A technique for image ocmpresswion using binary Evolutinary Cellular Automata (ECA) is presented.the mehtod is apleid to balck and white fingeprint images.these ECA are evolved with a Genetic Algorihtm (GA) guided by a fitness function consisting of a simuilarity measrue betwen the configuraitons of the ECA and the target images.When a suitable approxmiation of the target image is achieved it can be codified with the rule number s and logicla oeprations linling the ECA.In this way the original image undergoes a ocmresisn rpocess since it will be represented by a onisderably smaller bit amount.Typically compression rates of the roder of 100:1 are ahcieved in the expeirmentsA codified or comrpessed image cna be regenerated recorvering a very good aproaximation with a typcoial similarity of 96
展开▼
