Abstract
This paper proposes a method to extract multiple target image areas similar to a given template image. The proposed method based on a genetic algorithm (GA) with immune system searches efficiently multiple local solutions by using suppressor T cell's mechanism and local search, which are major improvements in it, whereas genetic algorithms search only one global solution. Experimental results show that the suppressive mechanism keeps efficiently diversity of individuals and extracts multiple target image areas in the condition of free locations, inclinations and scales at a high probability.
