Number of the records: 1
Edge preserving model-based image restoration
- 1.
SYSNO ASEP 0410286 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Edge preserving model-based image restoration Author(s) Haindl, Michal (UTIA-B) RID, ORCID Issue data Praha: Czech Pattern Recognition Society, 2000 ISBN 80-238-5215-9 Source Title Proceedings of the Czech Pattern Recognition Workshop 2000 / Svoboda T. Pages s. 49-54 Number of pages 6 s. Action Czech Pattern Recognition Workshop 2000 Event date 02.02.2000-04.02.2000 VEvent location Peršlák Country CZ - Czech Republic Language eng - English Country CZ - Czech Republic Subject RIV BD - Theory of Information R&D Projects GA102/00/0030 GA ČR - Czech Science Foundation (CSF) GA106/00/1715 GA ČR - Czech Science Foundation (CSF) CEZ 1075907 Annotation This paper presents a derivation of a fast recursive filter for image restoration if degradation obeys a linear degradation model with the unknown possibly non-homogeneous point-spread function. Pixels in the vicinity of steep discontinuities are left unrestored tominimize restoration blurring effect.The degraded image is assumed to follow a causal simultaneous regressive model and the point-spread function is estimated using the local least-square estimate. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201.
Number of the records: 1