Cartesian Genetic Programming for Image Processing Tasks

摘要

This paper presents experimental results on image analysis for a particular form of Genetic Programming called Cartesian Genetic Programming (CGP) in which programs use the structure of a graph represented as a linear sequence of integers. The efficency of this approach is investigated for the problem of Object Localization in a given image. This task is usually carried out by applying a series of well known image processing operators and commonly relies on the skills and expertise of the researchers. In this work, we present results from a number of runs on actual camera images, in which a set of fairly simple primitives were investigated.