A hybrid MLP-PNN architecture for fast image superresolution

Simple item page
dc.creatorMiravet, Carlos
dc.creatorRodriguez, Francisco B.
dc.date2005-03-22
dc.date.accessioned2026-07-07T03:22:45Z
dc.date.available2026-07-07T03:22:45Z
dc.descriptionImage superresolution methods process an input image sequence of a scene to obtain a still image with increased resolution. Classical approaches to this problem involve complex iterative minimization procedures, typically with high computational costs. In this paper is proposed a novel algorithm for super-resolution that enables a substantial decrease in computer load. First, a probabilistic neural network architecture is used to perform a scattered-point interpolation of the image sequence data. The network kernel function is optimally determined for this problem by a multi-layer perceptron trained on synthetic data. Network parameters dependence on sequence noise level is quantitatively analyzed. This super-sampled image is spatially filtered to correct finite pixel size effects, to yield the final high-resolution estimate. Results on a real outdoor sequence are presented, showing the quality of the proposed method.
dc.description8 pages with 4 figures. ICANN/ICONIP 2003
dc.identifierhttps://arxiv.org/abs/cs/0503053
dc.identifierhttp://arxiv.org/abs/cs/0503053
dc.identifierLect. Notes Comput. Sc. 2714 (2003) 401-408
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/32670
dc.subjectComputer Vision and Pattern Recognition
dc.subjectMultimedia
dc.subjectI.4.5; I.2.6; I.5.1
dc.titleA hybrid MLP-PNN architecture for fast image superresolution
dc.typetext

Files

Collections

arXiv