Infrared Image Colorization Using S-Shape Network

Dong, Z.; Kamata, S.; Breckon, T.P.

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.

Citation

Dong, Z., Kamata, S., & Breckon, T. (2018, October). Infrared Image Colorization Using S-Shape Network. Presented at 25th IEEE International Conference on Image Processing (ICIP)., Athens, Greece

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 25th IEEE International Conference on Image Processing (ICIP).
• Start Date: Oct 7, 2018
• End Date: Oct 10, 2018
• Acceptance Date: May 4, 2018
• Online Publication Date: Sep 6, 2018
• Publication Date: 2018
• Deposit Date: Jun 10, 2018
• Publicly Available Date: Jun 11, 2018
• Pages: 2242-2246
• Series ISSN: 2381-8549
• Book Title: Proc. Int. Conf. on Image Processing
• ISBN: 9781479970629
• DOI: https://doi.org/10.1109/ICIP.2018.8451230
• Keywords: deep learning, image colorization, near infrared, false colour
• Public URL: https://durham-repository.worktribe.com/output/1144533