Video
BibTex
@inproceedings{Azami:2020:10.20380/GI2020.08,
author = {Azami, Rosa and Mould, David},
title = {Image Abstraction through Overlapping Region Growth},
booktitle = {Proceedings of Graphics Interface 2020},
series = {GI 2020},
year = {2020},
isbn = {978-0-9947868-5-2},
location = {University of Toronto},
pages = {66 -- 73},
numpages = {8},
doi = {10.20380/GI2020.08},
publisher = {Canadian Human-Computer Communications Society / Société canadienne du dialogue humain-machine},
}
Abstract
We propose a region-based abstraction of a photograph, where the image plane is covered by overlapping irregularly shaped regions that approximate the image content. We segment regions using a novel region growth algorithm intended to produce highly irregular regions that still respect image edges, different from conventional segmentation methods that encourage compact regions.