Focus-and-Context Skeleton-based Image Simplification using Saliency Maps

Jieying Wang, Leonardo de Melo Joao, Alexandre Falcão, Jiří Kosinka, Alexandru Telea

2021

Abstract

Medial descriptors offer a promising way for representing, simplifying, manipulating, and compressing images. However, to date, these have been applied in a global manner that is oblivious to salient features. In this paper, we adapt medial descriptors to use the information provided by saliency maps to selectively simplify and encode an image while preserving its salient regions. This allows us to improve the trade-off between compression ratio and image quality as compared to the standard dense-skeleton method while keeping perceptually salient features, in a focus-and-context manner. We show how our method can be combined with JPEG to increase overall compression rates at the cost of a slightly lower image quality. We demonstrate our method on a benchmark composed of a broad set of images.

Paper Citation

in Harvard Style

Wang J., Joao L., Falcão A., Kosinka J. and Telea A. (2021). Focus-and-Context Skeleton-based Image Simplification using Saliency Maps. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 45-55. DOI: 10.5220/0010193400450055

in Bibtex Style

@conference{visapp21,
author={Jieying Wang and Leonardo de Melo Joao and Alexandre Falcão and Jiří Kosinka and Alexandru Telea},
title={Focus-and-Context Skeleton-based Image Simplification using Saliency Maps},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP},
year={2021},
pages={45-55},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010193400450055},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP
TI - Focus-and-Context Skeleton-based Image Simplification using Saliency Maps
SN - 978-989-758-488-6
AU - Wang J.
AU - Joao L.
AU - Falcão A.
AU - Kosinka J.
AU - Telea A.
PY - 2021
SP - 45
EP - 55
DO - 10.5220/0010193400450055
PB - SciTePress