Spline-Based Dense Medial Descriptors for Image Simplification Using Saliency Maps

Jieying Wang*, Leonardo de Melo, Alexandre X. Falcao, Jiri Kosinka, Alexandru Telea

*Bijbehorende auteur voor dit werk

OnderzoeksoutputAcademicpeer review


Medial descriptors have attracted increasing interest in image representation, simplification, and compression. Recently, such descriptors have been separately used to (a) increase the local quality of representing salient features in an image and (b) globally compress an entire image via a B-spline encoding. To date, the two desiderates, (a) high local quality and (b) high overall compression of images, have not been addressed by a single medial method. We achieve this integration by presenting Spatial Saliency Spline Dense Medial Descriptors (3S-DMD) for saliency-aware image simplification-and-compression. Our method significantly improves the trade-off between compression and image quality of earlier medial-based methods while keeping perceptually salient features. We also demonstrate the added-value of user-designed, as compared to automatically-computed, saliency maps. We show that our method achieves both higher compression and better quality than JPEG for a broad range of images and, for specific image types, yields higher compression and similar quality than JPEG 2000.
Originele taal-2English
TitelComputer Vision, Imaging and Computer Graphics Theory and Applications
Subtitel16th International Joint Conference, VISIGRAPP 2021, Virtual Event, February 8–10, 2021, Revised Selected Papers
RedacteurenA. Augusto de Sousa, Vlastimil Havran, Alexis Paljic, Tabitha Peck, Christophe Hurter, Helen Purchase, Giovanni Maria Farinella, Petia Radeva, Kadi Bouatouch
Aantal pagina's24
ISBN van elektronische versie978-3-031-25477-2
ISBN van geprinte versie978-3-031-25476-5
StatusPublished - 2-feb.-2023
Evenement16th International Conference on Computer Graphics Theory and Applications (VISIGRAPP 2021) -
Duur: 8-feb.-202110-feb.-2021

Publicatie series

NaamCommunications in Computer and Information Science (CCIS)
ISSN van geprinte versie1865-0929
ISSN van elektronische versie1865-0937


Conference16th International Conference on Computer Graphics Theory and Applications (VISIGRAPP 2021)

Citeer dit