Autoencoder based Visibility Enhancement Technique for Hazy Scenes

Abstract

This paper proposes a single image dehazing model built with the autoencoder network. The Outdoor images captured during the inclement weather conditions such as haze, fog and sandstorms generally exhibit visibility degradation. Due to the unclear visibility, transportation system may suffer a lot. So, an automatic method has been proposed to enhance the visibility of images even in the bad weather condition too. There are so many traditional haze removal methods available, but there is a scope to improve the visibility of the image. To improve the visibility of the images still better, deep learning techniques are preferred in this work. The proposed method enhances the visual quality of the input hazy image. Experimentation is carried out with the FRIDA database images and natural hazy images. The result of this work is superior than the state of art in terms of the performance measures such as PSNR, E metric and metric.