Blocking Artifact Reduction in Block-Coded Image Using Block Classification and Feedforward Neural Network

Kee-Koo KWON; Suk-Hwan LEE; Seong-Geun KWON; Kyung-Nam PARK; Kuhn-Il LEE

Blocking Artifact Reduction in Block-Coded Image Using Block Classification and Feedforward Neural Network

Kee-Koo KWON, Suk-Hwan LEE, Seong-Geun KWON, Kyung-Nam PARK, Kuhn-Il LEE

Full Text Views

0

Cite this

Summary :

A new blocking artifact reduction algorithm is proposed that uses block classification and feedforward neural network filters in the spatial domain. At first, the existence of blocking artifact is determined using statistical characteristics of neighborhood block, which is then used to classify the block boundaries into one of four classes. Thereafter, adaptive inter-block filtering is only performed in two classes of block boundaries that include blocking artifact. That is, in smooth regions with blocking artifact, a two-layer feedforward neural network filters trained by an error back-propagation algorithm is used, while in complex regions with blocking artifact, a linear interpolation method is used to preserve the image details. Experimental results show that the proposed algorithm produces better results than the conventional algorithms.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E85-A No.7 pp.1742-1745

Publication Date: 2002/07/01

Publicized

Online ISSN

DOI

Type of Manuscript: LETTER

Category: Digital Signal Processing

Cite this

Copy

Kee-Koo KWON, Suk-Hwan LEE, Seong-Geun KWON, Kyung-Nam PARK, Kuhn-Il LEE, "Blocking Artifact Reduction in Block-Coded Image Using Block Classification and Feedforward Neural Network" in IEICE TRANSACTIONS on Fundamentals, vol. E85-A, no. 7, pp. 1742-1745, July 2002, doi: .
Abstract: A new blocking artifact reduction algorithm is proposed that uses block classification and feedforward neural network filters in the spatial domain. At first, the existence of blocking artifact is determined using statistical characteristics of neighborhood block, which is then used to classify the block boundaries into one of four classes. Thereafter, adaptive inter-block filtering is only performed in two classes of block boundaries that include blocking artifact. That is, in smooth regions with blocking artifact, a two-layer feedforward neural network filters trained by an error back-propagation algorithm is used, while in complex regions with blocking artifact, a linear interpolation method is used to preserve the image details. Experimental results show that the proposed algorithm produces better results than the conventional algorithms.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e85-a_7_1742/_p

Copy

@ARTICLE{e85-a_7_1742,
author={Kee-Koo KWON, Suk-Hwan LEE, Seong-Geun KWON, Kyung-Nam PARK, Kuhn-Il LEE, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Blocking Artifact Reduction in Block-Coded Image Using Block Classification and Feedforward Neural Network},
year={2002},
volume={E85-A},
number={7},
pages={1742-1745},
abstract={A new blocking artifact reduction algorithm is proposed that uses block classification and feedforward neural network filters in the spatial domain. At first, the existence of blocking artifact is determined using statistical characteristics of neighborhood block, which is then used to classify the block boundaries into one of four classes. Thereafter, adaptive inter-block filtering is only performed in two classes of block boundaries that include blocking artifact. That is, in smooth regions with blocking artifact, a two-layer feedforward neural network filters trained by an error back-propagation algorithm is used, while in complex regions with blocking artifact, a linear interpolation method is used to preserve the image details. Experimental results show that the proposed algorithm produces better results than the conventional algorithms.},
keywords={},
doi={},
ISSN={},
month={July},}

Copy

TY - JOUR
TI - Blocking Artifact Reduction in Block-Coded Image Using Block Classification and Feedforward Neural Network
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1742
EP - 1745
AU - Kee-Koo KWON
AU - Suk-Hwan LEE
AU - Seong-Geun KWON
AU - Kyung-Nam PARK
AU - Kuhn-Il LEE
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E85-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 2002
AB - A new blocking artifact reduction algorithm is proposed that uses block classification and feedforward neural network filters in the spatial domain. At first, the existence of blocking artifact is determined using statistical characteristics of neighborhood block, which is then used to classify the block boundaries into one of four classes. Thereafter, adaptive inter-block filtering is only performed in two classes of block boundaries that include blocking artifact. That is, in smooth regions with blocking artifact, a two-layer feedforward neural network filters trained by an error back-propagation algorithm is used, while in complex regions with blocking artifact, a linear interpolation method is used to preserve the image details. Experimental results show that the proposed algorithm produces better results than the conventional algorithms.
ER -