library Framework for Biodiversity 
Information Systems, International Journal on Digital Libraries, 6(1):3-17, February, 2006. 
http://www.ic.unicamp.br/~rtorres/torres06ijdl.pdf

2. R. da S. Torres, C. B. Medeiros, M. A. Goncalves, and E. A. Fox, An OAI Compliant Content-Based Image Search 
Component , ACM-IEEE Joint Conference on Digital Libraries, Tucson, AZ, 418, June 2004.
http://www.ic.unicamp.br/~rtorres/torres04jcdldemo.pdf

3. C. Traina, B. Seeger, C. Faloutsos, and A. Traina, Fast Indexing and Visualization of Metric Datasets Using 
Slim-Trees, IEEE Transactions on Knowledge and Data Engineering,14, 2, 244-260, March/April, 2002