Abstract
Images captured in poor atmospheric circumstances, like smog, rainy, cloudy, fog, smoke, etc., suffer from number of problems such as poor visibility, distortion of spectral ans spatial information, etc. In this paper, we have considered images taken in smoggy environment. However, optical imaging systems provide only smoggy images, but desmogging process require atmospheric veil and transmission map information. Thus, to restore smoggy images, it is required to predict optical information of smoggy images in an efficient manner. From the extensive review, it has been found that the optical information predicted using various channel prior such as dark channel prior may provide poor results especially when images contain brighter regions, large smog gradient, textured information, etc. Therefore, in this paper, a deep transfer learning (DTL) and oblique gradient profile prior (OGPP) is utilized to approximate the optical information. To train DTL, we have obtained benchmark somggy and smog-free images. Thereafter, DTL model is trained. Smog gradient predicted using DTL is used by OGPP model to recover smog-free images. Comparative analysis prove that the proposed DTL-OGPP based restoration model performs significantly better than the competitive restoration models.
Similar content being viewed by others
References
Abdullah-Al-Wadud M, Kabir MH, Dewan MAA, Chae O (2007) A dynamic histogram equalization for image contrast enhancement. IEEE Trans Consum Electron 53(2):593–600
Alajarmeh A, Zaidan A (2018) A real-time framework for video dehazing using bounded transmission and controlled gaussian filter. Multimedia Tools Appl 77(20):26315–26350
Bala J, Lakhwani K (2020) Single image desmogging using oblique gradient profile prior and variational minimization. Multidimens Syst Signal Process:1–17
Basavegowda HS, Dagnew G (2020) Deep learning approach for microarray cancer data classification. CAAI Trans Intell Technol 5(1):22–33
Borkar K, Mukherjee S (2020) Single image dehazing by approximating and eliminating the additional airlight component. Neurocomputing 400:294–308. https://doi.org/10.1016/j.neucom.2020.03.027
Ding R, Dai L, Li G, Liu H (2019) Tdd-net: a tiny defect detection network for printed circuit boards. CAAI Trans Intell Technol 4(2):110–116
Gao Y, Li Q, Li J (2020) Single image dehazing via a dual-fusion method. Image Vis Comput 94:103868
Gao Y, Su Y, Li Q, Li H, Li J (2020) Single image dehazing via self-constructing image fusion. Signal Process 167:107284. https://doi.org/10.1016/j.sigpro.2019.107284
Gui B, Zhu Y, Zhen T (2020) Adaptive single image dehazing method based on support vector machine. J Vis Commun Image Rep 102792
Gupta A, Singh D, Kaur M (2020) An efficient image encryption using non-dominated sorting genetic algorithm-iii based 4-d chaotic maps. J Ambient Intell Hum Comput 11(3):1309–1324
He K, Sun J, Tang X (2011) Single image haze removal using dark channel prior. IEEE Trans Pattern Anal Mach Intell 33(12):2341–2353
He K, Sun J, Tang X (2013) Guided image filtering. TPAMI 35(6):1397–1409
Iozzia G (2019) Hands-on deep learning with apache spark. Packt Publishing Limited, Birmingham
Jiang Y, Sun C, Zhao Y, Yang L (2017) Image dehazing using adaptive bi-channel priors on superpixels. Comput Vis Image Underst 165:17–32
Jiang B, Meng H, Zhao J, Ma X, Jiang S, Wang L, Zhou Y, Ru Y, Ru C (2017) Single image fog and haze removal based on self-adaptive guided image filter and color channel information of sky region. Multimedia Tools Appl:1–18
Kaur M, Kumar V (2018) Beta chaotic map based image encryption using genetic algorithm. Int J Bifurc Chaos 28(11):1850132
Kaur M, Singh D (2019) Fusion of medical images using deep belief networks. Clust Comput. https://doi.org/10.1007/s10586-019-02999-x
Kaur M, Kumar V, Li L (2019) Color image encryption approach based on memetic differential evolution. Neural Comput Appl 31(11):7975–7987
Kaur M, Singh D, Uppal RS (2019) Parallel strength pareto evolutionary algorithm-ii based image encryption. IET Image Process. https://doi.org/10.1049/iet-ipr.2019.0587
