Postprocessing for image coding applications using neural network visual model
Postprocessing for image coding applications using neural network visual model
We present a neural network visual model (NNVM), which extracts multi-scale edge features from the decompressed image and uses these visual features as input to estimate and compensate the coding distortions. Our approach is a generic postprocessing technique and can be applied to all the main coding methods. Experimental results involving post-processing four coding systems show that the NNVM significantly improves the quality of reconstructed images, both in terms of the objective peak signal to noise ratio (PSNR) and subjective visual assessment.
557-566
He, Z.
c7048a1b-3632-409a-96f5-e82b998d4754
Chen, S.
9310a111-f79a-48b8-98c7-383ca93cbb80
Luk, B. L.
93cd9097-1776-4671-b6bb-71febac67594
Istepanian, R. H.
b71b8b46-cb69-4fcd-8253-d2e7a93079ea
1998
He, Z.
c7048a1b-3632-409a-96f5-e82b998d4754
Chen, S.
9310a111-f79a-48b8-98c7-383ca93cbb80
Luk, B. L.
93cd9097-1776-4671-b6bb-71febac67594
Istepanian, R. H.
b71b8b46-cb69-4fcd-8253-d2e7a93079ea
He, Z., Chen, S., Luk, B. L. and Istepanian, R. H.
(1998)
Postprocessing for image coding applications using neural network visual model.
Proceedings of 8th IEEE Workshop on Neural Networks for Signal Processing.
.
Record type:
Conference or Workshop Item
(Other)
Abstract
We present a neural network visual model (NNVM), which extracts multi-scale edge features from the decompressed image and uses these visual features as input to estimate and compensate the coding distortions. Our approach is a generic postprocessing technique and can be applied to all the main coding methods. Experimental results involving post-processing four coding systems show that the NNVM significantly improves the quality of reconstructed images, both in terms of the objective peak signal to noise ratio (PSNR) and subjective visual assessment.
Text
c-1998-wnnsp
- Accepted Manuscript
Restricted to Repository staff only
Request a copy
More information
Published date: 1998
Additional Information:
8th IEEE Workshop on Neural Networks for Signal Processing (Cambridge, UK), Aug. 31-Sept. 3, 1998 Organisation: IEEE Signal Processing Society
Venue - Dates:
Proceedings of 8th IEEE Workshop on Neural Networks for Signal Processing, 1998-01-01
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 251035
URI: http://eprints.soton.ac.uk/id/eprint/251035
PURE UUID: 4d215e2b-640c-424a-852a-b0cda85d3c23
Catalogue record
Date deposited: 31 Mar 2000
Last modified: 14 Mar 2024 05:07
Export record
Contributors
Author:
Z. He
Author:
S. Chen
Author:
B. L. Luk
Author:
R. H. Istepanian
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics