Camouflage pattern generator

The thesis focuses on the visual camouflage generation problem characterised by cre- ating a colored pattern that, when printed on an object, has concealment capabilities. A good concealment can save lives of military personnel and protect important facilities. We approach the problem by devising a genetic algorithm with problem-specific ge- netic operators. The complexity of the algorihm lies in innovative utilization of the saliency predicting tool in the fitness operator. The construction of the operator con- nects human vision, image processing, deep learning and evolutionary computation. Along the computaionally costly fitness operator we suggest fast and simple concep- tually related trial operator we use for exploring characterics of the costly one. Then, we use this knowledge for generation of a camouflage pattern for forest environment.