Home » Proceedings » GI 2021 » Artistic Recoloring of Image Oversegmentations

Artistic Recoloring of Image Oversegmentations

Rosa Azami (Carleton University), David Mould (Carleton University)


Proceedings of Graphics Interface 2021:
Virtual Event,
28 – 29 May 2021, pp. 68 – 76

Abstract

We propose a method to assign vivid colors to regions of an oversegmented image. We restrict the output colors to those found in an input palette, and seek to preserve the recognizability of structure in the image. Our strategy is to match the color distances between the colors of adjacent regions with the color differences between the assigned palette colors; thus, assigned colors may be very far from the original colors, but both large local differences (edges) and small ones (uniform areas) are maintained. We use the widest path algorithm on a graph-based structure to obtain a spanning tree over the set of regions, then traverse the tree to assign colors in a greedy fashion. Our method produces vivid recolorings of region-based abstraction using arbitrary palettes. We demonstrate a set of stylizations that can be generated by our algorithm.

Michael A. J. Sweeney Award

Alain Fournier Awards

Bill Buxton Awards

CHCCS Service Awards

CHCCS Achievement Awards

Canadian Digital Media Pioneer Awards

Connect with us

Prix Pionnier des médias numériques

Early Career Researcher Award

primary_navigation_menu