Vol. 26 Issue 1 2023

P. Naresh babu1, CH. Amitha Reddy2, D. Akanksha3, CH. Pravalika4

1Assistant Professor, Department of ECE, Malla Reddy Engineering College For Women, Hyderabad.

2,3&4UG Scholar, Department of ECE, Malla Reddy Engineering College For Women, Hyderabad


Haze is a natural phenomenon in which the dust, smoke and other particles alter the vision of the sky to reduce the visibility. Hazy images cause various visibility problems for traffic user, tourists everywhere, especially in hilly areas where haze and fog are very common. In this paper, a method for single image dehazing using convolutional neural network is proposed. Outdoor images have been used on which particular filters are applied to find the haze in image. Hazy images contain small value in only one-color alpha channel from Red, Blue, green RGB channel. The intensity of these pixels is mainly bestowed by air light depth map. Estimating these low value points of haze transmission map are useful to obtain a high quality dehazed image. An end-to-end encoder-decoder training model is utilized to achieve a high quality dehazed image. The approach is validated on datasets which consists of around 1500 outdoor images. The method also gives transmission map of the hazy image which can further be used to enhance visibility of the scene.