Evolutionary algorithms and cellular automata towards image reconstruction
Franciszek Seredyński, Jarosław Skaruz · 2012
In the paper we present a new approach based on evolutionary algorithms and cellular automata to the image reconstruction problem. Two-dimensional, nine state cellular automata with Moore neighbourhood perform reconstruction of an image presenting a human face. Large space of automata rules is searched through efficiently by a genetic algotihm (GA), which finds a good quality rule. Experimental results present that obtained rule allows to reconstruct an image with even 70% damaged pixels. Moreover, we also show that a rule found in the genetic evolution process can be applied to the reconstruction of images of the same class but not presented during the evolutionary process.