Genetic programming with user-driven selection: experiments on the evolution of algorithms for image enhancement

In this paper we present an approach to the interactive development of programs for image enhancement with Genetic Programming (GP) based on pseudocolour transformations. In our approach the user drives GP by deciding which individual should be the winner in tournament selection. The presence of the user does not only allow running GP without a fitness function but it also transforms GP into a very efficient search procedure capable of producing effective solutions to real-life problems in only hundreds of evaluations. In the paper we also propose a strategy to further reduce user interaction: we record the choices made by the user in interactive runs and we later use them to build a model which can replace him/her in longer runs. Experimental results with interactive GP and with our user-modelling strategy are also reported.