Texture Spectral Similarity Criteria Comparison

0573712 - ÚTIA 2024 RIV CZ eng C - Conference Paper (international conference)
Havlíček, Michal - Haindl, Michal
Texture Spectral Similarity Criteria Comparison.
WSCG 2023 Proceedings - 31. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision WSCG 2023. Plzeň: University of West Bohemia, 2023, s. 100-106. Computer Science Research Notes, CSRN 3301. ISBN 978-80-86943-32-9. ISSN 2464-4617. E-ISSN 2464-4625.
[International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision 2023, WSCG 2023, /31./. Plzen (CZ), 15.05.2023-19.05.2023]
R&D Projects: GA ČR(CZ) GA19-12340S
Institutional support: RVO:67985556
Keywords : Texture Comparison * Texture Modeling * Texture Retrieval * Texture Classification * Texture Acquisition
OECD category: Automation and control systems
Method of publishing: Limited access
http://library.utia.cas.cz/separaty/2023/RO/haindl-0573712.pdf

Criteria capable of texture spectral similarity evaluation are presented and compared. From the fifteen evaluated criteria, only four criteria guarantee zero or minimal spectral ranking errors. Such criteria can support texture modeling algorithms by comparing the modeled texture with corresponding synthetic simulations. Another possible application is the development of texture retrieval, classification, or texture acquisition system. These criteria thoroughly test monotonicity and mutual correlation on specifically designed extensive monotonously degrading experiments.
Permanent Link: https://hdl.handle.net/11104/0344423