Image Demosaicking via Chrominance Images with Parallel Convolutional Neural Networks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Many conventional demosaicking methods are based on hand-crafted filters. However, the filters yield false colors in salient regions like edges and textures. For acquisition of high quality images, we focus on neural networks. Neural networks lead to high accuracy in many fields. However, there are few methods in demosaicking field. For adaptation to demosaicking, we consider not only network's architecture but also the input. In this research, we utilize a Bayer image as input of our networks. However, different filter is needed in estimation at different color pixels, for example, missing red value at green pixel and that at blue pixel. Therefore, we prepare four networks with downsampling operators classified by color patterns in Bayer images. This downsampling operator not only identifies the color pattern but also reduces the calculation cost in each network due to reduction of the size of feature maps. Besides, preparation of multi-networks instead of a deep single-network is suitable for today's parallel computing. Moreover, we utilize not missing color images but chrominance images as output. Compared to results with missing color images as output, the results with chrominance images obtains higher accuracy. Experimental results show our CNN-based approach produces high quality restored images.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1702-1706
Number of pages5
ISBN (Electronic)9781479981311
DOIs
Publication statusPublished - 2019 May 1
Event44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
Duration: 2019 May 122019 May 17

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2019-May
ISSN (Print)1520-6149

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
CountryUnited Kingdom
CityBrighton
Period19/5/1219/5/17

Fingerprint

Color
Neural networks
Pixels
Image quality
Parallel processing systems
Network architecture
Textures
Costs

Keywords

  • Convolutional Neural Network
  • Demosaicking
  • Multi-network
  • Parallel Computing

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Yamaguchi, T., & Ikehara, M. (2019). Image Demosaicking via Chrominance Images with Parallel Convolutional Neural Networks. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings (pp. 1702-1706). [8682874] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2019.8682874

Image Demosaicking via Chrominance Images with Parallel Convolutional Neural Networks. / Yamaguchi, Takuro; Ikehara, Masaaki.

2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1702-1706 8682874 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yamaguchi, T & Ikehara, M 2019, Image Demosaicking via Chrominance Images with Parallel Convolutional Neural Networks. in 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings., 8682874, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., pp. 1702-1706, 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019, Brighton, United Kingdom, 19/5/12. https://doi.org/10.1109/ICASSP.2019.8682874
Yamaguchi T, Ikehara M. Image Demosaicking via Chrominance Images with Parallel Convolutional Neural Networks. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1702-1706. 8682874. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2019.8682874
Yamaguchi, Takuro ; Ikehara, Masaaki. / Image Demosaicking via Chrominance Images with Parallel Convolutional Neural Networks. 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1702-1706 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).
@inproceedings{10c04fbca11e43e3a9d7eb19c4c2eb79,
title = "Image Demosaicking via Chrominance Images with Parallel Convolutional Neural Networks",
abstract = "Many conventional demosaicking methods are based on hand-crafted filters. However, the filters yield false colors in salient regions like edges and textures. For acquisition of high quality images, we focus on neural networks. Neural networks lead to high accuracy in many fields. However, there are few methods in demosaicking field. For adaptation to demosaicking, we consider not only network's architecture but also the input. In this research, we utilize a Bayer image as input of our networks. However, different filter is needed in estimation at different color pixels, for example, missing red value at green pixel and that at blue pixel. Therefore, we prepare four networks with downsampling operators classified by color patterns in Bayer images. This downsampling operator not only identifies the color pattern but also reduces the calculation cost in each network due to reduction of the size of feature maps. Besides, preparation of multi-networks instead of a deep single-network is suitable for today's parallel computing. Moreover, we utilize not missing color images but chrominance images as output. Compared to results with missing color images as output, the results with chrominance images obtains higher accuracy. Experimental results show our CNN-based approach produces high quality restored images.",
keywords = "Convolutional Neural Network, Demosaicking, Multi-network, Parallel Computing",
author = "Takuro Yamaguchi and Masaaki Ikehara",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/ICASSP.2019.8682874",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1702--1706",
booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",

}

TY - GEN

T1 - Image Demosaicking via Chrominance Images with Parallel Convolutional Neural Networks

AU - Yamaguchi, Takuro

AU - Ikehara, Masaaki

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Many conventional demosaicking methods are based on hand-crafted filters. However, the filters yield false colors in salient regions like edges and textures. For acquisition of high quality images, we focus on neural networks. Neural networks lead to high accuracy in many fields. However, there are few methods in demosaicking field. For adaptation to demosaicking, we consider not only network's architecture but also the input. In this research, we utilize a Bayer image as input of our networks. However, different filter is needed in estimation at different color pixels, for example, missing red value at green pixel and that at blue pixel. Therefore, we prepare four networks with downsampling operators classified by color patterns in Bayer images. This downsampling operator not only identifies the color pattern but also reduces the calculation cost in each network due to reduction of the size of feature maps. Besides, preparation of multi-networks instead of a deep single-network is suitable for today's parallel computing. Moreover, we utilize not missing color images but chrominance images as output. Compared to results with missing color images as output, the results with chrominance images obtains higher accuracy. Experimental results show our CNN-based approach produces high quality restored images.

AB - Many conventional demosaicking methods are based on hand-crafted filters. However, the filters yield false colors in salient regions like edges and textures. For acquisition of high quality images, we focus on neural networks. Neural networks lead to high accuracy in many fields. However, there are few methods in demosaicking field. For adaptation to demosaicking, we consider not only network's architecture but also the input. In this research, we utilize a Bayer image as input of our networks. However, different filter is needed in estimation at different color pixels, for example, missing red value at green pixel and that at blue pixel. Therefore, we prepare four networks with downsampling operators classified by color patterns in Bayer images. This downsampling operator not only identifies the color pattern but also reduces the calculation cost in each network due to reduction of the size of feature maps. Besides, preparation of multi-networks instead of a deep single-network is suitable for today's parallel computing. Moreover, we utilize not missing color images but chrominance images as output. Compared to results with missing color images as output, the results with chrominance images obtains higher accuracy. Experimental results show our CNN-based approach produces high quality restored images.

KW - Convolutional Neural Network

KW - Demosaicking

KW - Multi-network

KW - Parallel Computing

UR - http://www.scopus.com/inward/record.url?scp=85069003637&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069003637&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2019.8682874

DO - 10.1109/ICASSP.2019.8682874

M3 - Conference contribution

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 1702

EP - 1706

BT - 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -