IEICE TRANSACTIONS on Fundamentals
Adaptive Postprocessing Algorithm in Block-Coded Images Using Block Classification and MLP
Summary :
A novel postprocessing algorithm for reducing the blocking artifacts in block-based coded images is proposed using block classification and adaptive multi-layer perceptron (MLP). This algorithm is exploited the nonlinearity property of the neural network learning algorithm to reduce the blocking artifacts more accurately. In this algorithm, each block is classified into four classes; smooth, horizontal edge, vertical edge, and complex blocks, based on the characteristic of their discrete cosine transform (DCT) coefficients. Thereafter, according to the class information of the neighborhood block, adaptive neural network filters (NNF) are then applied to the horizontal and vertical block boundaries. That is, for each class a different two-layer NNF is used to remove the blocking artifacts. Experimental results show that the proposed algorithm produced better results than conventional algorithms both subjectively and objectively.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E86-A No.4 pp.961-967
- Publication Date
- 2003/04/01
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- LETTER
- Category
- Image
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Kee-Koo KWON, Byung-Ju KIM, Suk-Hwan LEE, Seong-Geun KWON, Kuhn-Il LEE, "Adaptive Postprocessing Algorithm in Block-Coded Images Using Block Classification and MLP" in IEICE TRANSACTIONS on Fundamentals,
vol. E86-A, no. 4, pp. 961-967, April 2003, doi: .
Abstract: A novel postprocessing algorithm for reducing the blocking artifacts in block-based coded images is proposed using block classification and adaptive multi-layer perceptron (MLP). This algorithm is exploited the nonlinearity property of the neural network learning algorithm to reduce the blocking artifacts more accurately. In this algorithm, each block is classified into four classes; smooth, horizontal edge, vertical edge, and complex blocks, based on the characteristic of their discrete cosine transform (DCT) coefficients. Thereafter, according to the class information of the neighborhood block, adaptive neural network filters (NNF) are then applied to the horizontal and vertical block boundaries. That is, for each class a different two-layer NNF is used to remove the blocking artifacts. Experimental results show that the proposed algorithm produced better results than conventional algorithms both subjectively and objectively.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e86-a_4_961/_p
Copy
@ARTICLE{e86-a_4_961,
author={Kee-Koo KWON, Byung-Ju KIM, Suk-Hwan LEE, Seong-Geun KWON, Kuhn-Il LEE, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Adaptive Postprocessing Algorithm in Block-Coded Images Using Block Classification and MLP},
year={2003},
volume={E86-A},
number={4},
pages={961-967},
abstract={A novel postprocessing algorithm for reducing the blocking artifacts in block-based coded images is proposed using block classification and adaptive multi-layer perceptron (MLP). This algorithm is exploited the nonlinearity property of the neural network learning algorithm to reduce the blocking artifacts more accurately. In this algorithm, each block is classified into four classes; smooth, horizontal edge, vertical edge, and complex blocks, based on the characteristic of their discrete cosine transform (DCT) coefficients. Thereafter, according to the class information of the neighborhood block, adaptive neural network filters (NNF) are then applied to the horizontal and vertical block boundaries. That is, for each class a different two-layer NNF is used to remove the blocking artifacts. Experimental results show that the proposed algorithm produced better results than conventional algorithms both subjectively and objectively.},
keywords={},
doi={},
ISSN={},
month={April},}
Copy
TY - JOUR
TI - Adaptive Postprocessing Algorithm in Block-Coded Images Using Block Classification and MLP
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 961
EP - 967
AU - Kee-Koo KWON
AU - Byung-Ju KIM
AU - Suk-Hwan LEE
AU - Seong-Geun KWON
AU - Kuhn-Il LEE
PY - 2003
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E86-A
IS - 4
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - April 2003
AB - A novel postprocessing algorithm for reducing the blocking artifacts in block-based coded images is proposed using block classification and adaptive multi-layer perceptron (MLP). This algorithm is exploited the nonlinearity property of the neural network learning algorithm to reduce the blocking artifacts more accurately. In this algorithm, each block is classified into four classes; smooth, horizontal edge, vertical edge, and complex blocks, based on the characteristic of their discrete cosine transform (DCT) coefficients. Thereafter, according to the class information of the neighborhood block, adaptive neural network filters (NNF) are then applied to the horizontal and vertical block boundaries. That is, for each class a different two-layer NNF is used to remove the blocking artifacts. Experimental results show that the proposed algorithm produced better results than conventional algorithms both subjectively and objectively.
ER -
English
