An Automatic Graphic Pattern Generation Algorithm and Its Application to the Multipurpose Camouflage Pattern Design.

Abstract

Graphic patterns are usually drawn manually by graphic designers. Although many methods have been developed to computerize the creation process of graphic patterns, most of them solely provide some facilitating tools for the designers and could not propose an automatic procedure. This article proposes a fully automatic graphic pattern generation (AGPG) model that performs the entire pattern generation process without any human interference. We then customize the proposed model for camouflage pattern design. Most of the existing camouflage pattern creation methods consider only one or a few background images. Since the objects move and their backgrounds may vary significantly, it is essential to generate multipurpose camouflage patterns with appropriate performance in various backgrounds. The previously proposed methods are also heavily dependent on the existing patterns to produce new ones and could not create novel structures in their generated patterns. Our model is equipped with a novel creative drawing engine that can create a wide variety of new graphical structures without using any existing pattern. The drawing module in our model is controlled by several parameters tuned for the desired task employing an evolutionary strategy-based algorithm. The proposed method has no limits for the number of background images and creates the camouflage patterns appropriate for any number of provided images. The experimental results show that the AGPG method can create novel multipurpose camouflage patterns automatically with high concealment capabilities.