Kaur M, Singh D, Kumar V, Sun K (2020) Color image dehazing using gradient channel prior and guided l0 filter. Inf Sci 521:326–342. https://doi.org/10.1016/j.ins.2020.02.048
Kaur M, Singh D, Sun K, Rawat U (2020) Color image encryption using non-dominated sorting genetic algorithm with local chaotic search based 5d chaotic map. Fut Gen Comput Syst 107:333–350. https://doi.org/10.1016/j.future.2020.02.029
Kim J-H, Jang W-D, Sim J-Y, Kim C-S (2013) Optimized contrast enhancement for real-time image and video dehazing. J Vis Commun Image Rep 24(3):410–425
Kim J-H, Jang W-D, Sim J-Y, Kim C-S (2013) Optimized contrast enhancement for real-time image and video dehazing. J Vis Commun Image Rep 24(3):410–425. https://doi.org/10.1016/j.jvcir.2013.02.004
Kou F, Chen W, Wen C, Li Z (2015) Gradient domain guided image filtering. IEEE Trans Image Process 24(11):4528–4539
Levin A, Lischinski D, Weiss Y (2006) A closed form solution to natural image matting. In: CVPR
Li C-Y, Guo J-C, Cong R-M, Pang Y-W, Wang B (2016) Underwater image enhancement by dehazing with minimum information loss and histogram distribution prior. IEEE Trans Image Process 25(12):5664–5677
Li Y, Miao Q, Liu R, Song J, Quan Y, Huang Y (2018) A multi-scale fusion scheme based on haze-relevant features for single image dehazing. Neurocomputing 283:73–86. https://doi.org/10.1016/j.neucom.2017.12.046
Liang Z, Wang Y, Ding X, Mi Z, Fu X (2020) Single underwater image enhancement by attenuation map guided color correction and detail preserved dehazing. Neurocomputing
Liao B, Yin P, Xiao C (2018) Efficient image dehazing using boundary conditions and local contrast. Comput Gr 70:242–250. https://doi.org/10.1016/j.cag.2017.07.016
Li W, Hu W, Ran Q, Zhang F, Du Q, Younan N (2014) Improving hyperspectral image classification using smoothing filter via sparse gradient minimization. In: Pattern recognition in remote sensing (PRRS), 2014 8th IAPR Workshop on, IEEE, pp 1–4
Liu X, Zhang H, Cheung Y, You X, Tang YY (2017) Efficient single image dehazing and denoising: An efficient multi-scale correlated wavelet approach. Comput Vis Image Underst 162:23–33. https://doi.org/10.1016/j.cviu.2017.08.002
Luan Z, Shang Y, Zhou X, Shao Z, Guo G, Liu X (2017) Fast single image dehazing based on a regression model. Neurocomputing 245:10–22. https://doi.org/10.1016/j.neucom.2017.03.024
Menotti D, Najman L, Facon J, Araujo ADA (2007) Multi-histogram equalization methods for contrast enhancement and brightness preserving. IEEE Trans Consum Electron 53(3):1186–1194
Nair D, Sankaran P (2018) Color image dehazing using surround filter and dark channel prior. J Vis Commun Image Rep 50:9–15. https://doi.org/10.1016/j.jvcir.2017.11.005
Ooi CH, Kong NSP, Ibrahim H (2009) Bi-histogram equalization with a plateau limit for digital image enhancement. IEEE Trans Consum Electron 55(4):2072–2080
Pannu HS, Singh D, Malhi AK (2018) Improved particle swarm optimization based adaptive neuro-fuzzy inference system for benzene detection, CLEAN-Soil, Air. Water 46(5):1700162
Pannu HS, Singh D, Malhi AK (2019) Multi-objective particle swarm optimization-based adaptive neuro-fuzzy inference system for benzene monitoring. Neural Comput Appl 31:2195–2205
Pathak Y, Shukla PK, Tiwari A, Stalin S, Singh S, Shukla PK (2020) Deep transfer learning based classification model for covid-19 disease. IRBM. https://doi.org/10.1016/j.irbm.2020.05.003
Qi G, Wang H, Haner M, Weng C, Chen S, Zhu Z (2019) Convolutional neural network based detection and judgement of environmental obstacle in vehicle operation. CAAI Trans Intell Technol 4(2):80–91
Shu Q, Wu C, Zhong Q, Liu RW (2019) Alternating minimization algorithm for hybrid regularized variational image dehazing. Optik 185:943–956. https://doi.org/10.1016/j.ijleo.2019.04.002
Shukla PK, Shukla PK, Sharma P, Rawat P, Samar J, Moriwal R, Kaur M (2020) Efficient prediction of drug-drug interaction using deep learning models. IET Syst Biol. https://doi.org/10.1049/iet-syb.2019.0116
Singh D, Kumar V (2017) Modified gain intervention filter based dehazing technique. J Mod Opt 64(20):2165–2178
