An adaptive weight value-based multi-scale retinex algorithm for color image enhancement

There are limited dynamic range problems when real world scenes are captured from a digital camera and displayed on monitors.Retinex is one of the most popular theories for dynamic range compression, color constancy and color rendition.However, there still exist some problems, such as hue shift and excessive noise, especially for those images including large bright areas and dark regions.In order to solve these problems,an adaptive weight value-based multi-scale retinex algorithm is proposed in this paper. Compared to other methods, visual experiments and data evaluation show that the proposed algorithms can achieve better performance for color image enhancement and noise suppression simultaneously. What is more, there is no need for color correction phase in the proposed algorithm, which makes it more efficient and convenient to apply.

[1]  Wei Guo,et al.  Luminance Based MSR for Color Image Enhancement , 2008, 2008 Congress on Image and Signal Processing.

[2]  E H Land,et al.  An alternative technique for the computation of the designator in the retinex theory of color vision. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[3]  Zia-ur Rahman,et al.  Statistics of visual representation , 2002, SPIE Defense + Commercial Sensing.

[4]  Chin-Chuan Han,et al.  Adaptive Multiscale Retinex for Image Contrast Enhancement , 2013, 2013 International Conference on Signal-Image Technology & Internet-Based Systems.

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

[6]  Michael Elad,et al.  A Variational Framework for Retinex , 2002, IS&T/SPIE Electronic Imaging.

[7]  Zia-ur Rahman,et al.  Properties and performance of a center/surround retinex , 1997, IEEE Trans. Image Process..