A two-step neural-network based algorithm for fast image super-resolution

We propose a novel, learning-based algorithm for image super-resolution. First, an optimal distance-based weighted interpolation of the image sequence is performed using a new neural architecture, hybrid of a multi-layer perceptron and a probabilistic neural network, trained on synthetic image data....

Full description

Saved in:
Bibliographic Details
Published inImage and vision computing Vol. 25; no. 9; pp. 1449 - 1473
Main Authors Miravet, Carlos, Rodrı´guez, Francisco B.
Format Journal Article
LanguageEnglish
Published Elsevier B.V 01.09.2007
Subjects
Image restoration
Multi-layer perceptron
Probabilistic neural network
Sequence processing
Super-resolution
Super-resolution
Probabilistic neural network
Sequence processing
Image restoration
Multi-layer perceptron
Online AccessGet full text
ISSN0262-8856
1872-8138
DOI10.1016/j.imavis.2006.12.016

Cover

More Information
Summary:We propose a novel, learning-based algorithm for image super-resolution. First, an optimal distance-based weighted interpolation of the image sequence is performed using a new neural architecture, hybrid of a multi-layer perceptron and a probabilistic neural network, trained on synthetic image data. Secondly, a linear filter is applied with coefficients learned to restore residual interpolation artifacts in addition to low-resolution blurring, providing noticeable improvements over lens-detector Wiener restorations. Our method has been evaluated on real visible and IR sequences with widely different contents, providing significantly better results that a two-step method with high computational requirements. Results were similar or better than those of a maximum-a-posteriori estimator, with a reduction in processing time by a factor of almost 300. This paves the way to high-quality, quasi-real time applications of super-resolution techniques.
ISSN:0262-8856
1872-8138
DOI:10.1016/j.imavis.2006.12.016