1 October 2003 New image super-resolution scheme based on residual error restoration by neural networks
Author Affiliations +
Abstract
The scheme proposed combines an existing image interpolation algorithm with an artificial neural network (ANN) used to model the residual errors between the interpolated image and the respective original image. Mathematical analysis shows that the performance of the proposed method is superior to that of known single-frame interpolation algorithms. The image restoration results using the presented scheme indicate that the restored images are very similar to the real high-resolution images. We also illustrate that the performance of any single-frame interpolation algorithm can be enhanced by combining the interpolation algorithm into our scheme. Experimental results show the proposed method on generalization and computation complexity is superior to other neural network schemes.
© (2003) Society of Photo-Optical Instrumentation Engineers (SPIE)
Fengzhi Pan, Fengzhi Pan, Liming Zhang, Liming Zhang, } "New image super-resolution scheme based on residual error restoration by neural networks," Optical Engineering 42(10), (1 October 2003). https://doi.org/10.1117/1.1604397 . Submission:
JOURNAL ARTICLE
9 PAGES


SHARE
RELATED CONTENT

Image super-resolution via multistage sparse coding
Proceedings of SPIE (August 28 2016)
Super-Resolution And Neural Computing
Proceedings of SPIE (April 19 1988)
Neural network-based multiscale image restoration approach
Proceedings of SPIE (February 26 2007)

Back to Top