Standard-Compliant Multiple Description Image Coding Based on Convolutional Neural Networks

Ting ZHANG; Huihui BAI; Mengmeng ZHANG; Yao ZHAO

doi:10.1587/transinf.2018EDL8028

Standard-Compliant Multiple Description Image Coding Based on Convolutional Neural Networks

Ting ZHANG, Huihui BAI, Mengmeng ZHANG, Yao ZHAO

Full Text Views

0

Cite this

Summary :

Multiple description (MD) coding is an attractive framework for robust information transmission over non-prioritized and unpredictable networks. In this paper, a novel MD image coding scheme is proposed based on convolutional neural networks (CNNs), which aims to improve the reconstructed quality of side and central decoders. For this purpose initially, a given image is encoded into two independent descriptions by sub-sampling. Such a design can make the proposed method compatible with the existing image coding standards. At the decoder, in order to achieve high-quality of side and central image reconstruction, three CNNs, including two side decoder sub-networks and one central decoder sub-network, are adopted into an end-to-end reconstruction framework. Experimental results show the improvement achieved by the proposed scheme in terms of both peak signal-to-noise ratio values and subjective quality. The proposed method demonstrates better rate central and side distortion performance.

Publication: IEICE TRANSACTIONS on Information Vol.E101-D No.10 pp.2543-2546

Publication Date: 2018/10/01

Publicized: 2018/07/19

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2018EDL8028

Type of Manuscript: LETTER

Category: Image Processing and Video Processing

Authors

Ting ZHANG
  Beijing Jiaotong University
Huihui BAI
  Beijing Jiaotong University
Mengmeng ZHANG
  North China University of Technology
Yao ZHAO
  Beijing Jiaotong University

Keyword

image coding, multiple description (MD) coding, convolutional neural network

Cite this

Copy

Ting ZHANG, Huihui BAI, Mengmeng ZHANG, Yao ZHAO, "Standard-Compliant Multiple Description Image Coding Based on Convolutional Neural Networks" in IEICE TRANSACTIONS on Information, vol. E101-D, no. 10, pp. 2543-2546, October 2018, doi: 10.1587/transinf.2018EDL8028.
Abstract: Multiple description (MD) coding is an attractive framework for robust information transmission over non-prioritized and unpredictable networks. In this paper, a novel MD image coding scheme is proposed based on convolutional neural networks (CNNs), which aims to improve the reconstructed quality of side and central decoders. For this purpose initially, a given image is encoded into two independent descriptions by sub-sampling. Such a design can make the proposed method compatible with the existing image coding standards. At the decoder, in order to achieve high-quality of side and central image reconstruction, three CNNs, including two side decoder sub-networks and one central decoder sub-network, are adopted into an end-to-end reconstruction framework. Experimental results show the improvement achieved by the proposed scheme in terms of both peak signal-to-noise ratio values and subjective quality. The proposed method demonstrates better rate central and side distortion performance.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDL8028/_p

Copy

@ARTICLE{e101-d_10_2543,
author={Ting ZHANG, Huihui BAI, Mengmeng ZHANG, Yao ZHAO, },
journal={IEICE TRANSACTIONS on Information},
title={Standard-Compliant Multiple Description Image Coding Based on Convolutional Neural Networks},
year={2018},
volume={E101-D},
number={10},
pages={2543-2546},
abstract={Multiple description (MD) coding is an attractive framework for robust information transmission over non-prioritized and unpredictable networks. In this paper, a novel MD image coding scheme is proposed based on convolutional neural networks (CNNs), which aims to improve the reconstructed quality of side and central decoders. For this purpose initially, a given image is encoded into two independent descriptions by sub-sampling. Such a design can make the proposed method compatible with the existing image coding standards. At the decoder, in order to achieve high-quality of side and central image reconstruction, three CNNs, including two side decoder sub-networks and one central decoder sub-network, are adopted into an end-to-end reconstruction framework. Experimental results show the improvement achieved by the proposed scheme in terms of both peak signal-to-noise ratio values and subjective quality. The proposed method demonstrates better rate central and side distortion performance.},
keywords={},
doi={10.1587/transinf.2018EDL8028},
ISSN={1745-1361},
month={October},}

Copy

TY - JOUR
TI - Standard-Compliant Multiple Description Image Coding Based on Convolutional Neural Networks
T2 - IEICE TRANSACTIONS on Information
SP - 2543
EP - 2546
AU - Ting ZHANG
AU - Huihui BAI
AU - Mengmeng ZHANG
AU - Yao ZHAO
PY - 2018
DO - 10.1587/transinf.2018EDL8028
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2018
AB - Multiple description (MD) coding is an attractive framework for robust information transmission over non-prioritized and unpredictable networks. In this paper, a novel MD image coding scheme is proposed based on convolutional neural networks (CNNs), which aims to improve the reconstructed quality of side and central decoders. For this purpose initially, a given image is encoded into two independent descriptions by sub-sampling. Such a design can make the proposed method compatible with the existing image coding standards. At the decoder, in order to achieve high-quality of side and central image reconstruction, three CNNs, including two side decoder sub-networks and one central decoder sub-network, are adopted into an end-to-end reconstruction framework. Experimental results show the improvement achieved by the proposed scheme in terms of both peak signal-to-noise ratio values and subjective quality. The proposed method demonstrates better rate central and side distortion performance.
ER -