A Variational Framework for Single Image Dehazing Based on Restoration

The single image dehazing algorithm in existence can satisfy the demand only for improving either the effectiveness or efficiency. In order to solve the problem, a novel variational framework for single image dehazing based on restoration is proposed. Firstly, the initial atmospheric scattering model is transformed to meet the kimmel`s Retinex variational model. Then, the green light component of image is considered as an input of the variational framework, which is generated by the sensitivity of green wavelength. Finally, the atmospheric transmission map is achieved by multi-resolution pyramid reduction to improve the visual effect of the results. Experimental results demonstrate that the proposed method can remove haze effectively with less memory consumption.

[1]  W. Marsden.  I and J , 2012 .

[2]  Cosmin Ancuti,et al.  A Fast Semi-inverse Approach to Detect and Remove the Haze from a Single Image , 2010, ACCV.

[3]  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.

[4]  Zhan Ji.  Simultaneous Dehazing and Denoising of Single Hazing Image , 2012 .

[5]  E. Land,et al.  Lightness and retinex theory. , 1971, Journal of the Optical Society of America.

[6]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[7]  Duyan Bi,et al.  A modif ied image enhancement algorithm based on color constancy , 2009 .

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

[9]  Peter Carr,et al.  Improved Single Image Dehazing Using Geometry , 2009, 2009 Digital Image Computing: Techniques and Applications.

[10]  Wenbin Chen,et al.  Real-Time Dehazing for Image and Video , 2010, 2010 18th Pacific Conference on Computer Graphics and Applications.

[11]  Wang Yun-fei.  Retinex color image enhancement based on adaptive bidimensional empirical mode decomposition , 2011 .

[12]  Neil Genzlinger.  A. and Q , 2006 .