Single Image Dehazing Using Deep Learning

Cahyo Hartanto - Faculty of Computer Science, Universitas Indonesia, Depok, Indonesia
Laksmita Rahadianti - Faculty of Computer Science, Universitas Indonesia, Depok, Indonesia


Citation Format:



DOI: http://dx.doi.org/10.30630/joiv.5.1.431

Abstract


Many real-world situations such as bad weather may result in hazy environments. Images captured in these hazy conditions will have low image quality due to microparticles in the air. The microparticles light to scatter and absorb, resulting in hazy images with various effects. In recent years, image dehazing has been researched in depth to handle images captured in these conditions. Various methods were developed, from traditional methods to deep learning methods. Traditional methods focus more on the use of statistical prior. These statistical prior have weaknesses in certain conditions. This paper proposes a novel architecture based on PDR-Net by using a pyramid dilated convolution and pre-processing modules, processing modules, post-processing modules, and attention applications. The proposed network is trained to minimize L1 loss and perceptual loss with the O-Haze dataset. To evaluate our architecture's result, we used structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), and color difference as an objective assessment and psychovisual experiment as a subjective assessment. Our architecture obtained better results than the previous method using the O-Haze dataset with an SSIM of 0.798, a PSNR of 25.39, but not better on the color difference. The SSIM and PSNR results were strengthened by using subjective assessments and 65 respondents, most of whom chose the results of the restoration of the image produced by our architecture.

Keywords


Single image dehazing; deep learning; image restoration; image quality assessment.

Full Text:

PDF

References


H. Fu, B. Wu, Y. Shao, and H. Zhang, “Perception Oriented Haze Image Definition Restoration by Basing on Physical Optics Perception Oriented Haze Image Definition Restoration by Basing,†IEEE Photonics J., vol. 10, no. 3, pp. 1–16, 2018.

Y. Liang, K. Zhao, W. Zhang, and Y. Li, “Research on single image haze removal algorithm based on parameter optimization search of linear model,†2018 Int. Conf. Adv. Mechatron. Syst., pp. 326–331, 2018.

X. Min, G. Zhai, K. Gu, X. Yang, and X. Guan, “Objective Quality Evaluation of Dehazed Images,†IEEE Trans. Intell. Transp. Syst., pp. 1–14, 2018.

K. He, J. Sun, and X. Tang, “Single Image Haze Removal Using Dark Channel Prior,†IEEE Trans. Pattern Anal. Mach. Intell., pp. 2351–2353, 2011.

G. Meng, Y. Wang, J. Duan, S. Xiang, and C. Pan, “Efficient Image Dehazing with Boundary Constraint and Contextual Regularization,†IEEE Int. Conf. Comput. Vis., 2013.

B. Li et al., “Benchmarking Single Image Dehazing and Beyond,†IEEE Trans. Image Process., vol. PP, no. 8, p. 1, 2018.

B. Cai, X. Xu, K. Jia, C. Qing, and D. Tao, “DehazeNet : An End-to-End System for Single Image,†Springer Int. Publ., pp. 1–13, 2016.

H. Zhang, V. Sindagi, and V. M. Patel, “Multi-scale Single Image Dehazing using Perceptual Pyramid Deep Network.â€

X. Qin, Z. Wang, Y. Bai, X. Xie, and H. Jia, “FFA-Net : Feature Fusion Attention Network for Single Image Dehazing,†AAAI Conf. Artif. Intell., 2020.

X. Liu, Y. M. Ma, Z. Shi, and C. Jun, “GridDehazeNet : Attention-Based Multi-Scale Network for Image Dehazing,†CVPR 2019, pp. 7314–7323, 2019.

C. Li, C. Guo, J. Guo, P. Han, H. Fu, and S. Member, “PDR-Net : Perception-Inspired Single Image Dehazing Network With Refinement,†vol. 22, no. 3, pp. 704–716, 2020.

F. Yu and V. Koltun, “Multi-scale Context Aggregation by Dilated Convolutions,†ICLR, 2016.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,†2016 IEEE Conf. Comput. Vis. Pattern Recognit., 2016.

H. Park, D. Park, D. K. Han, and H. Ko, “Single Image Haze Removal Using Novel Estimation of Atmospheric Light and Transmission,†Int. Conf. Image Process., no. 2, pp. 4502–4506, 2014.

R. Fattal, “Dehazing Using Color-Lines,†ACM Trans. Graph., vol. 34, no. 1, pp. 1–14, 2014.

C. Ancuti, C. O. Ancuti, and A. C. Bovik, “Night time dehazing by fusion,†Int. Conf. Image Process., 2016.

W. Ren, S. Liu, H. Zhang, J. Pan, and X. C. B, “Single Image Dehazing via Multi-scale Convolutional Neural Networks,†Springer Int. Publ., vol. 1, pp. 154–169, 2016.

M. Gridach and I. Voiiculescu, “Oxendonet : A Dilated Convolutional Neural Networks for Endoscopic Artefact Segmentation,†EndoCV2020, pp. 2–5, 2020.

M. Holschneider and R. Kronland-martinet, “A Real-Time Algorithm for Signal Analysis with the Help of the Wavelet Transform,†Springer, 1990, no. August 2014, 1989.

J. Long, E. Shelhamer, and T. Darrell, “Fully Convolutional Networks for Semantic Segmentation,†CVPR 2015, pp. 3431–3440, 2015.

L. Yan, B. Zhong, and W. Song, “Region-based Fully Convolutional Networks for Vertical Corner Line Detection,†2017 Int. Symp. Intell. Signal Process. Commun. Syst., pp. 159–163, 2017.

L. Chen and A. L. Yuille, “Attention to Scale : Scale-aware Semantic Image Segmentation,†2016.

H. Zhang, V. Sindagi, and V. M. Patel, “Multi-scale Single Image Dehazing using Perceptual Pyramid Deep Network,†2018 IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Work., pp. 1015–101509, 2018.

Y. Qu, Y. Chen, J. Huang, and Y. Xie, “Enhanced Pix2pix Dehazing Network,†CVPR 2017, pp. 8160–8168, 2017.

Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image Quality Assessment : From Error Visibility to Structural Similarity,†IEEE Trans. Image Process., vol. 13, no. 4, pp. 600–612, 2004.

Z. Kotevski and P. Mitrevski, “Experimental Comparison of PSNR and SSIM Metrics,†ICT Innov. 2009, 2009.

M. R. Luo, G. Cui, and B. Rigg, “The Development of the CIE 2000 Colour-Difference Formula :,†CIE, pp. 340–350, 2001.

C. O. Ancuti, C. Ancuti, R. Timofte, and C. De Vleeschouwer, “O-HAZE : a dehazing benchmark with real hazy and haze-free outdoor images,†2018.