Vol.7, No.4, November 2018.                                                                                                                                                                             ISSN: 2217-8309

                                                                                                                                                                                                                        eISSN: 2217-8333


TEM Journal



Association for Information Communication Technology Education and Science

A Robust Visibility Restoration Framework for Rainy Weather Degraded Images


Narendra Singh Pal, Shyam Lal, Kshitij Shinghal


© 2018 Narendra Singh Pal, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)


Citation Information: TEM Journal. Volume 7, Issue 4, Pages 859-868, ISSN 2217-8309, DOI: 10.18421/TEM74-26, November 2018.


Received: 18 August 2018.
Accepted: 22 October 2018.
Published: 26 November 2018.




Visibility restoration of color rainy images is inevitable task for the researchers in many vision based applications. Rain produces a visual impact on
image, so that the intensity and visibility of image is low. Therefore, there is a need to develop a robust visibility restoration algorithm for the rainy images. In
this paper we proposed a robust visibility restoration framework for the images captured in rainy weather. The framework is the combined form of convolution
neural network for rain removal and low light image enhancement for low contrast. The output results of the proposed framework and other latest de-rainy
algorithms are estimated in terms of PSNR, SSIM and UIQI on rainy image from different databases. The quantitative and qualitative results of the proposed
framework are better than other de-rainy algorithms. Finally, the obtained visualization result also shows the efficiency of the proposed framework.


Keywords –De-rain, Convolution Neural network, Low light image enhancement, Visibility enhancement.



Full text PDF >  



Copyright © 2012-2018 UIKTEN, All Rights reserved
Copyright licence: All articles are licenced via Creative Commons CC BY-NC-ND 4.0 licence