A generic framework for the structured abstraction of images

Abstract

Structural properties are important clues for non-photorealistic representations of digital images. Therefore, image analysis tools have been intensively used either to produce stroke-based renderings or to yield abstractions of images. In this work, we propose to use a hierarchical and geometrical image representation, called a topographic map, made of shapes organized in a tree structure. There are two main advantages of this analysis tool. Firstly, it is able to deal with all scales, so that every shape of the input image is represented. Secondly, it accounts for the inclusion properties within the image. By iteratively performing simple local operations on the shapes (removal, rotation, scaling, replacement...), we are able to generate abstract renderings of digital photographs ranging from geometrical abstraction and painting-like effects to style transfer, using the same framework. In particular, results show that it is possible to create abstract images evoking Malevitchs Suprematist school, while remaining grounded in the structure of digital images, by replacing all the shapes in the tree by simple geometric shapes.