In this article, we describe the FINT system, which stands for Find Images aNd Text. This system is built within the VindIT project, that focuses on handling large amounts of multi-media data. The current approach concentrates on searching in a combination of textual and visual data. The system described here is an iterative system that computes distances between the images. From each image (and corresponding case), a feature vector is extracted. The distances are now computed using these feature vectors. The distance computation can be different in each step of the iterative system. Here we will describe the system and settings that were used in the medical retrieval task of the ImageCLEF 2004 competition.
[1]
G. Cottrell,et al.
EMPATH: A Neural Network that Categorizes Facial Expressions
,
2002,
Journal of Cognitive Neuroscience.
[2]
Hinrich Schütze,et al.
Ambiguity resolution in language learning
,
1997
.
[3]
Stanley Peters,et al.
Query translation method for cross language information retrieval
,
1999
.
[4]
Paul DuBois,et al.
MySQL Reference Manual
,
2002
.
[5]
W. B. Cavnar,et al.
N-gram-based text categorization
,
1994
.
[6]
Andrew J. Calder,et al.
PII: S0042-6989(01)00002-5
,
2001
.