.png){kind=icon}
Return
A two-step neural-network based algorithm for fast image super-resolution
.png){kind=icon}
PRE
AI
DOI：10.1016/j.imavis.2006.12.016.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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. (C) 2007 Elsevier B.V. All rights reserved.
Keywords:
super-resolution
multi-layer perceptron
probabilistic neural network
sequence processing
image restoration
Journal
IF:
4.2
Papers:
4.1K
Citations:
6.7K
Organization
No organization information available
Cited Papers
ShareSaveSuperresolution video reconstruction with arbitrary sampling lattices and nonzero aperture time
PREAI
ShareSaveShareSaveShareSave
An overview of power topologies for micro-hydro turbines.png)
2012 3rd IEEE International Symposium on Power Electronics for Distributed Generation Systems (PEDG)
2012 3rd IEEE International Symposium on Power Electronics for Distributed Generation Systems (PEDG)IF0
PREAI
ShareSaveShareSave
View more