*Project Title*
Relevance Feedback based on Genetic Programming

*Project Description* 

Relevance feedback is a commonly accepted method to improve interactive retrieval effectiveness. Basically, it 
is composed of three steps: (a) an initial search is made by the system with a user-supplied query pattern, returning 
a small number of images; (b) the user then indicates which of the retrieved images are useful (relevant); (c) finally, 
the system automatically reformulates the original query based upon user relevance judgments. This process can continue 
to iterate until the user is satisfied.

Genetic programming (GP) is an artificial intelligence problem-solving technique based on the principles of biological 
inheritance and evolution. Each potential solution is called an individual (i.e., a chromosome) in a population. GP works 
by iteratively applying genetic transformations, such as crossover and mutation, to a population of individuals to create 
more diverse and better performing individuals in subsequent generations. A fitness function is available to assign the 
fitness value for each individual.

This project aims to develop a relevance feedback approach based on the GP technique.

*Language/technology skills*
C, Java

*Number of People*
1-2

*Project Resources*

1. R. da S. Torres, A. X. Falcão, M. A. Goncalves, B. Zhang, W. Fan, E. A. Fox, and P. Calado, 
A New Framework to Combine Descriptors for Content-based Image Retrieval, CIKM'05, Fourteenth Conference on 
Information and Knowledge Management, 335-336, Bremen, Germany, 2005.
http://www.ic.unicamp.br/~rtorres/torres05cikm.pdf