Multi-Feature-Based Bilinear CNN for Single Image Dehazing

Image dehazing has been a great challenge in the process of adjusting haze images. In this paper, an effective and accurate dehazing method based on atmospheric scattering model is proposed. Since the dark channel is not applicable to sky areas, single-threshold segmentation combined with quad-tree partition technique is adopted to position and estimate the ambient light $A$ * rapidly and accurately. In order to optimize transmittance, we employ a new convolutional network architecture, multi-feature-based bilinear CNN, which can mitigate the halo effect around the abrupt edges and restrain image noise, and the whole transmittance estimation process can be divided into three main parts: feature extraction, nonlinear mapping, and image reconstruction. A large number of outdoor haze image test results show that our optimized method has better experimental results than the existing methods.

[1]  Go Tanaka,et al.  Proposal of Multiscale Retinex Using Illumination Adjustment for Digital Images , 2016, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[2]  Javier Vazquez-Corral,et al.  Fusion-Based Variational Image Dehazing , 2017, IEEE Signal Processing Letters.

[3]  Swarnajyoti Patra,et al.  A novel context sensitive multilevel thresholding for image segmentation , 2014, Appl. Soft Comput..

[4]  Michael Werman,et al.  Automatic recovery of the atmospheric light in hazy images , 2014, 2014 IEEE International Conference on Computational Photography (ICCP).

[5]  Alan C. Bovik,et al.  A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms , 2006, IEEE Transactions on Image Processing.

[6]  Joonki Paik,et al.  Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering , 1998 .

[7]  Bin Wu,et al.  Perception Oriented Haze Image Definition Restoration by Basing on Physical Optics Model , 2018, IEEE Photonics Journal.

[8]  Sarah Marzen,et al.  Revisiting Perceptual Distortion for Natural Images: Mean Discrete Structural Similarity Index , 2017, 2017 Data Compression Conference (DCC).

[9]  Ketan Tang,et al.  Investigating Haze-Relevant Features in a Learning Framework for Image Dehazing , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  D. Van der Weken,et al.  Image quality evaluation , 2002, 6th International Conference on Signal Processing, 2002..

[11]  Weixing Wang,et al.  Retinex Algorithm on Changing Scales for Haze Removal with Depth Map , 2014 .

[12]  Xiaoou Tang,et al.  Single Image Haze Removal Using Dark Channel Prior , 2011 .

[13]  Rinita Roy,et al.  Optimization of Stego Image Retaining Secret Information Using Genetic Algorithm with 8-connected PSNR , 2015, KES.

[14]  Keyan Wang,et al.  Quantitative Performance Evaluation for Dehazing Algorithms on Synthetic Outdoor Hazy Images , 2018, IEEE Access.

[15]  Zia-ur Rahman,et al.  Retinex processing for automatic image enhancement , 2004, J. Electronic Imaging.

[16]  Jian Sun,et al.  Fast Guided Filter , 2015, ArXiv.

[17]  Saumik Bhattacharya,et al.  Dehazing of color image using stochastic enhancement , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[18]  Changchun Liu,et al.  A Region-Wised Medium Transmission Based Image Dehazing Method , 2017, IEEE Access.

[19]  Dragan Kukolj,et al.  Image quality assessment based on pyramid decomposition and mean squared error , 2015, 2015 23rd Telecommunications Forum Telfor (TELFOR).

[20]  A. Kokhanovsky,et al.  Analytical solutions of multiple light scattering problems: a review , 2002 .

[21]  Jian Liang,et al.  Fast polarimetric dehazing method for visibility enhancement in HSI colour space , 2017 .

[22]  Tae-Hwan Kim,et al.  Fast Execution Schemes for Dark-Channel-Prior-Based Outdoor Video Dehazing , 2018, IEEE Access.

[23]  吴 斌 Wu Bin,et al.  De-hazing of atmosphere veil haze images , 2016 .

[24]  Du-Yih Tsai,et al.  Information Entropy Measure for Evaluation of Image Quality , 2008, Journal of Digital Imaging.

[25]  Dacheng Tao,et al.  DehazeNet: An End-to-End System for Single Image Haze Removal , 2016, IEEE Transactions on Image Processing.

[26]  Y. Rao,et al.  Generalized Equalization Model for Image Enhancement , 2016 .

[27]  Xiaochun Cao,et al.  Single Image Dehazing via Multi-scale Convolutional Neural Networks , 2016, ECCV.

[28]  Fu Hu.  Fast Image Dehazing Based on Dark-chanel Physical Model , 2016 .

[29]  Djemel Ziou,et al.  Image Quality Metrics: PSNR vs. SSIM , 2010, 2010 20th International Conference on Pattern Recognition.

[30]  Jean-Philippe Tarel,et al.  Vision Enhancement in Homogeneous and Heterogeneous Fog , 2012, IEEE Intelligent Transportation Systems Magazine.

[31]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[32]  Jian Sun,et al.  Guided Image Filtering , 2010, ECCV.

[33]  V. Rajamani,et al.  Contrast enhancement using real coded genetic algorithm based modified histogram equalization for gray scale images , 2015, Int. J. Imaging Syst. Technol..

[34]  Xiao Lu,et al.  Learning deep transmission network for single image dehazing , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[35]  Bertram Walter.  Simulation and visualization of atmospheric light phenomena induced by light scattering , 2002 .

[36]  Wilfried Philips,et al.  Image segmentation with adaptive region growing based on a polynomial surface model , 2013, J. Electronic Imaging.

[37]  Abdul Ghafoor,et al.  A Framework for Outdoor RGB Image Enhancement and Dehazing , 2018, IEEE Geoscience and Remote Sensing Letters.

[38]  D. Wang,et al.  Image and Texture Segmentation Using Local Spectral Histograms , 2006, IEEE Transactions on Image Processing.

[39]  Raanan Fattal,et al.  Single image dehazing , 2008, ACM Trans. Graph..

[40]  Jean-Philippe Tarel,et al.  BLIND CONTRAST ENHANCEMENT ASSESSMENT BY GRADIENT RATIOING AT VISIBLE EDGES , 2011 .