Singh D, Kumar V (2018) Dehazing of outdoor images using notch based integral guided filter. Multimedia Tools Appl 77(20):27363–27386
Singh D, Kumar V (2018) A novel dehazing model for remote sensing images. Comput Electr Eng 69:14–27
Singh D, Kumar V (2019) Single image defogging by gain gradient image filter. Sci China Inf Sci 62(7):79101
Singh D, Kumar V (2019) Image dehazing using moore neighborhood-based gradient profile prior. Sig Process Image Commun 70:131–144
Singh D, Kumar V (2019) A comprehensive review of computational dehazing techniques. Arch Comput Methods Eng 26(5):1395–1413
Singh D, Kumar V, Kaur M (2019) Image dehazing using window-based integrated means filter. Multimedia Tools Appl. https://doi.org/10.1007/s11042-019-08286-6
Singh D, Kumar V, Kaur M (2019) Single image dehazing using gradient channel prior. Appl Intell 49(12):4276–4293
Singh D, Kumar V, Vaishali KM (2020) Classification of covid-19 patients from chest ct images using multi-objective differential evolution-based convolutional neural networks. Eur J Clin Microbiol Infect Dis. https://doi.org/10.1007/s10096-020-03901-z
Singh D, Kumar V (2017) Comprehensive survey on haze removal techniques. Multimedia Tools Appl:1–26
Wan Y, Shi D (2007) Joint exact histogram specification and image enhancement through the wavelet transform. IEEE Trans Image Process 16(9):2245–2250
Wang W, He C, Xia X-G (2018) A constrained total variation model for single image dehazing. Pattern Recogn 80:196–209
Wang Y, Huang T-Z, Zhao X-L, Deng L-J, Ji T-Y (2020) A convex single image dehazing model via sparse dark channel prior. Appl Math Comput 375:125085
Wu Y, Qin Y, Wang Z, Ma X, Cao Z (2020) Densely pyramidal residual network for uav-based railway images dehazing. Neurocomputing 371:124–136. https://doi.org/10.1016/j.neucom.2019.06.076
Xiao J, Zhu L, Zhang Y, Liu E, Lei J (2017) Scene-aware image dehazing based on sky-segmented dark channel prior. IET Image Proc 11(12):1163–1171
Xiao J, Shen M, Lei J, Zhou J, Klette R, Sui H (2020) Single image dehazing based on learning of haze layers. Neurocomputing 389:108–122
Yin S, Wang Y, Yang Y-H (2020) A novel image-dehazing network with a parallel attention block. Pattern Recogn 102:107255
Yoon I, Jeong S, Jeong J, Seo D, Paik J (2015) Wavelength-adaptive dehazing using histogram merging-based classification for uav images. Sensors 15(3):6633–6651
Yu T, Riaz I, Piao J, Shin H (2015) Real-time single image dehazing using block-to-pixel interpolation and adaptive dark channel prior. IET Image Proc 9(9):725–734
Yuan F, Zhou Y, Xia X, Shi J, Fang Y, Qian X (2020) Image dehazing based on a transmission fusion strategy by automatic image matting. Comput Vis Image Underst 194:102933
Zhang J, Wang X, Yang C, Zhang J, He D, Song H (2018) Image dehazing based on dark channel prior and brightness enhancement for agricultural remote sensing images from consumer-grade cameras. Comput Electron Agric 151:196–206
Zhang X, Wang T, Wang J, Tang G, Zhao L (2020) Pyramid channel-based feature attention network for image dehazing. Comput Vis Image Underst. https://doi.org/10.1016/j.cviu.2020.103003
Zhao D, Xu L, Yan Y, Chen J, Duan L-Y (2019) Multi-scale optimal fusion model for single image dehazing. Sig Process Image Commun 74:253–265
Zheng L, Shi H, Gu M (2017) Infrared traffic image enhancement algorithm based on dark channel prior and gamma correction. Mod Phys Lett B 31(19–21):1740044
Zhu X, Xiang R, Wu F, Jiang X (2017) Single image haze removal based on fusion darkness channel prior. Mod Phys Lett B 31(19–21):1740037
Zhu M, He B, Liu J, Yu J (2020) Boosting dark channel dehazing via weighted local constant assumption. Sig Process 171:107453. https://doi.org/10.1016/j.sigpro.2019.107453
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
About this article
Cite this article
Jain, A., Kumar, A. Desmogging of still smoggy images using a novel channel prior. J Ambient Intell Human Comput 12, 1161–1177 (2021). https://doi.org/10.1007/s12652-020-02161-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-020-02161-1