Improved algorithm for image haze removal based on dark channel priority

Abstract An improved algorithm is proposed for image haze removal based on dark channel priority to avoid the color distortion of haze removing about sky, white cloud or bright areas. The improved algorithm is mainly reflected in the following two aspects. One is the refined atmospheric transmittance of the hazy images with non-sky obtained using guided filter. The other is that the atmospheric transmittance of the hazy images with the sky, white cloud or the bright areas is estimated by a variety of classified statistics for haze-free outdoor images with non-sky or the haze-free outdoor images with sky. Compared with He algorithm, the weakness of atmospheric transmission of the hazy images with the sky, white cloud or the bright areas is remedied. Experimental results show that the improved algorithm is efficient to image haze removal.

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

[2]  Chunxia Xiao,et al.  Fast image dehazing using guided joint bilateral filter , 2012, The Visual Computer.

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

[4]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

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

[6]  Ling Shao,et al.  A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior , 2015, IEEE Transactions on Image Processing.

[7]  Gaofeng Meng,et al.  Efficient Image Dehazing with Boundary Constraint and Contextual Regularization , 2013, 2013 IEEE International Conference on Computer Vision.

[8]  A. Cantor.  Optics of the atmosphere--Scattering by molecules and particles , 1978, IEEE Journal of Quantum Electronics.

[9]  Robert V. Brill,et al.  Applied Statistics and Probability for Engineers , 2004, Technometrics.

[10]  Jean-Philippe Tarel,et al.  Fast visibility restoration from a single color or gray level image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[11]  Ko Nishino,et al.  Factorizing Scene Albedo and Depth from a Single Foggy Image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[12]  Seung-Won Jung,et al.  A review on dark channel prior based image dehazing algorithms , 2016, EURASIP Journal on Image and Video Processing.

[13]  Dani Lischinski,et al.  A Closed-Form Solution to Natural Image Matting , 2008 .

[14]  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.