The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
A codificação de descrição múltipla (MD) é uma estrutura atraente para transmissão robusta de informações em redes não priorizadas e imprevisíveis. Neste artigo, um novo esquema de codificação de imagens MD é proposto baseado em redes neurais convolucionais (CNNs), que visa melhorar a qualidade reconstruída de decodificadores laterais e centrais. Para tanto, inicialmente, uma determinada imagem é codificada em duas descrições independentes por subamostragem. Tal projeto pode tornar o método proposto compatível com os padrões de codificação de imagem existentes. No decodificador, a fim de obter reconstrução de imagem lateral e central de alta qualidade, três CNNs, incluindo duas sub-redes de decodificadores laterais e uma sub-rede de decodificador central, são adotadas em uma estrutura de reconstrução ponta a ponta. Os resultados experimentais mostram a melhoria alcançada pelo esquema proposto em termos de valores de pico da relação sinal-ruído e qualidade subjetiva. O método proposto demonstra melhor desempenho de distorção central e lateral da taxa.
Ting ZHANG
Beijing Jiaotong University
Huihui BAI
Beijing Jiaotong University
Mengmeng ZHANG
North China University of Technology
Yao ZHAO
Beijing Jiaotong University
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.
Copiar
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
Copiar
@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},}
Copiar
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 -