Multi-scale Retinex Algorithm for the Foggy Image Enhancement Based on Sub-band Decomposition

doi:DOI:10.3969/j.issn.1007-2985.2015.01.010

Abstract

Abstract: A kind of Multi-Scale Retinex (MSR) algorithm based on sub-band decomposition for image enhancement was proposed.First,the improved MSR algorithm was used to deal with the foggy image.Then,the gain of the different foggy image was obtained by the sub-band decomposition method.After that,the clear and enhanced image was obtained by the image fusion technology.At the same time,the simulation results of the algorithm was analyzed by using the mean value,standard deviation,entropy and mean square error (MSE) and peak signal-to-noise ratio (PSNR).The simulation and evaluation results show that the contrast of image is increased,the useful information of the original image is retained,the degree of distortion is small,and the clarity of the image can be improved.

Key words: sub-band decomposition, Retinex algorithm, sub-band decomposition multi-scale retinex (SDMSR), mean value, standard deviation, mean squared error(MSE), peak signal-to-noise ratio(PSNR)

SHU Ting, LIU Yao-Feng, DENG Bo, TAN Ya-Peng, CHEN Bing-Quan. Multi-scale Retinex Algorithm for the Foggy Image Enhancement Based on Sub-band Decomposition[J]. journal6, 2015, 36(1): 40-45.

References

[1] LAND E.The Retinex[J].Am Sci,1964,52(2):247-264.

[2] RAHMAN Z,JOBSON D J,WOODELL G A.Multi-Scale Retinex for Color Image Enhancement[C]//Image Processing,1996.Proceedings.,International Conference on.IEEE,1996,3:1 003-1 006.

[3] JOBSON D J,RAHMAN Z,WOODELL G A.Properties and Performance of a Center/surround Retinex[J].Image Processing,IEEE Transactions on,1997,6(3):451-462.

[4] MOORE A,ALLMAN J,GOODMAN R M.A Real-Time Neural System for Color Constancy[J].Neural Networks,IEEE Transactions on,1991,2(2):237-247.

[5] JOBSON D J,RAHMAN Z,WOODELL G A.A Multi-Scale Retinex for Bridging the Between Color Images and the Human Observation of Scenes[J].Ieee Transactions on Image Processing for Automatic Image Enhancement [J].Journal of Electronic Imaging,2004,13(1):100-110.

[6] RAHMAN Z.Investigating the Relationship Between Image Enhancement and Image Compression in the Context Of The Multi-Scale Retinex[J].Journal of Visual Communication and Image Representation,2011,22(3):237-250.

[7] 方志军，等.基于子带加权融合的多尺度Retinex图像增强算法[J].山东大学学报:理学版,2013(48).

[8] JANG J H,CHOI B,KIM S D,et al.Sub-Band Decomposed Multiscale Retinex with Space Varying Gain[C]//Image Processing,2008.ICIP 2008.15th IEEE International Conference on.IEEE,2008:3 168-3 171.

[9] JANG J H,KIM S D,RA J B.Enhancement of Optical Remote Sensing Images by Subband-Decomposed Multiscale Retinex with Hybrid Intensity Transfer Function[J].Geoscience and Remote Sensing Letters,IEEE,2011,8(5):983-987.

[10] JANG J H,BAE Y,RA J B.Contrast-Enhanced Fusion of Multisensory Images Using Subband-Decomposed Multiscale Retinex[J].Image Processing,IEEE Transactions on,2012,21(8):3479-3490.

[11] BJONTEGAARD G.document VCEG-M33:Calculation of Average PSNR Differences Between RD-Curves[C]//ITU-T VCEG Meeting,Austin,Texas,USA,Tech.Rep.2001.

[12] 赵小川.现代数字图像处理技术提高及应用案例的详解（MATLAB版）[M].北京：北京航空航天大学出版社，2011：112-132.

[1]	LU Weiyang,GAO Li. On the Hybrid Mean Value of the Smarandache Double-Factorial Function [J]. Journal of Jishou University（Natural Sciences Edition), 2017, 38(3): 4-7.
[2]	TAN Yapeng，LI Lihua，ZHANG Shuzhen. Adaptive Retinex and Modified Canny Edge Detection Algorithm for Furnace Flame [J]. Journal of Jishou University（Natural Sciences Edition), 2016, 37(3): 42-46.
[3]	HUANG Wei. Mean-Value Estimate for Two Smarandache Hybrid Functions [J]. Journal of Jishou University（Natural Sciences Edition), 2016, 37(3): 1-3.
[4]	SHU Ting, DENG Bo, CHEN Bing-Quan, LIU Yao-Feng. Defogging Algorithm Based on the Prior Dark-Channel and Theory of Retinex [J]. journal6, 2014, 35(2): 52-56.
[5]	HUANG Wei, MA Yan. Mean Value of Divisor Function for Smarandache k-Power Complements [J]. journal6, 2013, 34(5): 3-5.
[6]	HUANG Wei. On the Mean Value of Generalized Smarandache Summands Function [J]. journal6, 2012, 33(2): 7-9.
[7]	HUANG Wei. Smarandache Involving Function and Its Asymptotic Formula [J]. journal6, 2011, 32(5): 9-10.
[8]	HUANG Wei. k-th Root Sequence Average Value Asymptotic Formula [J]. journal6, 2010, 31(4): 8-9.
[9]	LIU Wen-Wu. A Register Upon the Asymptoticity of the Intermediate Point in the Mean Value Theorem of Integrals [J]. journal6, 2007, 28(4): 24-26.
[10]	GAO Li. The Distribution of the Even Power Weighted Mean of Dirichlet L-Functions [J]. journal6, 2006, 27(5): 1-3.
[11]	LIU Chang-Mao. Asymptoticity of the Intermediate Point in the Mean Value Theorem of Integrals [J]. journal6, 2006, 27(3): 8-11.
[12]	SUN Jian-Zhu, JI Hai-Jun. A Simplified Method for Deriving the Explicit Runge-Kutta’s Formula [J]. journal6, 2005, 26(4): 10-11.
[13]	GAO Li, Zhao-Zhen. On the Second Power Mean of Dirichlet L-function [J]. journal6, 2004, 25(3): 6-9.
[14]	GAO Li. On the Even Power Mean of the Inversion of Dirichlet L- Functions With the Weight of Gauss Sums [J]. journal6, 2004, 25(1): 48-51.
[15]	GAO Li, ZHAO Zhen. On the 2k-th Power Mean of the Inversion of DirichletL-Function With the Weight of Gauss Sums [J]. journal6, 2003, 24(2): 43-46.