• M.Vasudeva Reddy
• Dr.T.Ramashri

Haze in remotely sensed images degrades the visual multispectral information. The literature reveals that haze removed images have problems like halo artifacts, colour distortion, etc. To overcome these problems, in this paper the fine scale transmission map of images is used in Convolutional neural network to restore the haze free images. Hazy images contain small value in only one-color alpha channel from Red, Blue, green RGB channel. The intensity of these pixels varies by air light depth map. Hence estimating these low value points of haze transmission map and an end-to-end encoder-decoder training model is utilized to achieve a high quality dehazed image. The experimental results reveal that this approach provides visually significant haze-free images by preserving the significant details when compared to DWT based Dehazing.

Haze, Dehazing, Discrete Wavelet Transform, Dark Channel Prior, Haar wavelet.

"Dehazing of Satellite images using Convolutional Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.255-260, June 2019, Available :http://www.jetir.org/papers/JETIR1907H41.pdf

"Dehazing of Satellite images using Convolutional Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp255-260, June 2019, Available at : http://www.jetir.org/papers/JETIR1907H41.pdf