14 May 2018 Deep generative adversarial networks for infrared image enhancement
Author Affiliations +
Abstract
Extracting face images at a distance, in the crowd, or with a lower resolution infrared camera leads to a poorquality face image that is barely distinguishable. In this work, we present a Deep Convolutional Generative Adversarial Networks (DCGAN) for infrared face image enhancement. The proposed algorithm is used to build a super-resolution face image from its lower resolution counterpart. The resulting images are evaluated in term of qualitative and quantitative metrics on infrared face datasets (NIR and LWIR). The proposed algorithm performs well and preserves important details of the face. The analysis of the resulting images show that the proposed framework is promising and can help improve the performance of image super-resolution generation and enhancement in the infrared spectrum.
Conference Presentation
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Axel-Christian Guei, Axel-Christian Guei, Moulay A. Akhloufi, Moulay A. Akhloufi, } "Deep generative adversarial networks for infrared image enhancement", Proc. SPIE 10661, Thermosense: Thermal Infrared Applications XL, 106610B (14 May 2018); doi: 10.1117/12.2304875; https://doi.org/10.1117/12.2304875
PROCEEDINGS
12 PAGES + PRESENTATION

SHARE
Back to Top