Author(s)

Amina Khatun¹, Mohammad Reduanul Haque², Rabeya Basri¹, Mohammad Shorif Uddin¹

¹Department of Computer Science and Engineering, Jahangirnagar University, Dhaka, Bangladesh.
²Department of Computer Science and Engineering, Daffodil International University, Dhaka, Bangladesh.

Haze is a very common phenomenon that degrades or reduces visibility. It causes various problems where high-quality images are required such as traffic and security monitoring. So haze removal from scenes is an immediate demand for clear vision. Recently, in addition to the conventional dehazing mechanisms, different types of deep generative adversarial networks (GAN) are applied to suppress the noise and improve the dehazing performance. But it is unclear how these algorithms would perform on hazy images acquired “in the wild” and how we could gauge the progress in the field. To bridge this gap, this presents a comprehensive study on three single image dehazing state-of-the-art GAN models, such as AOD-Net, cGAN, and DHSGAN. We have experimented using benchmark dataset consisting of both synthetic and real-world hazy images. The obtained results are evaluated both quantitatively and qualitatively. Among these techniques, the DHSGAN gives the best performance.

Dehazing, Deep Leaning, Convulutional Neural Network (CNN), Generative Adversarial Networks (GAN)

Khatun, A. , Haque, M. , Basri, R. and Uddin, M. (2020) Single Image Dehazing: An Analysis on Generative Adversarial Network. Journal of Computer and Communications, 8, 127-137. doi: 10.4236/jcc.2020.84010.