Abstract
Since the beginning of Computer Vision, the resolution of image de-hazing has been a problem. Due to the presence of numerous air particles, resulting in haze, fog, and so on, photographs obtained under unfavorable weather circumstances often seem to be of low quality. This, in turn, makes recognizing objects in a picture difficult. This poses issues for many computer vision problems that depend on picture visibility. The image captured under haze as well as other weather conditions has a process of image deterioration. Image dehazing is a difficult as well as ill-posed task. It overcomes the difficulties of manually constructing haze-related characteristics by using deep learning algorithms. We develop a neural network for image de-hazing in this study. The network model consists of two phases: first, the network is given a foggy image and is tasked with estimating the transmission map; next, the network is given the transmission map estimate and the ratio of the foggy image to the transmission map, and is used to perform haze removal. It avoids estimating ambient light as well as enhances dehazing performance. The haze and dehaze datasets are used as the training set for the proposed scheme. The experimental outcomes for the full-reference metrics SSIM, PSNR, RMSE, MSE, or BRISQUE validate the suggested method's reliability and effectiveness.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
S.G. Narasimhan, S.K. Nayar, Contrast restoration of weather degraded images. IEEE Trans. Pattern Anal. Mach. Intell. (2003). https://doi.org/10.1109/TPAMI.2003.1201821
J. Gui et al., A comprehensive survey on image dehazing based on deep learning. (2021). https://doi.org/10.24963/ijcai.2021/604
T. Guo, V. Monga, Reinforced depth-aware deep learning for single image dehazing. (2020). https://doi.org/10.1109/ICASSP40776.2020.9054504
Y.H. Lai, Y.L. Chen, C.J. Chiou, C.T. Hsu, Single-image dehazing via optimal transmission map under scene priors. IEEE Trans. Circuits Syst. Video Technol. (2015). https://doi.org/10.1109/TCSVT.2014.2329381
R.R. Choudhary, K.K. Jisnu, G. Meena, Image DeHazing using deep learning techniques Ravi Raj Choudhary. (2020). https://doi.org/10.1016/j.procs.2020.03.413
C.A. Hartanto, L. Rahadianti, Single image dehazing using deep learning. Int. J. Informatics Vis. (2021). https://doi.org/10.30630/joiv.5.1.431
Z. Wang, A.C. Bovik, H.R. Sheikh, E.P. Simoncelli, Image quality assessment: From error visibility to structural similarity. IEEE Trans. Image Process. (2004). https://doi.org/10.1109/TIP.2003.819861
J. Li, G. Li, H. Fan, Image Dehazing using residual-based deep CNN. IEEE Access (2018). https://doi.org/10.1109/ACCESS.2018.2833888
J.L. Yin, Y.C. Huang, B.H. Chen, S.Z. Ye, Color transferred convolutional neural networks for image dehazing. IEEE Trans. Circuits Syst. Video Technol. (2020). https://doi.org/10.1109/TCSVT.2019.2917315
A. Golts, D. Freedman, M. Elad, Unsupervised single image dehazing using dark channel prior loss. IEEE Trans. Image Process. (2020). https://doi.org/10.1109/TIP.2019.2952032
X. Min et al., Quality evaluation of image dehazing methods using synthetic hazy images. IEEE Trans. Multimed. (2019). https://doi.org/10.1109/TMM.2019.2902097
L.Y. Huang, J.L. Yin, B.H. Chen, S.Z. Ye, Towards unsupervised single image dehazing with deep learning. (2019). https://doi.org/10.1109/ICIP.2019.8803316
Y. Du, X. Li, Recursive deep residual learning for single image dehazing. (2018). https://doi.org/10.1109/CVPRW.2018.00116
S. Kollmannsberger, D. D’Angella, M. Jokeit, L. Herrmann, Neural networks, in Studies in Computational Intelligence (2021)
L. Haripriya, M.A. Jabbar, M. Tech, A survey on neural networks and its applications. Int. J. Eng. Res. Comput. Sci. Eng. (2018)
J. Gu et al., Recent advances in convolutional neural networks. Pattern Recognit. (2018). https://doi.org/10.1016/j.patcog.2017.10.013
C. Szegedy et al., Going deeper with convolutions. (2015). https://doi.org/10.1109/CVPR.2015.7298594
C. Hodges, M. Bennamoun, H. Rahmani, Single image dehazing using deep neural networks. Pattern Recognit. Lett. (2019). https://doi.org/10.1016/j.patrec.2019.08.013
B. Sankur, Statistical evaluation of image quality measures. J. Electron. Imaging (2002). https://doi.org/10.1117/1.1455011
A. Mittal, A.K. Moorthy, A.C. Bovik, No-reference image quality assessment in the spatial domain. IEEE Trans. Image Process. (2012). https://doi.org/10.1109/TIP.2012.2214050
Funding
Each author confirms that he or she has no vested interest (financial or otherwise) in the contents of this document and has no financial or other ties to any organisations that could.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Parihar, A.S., Gupta, S. Dehazing optically haze images with AlexNet-FNN. J Opt 53, 294–303 (2024). https://doi.org/10.1007/s12596-023-01156-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12596-023-01156-3