Number of the records: 1
Non-separable rotation moment invariants
- 1.
SYSNO ASEP 0555291 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Non-separable rotation moment invariants Author(s) Bedratyuk, L. (UA)
Flusser, Jan (UTIA-B) RID, ORCID
Suk, Tomáš (UTIA-B) RID, ORCID
Kostková, Jitka (UTIA-B) ORCID
Kautský, J. (AU)Number of authors 5 Article number 108607 Source Title Pattern Recognition. - : Elsevier - ISSN 0031-3203
Roč. 127, č. 1 (2022)Number of pages 12 s. Publication form Print - P Language eng - English Country GB - United Kingdom Keywords Image recognition ; Rotation invariants ; Non-separable moments ; Appell polynomials ; Bi-orthogonality ; Recurrent relation Subject RIV JD - Computer Applications, Robotics OECD category Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8) R&D Projects GA21-03921S GA ČR - Czech Science Foundation (CSF) Method of publishing Limited access Institutional support UTIA-B - RVO:67985556 UT WOS 000784335600003 EID SCOPUS 85125526639 DOI https://doi.org/10.1016/j.patcog.2022.108607 Annotation In this paper, we introduce new rotation moment invariants, which are composed of non-separable Appell moments. We prove that Appell polynomials behave under rotation as monomials, which enables easy construction of the invariants. We show by extensive tests that non-separable moments may outperform the separable ones in terms of recognition power and robustness thanks to a better distribution of their zero curves over the image space. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2023 Electronic address https://www.sciencedirect.com/science/article/pii/S0031320322000887?via%3Dihub
Number of the records: 1