Infrared Image Colorization Using a S-Shape Network

Ziyue Dong, Seiichiro Kamata, Toby P. Breckon

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

Abstract

This paper proposes a novel approach for colorizing near infrared (NIR) images using a S-shape network (SNet). The proposed approach is based on the usage of an encoder-decoder architecture followed with a secondary assistant network. The encoder-decoder consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. The assistant network is a shallow encoder-decoder to enhance the edge and improve the output, which can be trained end-to-end from a few image examples. The trained model does not require any user guidance or a reference image database. Furthermore, our architecture will preserve clear edges within NIR images. Our overall architecture is trained and evaluated on a real-world dataset containing a significant amount of road scene images. This dataset was captured by a NIR camera and a corresponding RGB camera to facilitate side-by-side comparison. In the experiments, we demonstrate that our SNet works well, and outperforms contemporary state-of-the-art approaches.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
PublisherIEEE Computer Society
Pages2242-2246
Number of pages5
ISBN (Electronic)9781479970612
DOIs
Publication statusPublished - 2018 Aug 29
Event25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece
Duration: 2018 Oct 72018 Oct 10

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference25th IEEE International Conference on Image Processing, ICIP 2018
CountryGreece
CityAthens
Period18/10/718/10/10

Fingerprint

Infrared radiation
Cameras
Experiments

Keywords

  • Colorization
  • Convolutional neural network
  • Infrared
  • S-shape network

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Dong, Z., Kamata, S., & Breckon, T. P. (2018). Infrared Image Colorization Using a S-Shape Network. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings (pp. 2242-2246). [8451230] (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP.2018.8451230

Infrared Image Colorization Using a S-Shape Network. / Dong, Ziyue; Kamata, Seiichiro; Breckon, Toby P.

2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society, 2018. p. 2242-2246 8451230 (Proceedings - International Conference on Image Processing, ICIP).

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

Dong, Z, Kamata, S & Breckon, TP 2018, Infrared Image Colorization Using a S-Shape Network. in 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings., 8451230, Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 2242-2246, 25th IEEE International Conference on Image Processing, ICIP 2018, Athens, Greece, 18/10/7. https://doi.org/10.1109/ICIP.2018.8451230
Dong Z, Kamata S, Breckon TP. Infrared Image Colorization Using a S-Shape Network. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society. 2018. p. 2242-2246. 8451230. (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2018.8451230
Dong, Ziyue ; Kamata, Seiichiro ; Breckon, Toby P. / Infrared Image Colorization Using a S-Shape Network. 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society, 2018. pp. 2242-2246 (Proceedings - International Conference on Image Processing, ICIP).
@inproceedings{83305c89a540461f85a047289edbc841,
title = "Infrared Image Colorization Using a S-Shape Network",
abstract = "This paper proposes a novel approach for colorizing near infrared (NIR) images using a S-shape network (SNet). The proposed approach is based on the usage of an encoder-decoder architecture followed with a secondary assistant network. The encoder-decoder consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. The assistant network is a shallow encoder-decoder to enhance the edge and improve the output, which can be trained end-to-end from a few image examples. The trained model does not require any user guidance or a reference image database. Furthermore, our architecture will preserve clear edges within NIR images. Our overall architecture is trained and evaluated on a real-world dataset containing a significant amount of road scene images. This dataset was captured by a NIR camera and a corresponding RGB camera to facilitate side-by-side comparison. In the experiments, we demonstrate that our SNet works well, and outperforms contemporary state-of-the-art approaches.",
keywords = "Colorization, Convolutional neural network, Infrared, S-shape network",
author = "Ziyue Dong and Seiichiro Kamata and Breckon, {Toby P.}",
year = "2018",
month = "8",
day = "29",
doi = "10.1109/ICIP.2018.8451230",
language = "English",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "2242--2246",
booktitle = "2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings",

}

TY - GEN

T1 - Infrared Image Colorization Using a S-Shape Network

AU - Dong, Ziyue

AU - Kamata, Seiichiro

AU - Breckon, Toby P.

PY - 2018/8/29

Y1 - 2018/8/29

N2 - This paper proposes a novel approach for colorizing near infrared (NIR) images using a S-shape network (SNet). The proposed approach is based on the usage of an encoder-decoder architecture followed with a secondary assistant network. The encoder-decoder consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. The assistant network is a shallow encoder-decoder to enhance the edge and improve the output, which can be trained end-to-end from a few image examples. The trained model does not require any user guidance or a reference image database. Furthermore, our architecture will preserve clear edges within NIR images. Our overall architecture is trained and evaluated on a real-world dataset containing a significant amount of road scene images. This dataset was captured by a NIR camera and a corresponding RGB camera to facilitate side-by-side comparison. In the experiments, we demonstrate that our SNet works well, and outperforms contemporary state-of-the-art approaches.

AB - This paper proposes a novel approach for colorizing near infrared (NIR) images using a S-shape network (SNet). The proposed approach is based on the usage of an encoder-decoder architecture followed with a secondary assistant network. The encoder-decoder consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. The assistant network is a shallow encoder-decoder to enhance the edge and improve the output, which can be trained end-to-end from a few image examples. The trained model does not require any user guidance or a reference image database. Furthermore, our architecture will preserve clear edges within NIR images. Our overall architecture is trained and evaluated on a real-world dataset containing a significant amount of road scene images. This dataset was captured by a NIR camera and a corresponding RGB camera to facilitate side-by-side comparison. In the experiments, we demonstrate that our SNet works well, and outperforms contemporary state-of-the-art approaches.

KW - Colorization

KW - Convolutional neural network

KW - Infrared

KW - S-shape network

UR - http://www.scopus.com/inward/record.url?scp=85062898599&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062898599&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2018.8451230

DO - 10.1109/ICIP.2018.8451230

M3 - Conference contribution

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 2242

EP - 2246

BT - 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings

PB - IEEE Computer Society

ER -