Missioncritical monitoring based on surround suppression variational Retinex enhancement for nonuniform illumination images
 Zhitao Rao^{1},
 Tingfa Xu^{1}Email author and
 Hongqing Wang^{1}
https://doi.org/10.1186/s1363801708729
© The Author(s). 2017
Received: 30 March 2017
Accepted: 27 April 2017
Published: 15 May 2017
Abstract
In this letter, a surround suppression variational Retinex enhancement algorithm (SSVR) is proposed for nonuniform illumination images. Instead of a gradient module, a surround suppression mechanism is used to provide spatial information in order to constrain the total variation regularization strength of the illumination and reflectance. The proposed strategy preserves the boundary areas in the illumination so that halo artifacts are prevented. It also preserves textural details in the reflectance to prevent from illumination compression, which further contributes to the contrast enhancement in the resulting image. In addition, strong regularization strength is enforced to eliminate uneven intensities in the homogeneous areas. The split Bregman optimization algorithm is employed to solve the proposed model. Finally, after decomposition, a contrast gain is added to reflectance for contrast enhancement, and a Laplacianbased gamma correction is added to illumination for prevent color cast. The recombination of the modified reflectance and illumination become the final result. Experimental results demonstrate that the proposed SSVR algorithm performs better than other methods.
Keywords
Image enhancement Surround suppression variational Retinex Nonuniform illumination images Split Bregman optimization Contrast gain Laplacianbased gamma correction1 Introduction
Image enhancement techniques have been widely used in various applications in the past few decades, including face recognition [1, 2], microimaging [3] and intelligent video surveillance system [4] etc.. The primary purpose of image enhancement is to improve the contrast or perception of an image without losing details or introducing novel artifacts. In generally, many classical enhancement methods have been proposed, including sigmoid based algorithms [5], logarithmic domain algorithms [6], histogram equalization (HE) algorithms [7, 8], unsharp masking algorithms [9], and Retinex algorithms [10]. Sigmoid and logarithmic based methods are simple and effective for global brightness and contrast enhancement, but spatial information of images are not considered. HE algorithm is simple and widely used. But it is limited for the uneven illumination images, especially for dark areas. For unsharp masking algorithms, images are decomposed into highfrequency and lowfrequency terms, which are processed respectively. Result images by this method well preserve details, but introduce unnatural looking.
Amongst the various enhancement methods, Retinex has received much attention due to its simplicity and effectiveness in enhancing nonuniform illumination images [11]. Land and McCann first proposed Retinex algorithm, which is a model of color and luminance perception of human visual system (HVS). To simulate the mechanism of HVS, it is an illposed problem that computes illumination or reflectance from a single observed image. To overcome this problem, many modified Retinex theories have been proposed. Retinex algorithms are basically categorized into pathbased methods [12–14], center/surroundbased methods [15–18], recursive methods [19–21], PDEbased methods [22–24], and variational methods [11, 25–30]. Pathbased Retinex methods are the simplest, but they usually necessitate high computational complexity. For the center/surroundbased methods, Gaussian filtering is usually used as a low pass filter to estimate the illumination. In order to get better performance for RGB images, Jobson et al. had put forward multiscale Retinex (MSR) [16, 17] algorithm and color restored multiscale Retinex (CRMSR) [18] algorithm. These algorithms are easy to implement but too many parameters need to be manually set. Large numbers of iterations lower recursive methods’ efficiency. In 1974, Horn introduced partial differential equation (PDE) as a novel mathematical model to the Retinex algorithm [22]. PDEbased methods are usually based on the assumption that the illumination varies smoothly, while the reflectance changes at sharp edges. So, reflectance component can be estimated by solving Poisson equation. In 2010, Morel proposed a new PDEbased Retinex method that computed the divergence by thresholding the components of the gradient prior instead of the scalar Laplacian operator [23]. However, the hard thresholding operator in PDEbased Retinex will cause extra artifacts when solving the Poisson equations. In [24], Zosso presented a unifying framework for Retinex in which existing Retinex algorithms can be represented within a single model. He defined Retinex model in more general two steps: first, looking for a filtered gradient to solve the optimazation problem consisting of sparsity prior and quadratic fidelity prior of the reflectance; second, finding a reflectance whose actual gradient comes close. Based on the same assumption of PDE, a variational framework for the Retinex algorithm has been proposed. In 2003, Kimmel indicated that the illumination estimation problem can be formulated as a quadratic programming optimization problem [25]. M. Ng et al. [26] proposed a total variational model for Retinex in which both illumination and reflectance components are considered. X. Lan et al. [28] introduced the concept of spatial information for the uneven intensity correction. Different regularization strength of the reflectance is enforced to get more accurate results for nonuniform illumination images. And the split Bregman algorithm is employed to solve the proposed adaptive Retinex variational model. In 2014, L. Wang et al. [11] proposed variational bayesian model for Retinex by combining the variational Retinex and Beyesian theory. Due to the shortage of the traditional variational method on limiting the scope of reflectance and illumination components, Wei Wang [30] proposed a variational model with barrier functionals for Retinex. They built a new energy function by adding two barriers for getting a better output.
In this paper, a novel image enhancement algorithm for nonuniform illumination images is proposed. First, the variational Retinex model estimates the reflectance and illumination components simultaneously. A surround suppression mechanism, which is a human visual property, is used to constrain the TV regularization strength of both reflectance and illumination. Moreover, the Split Bregman algorithm is used to solve the proposed variational model. Second, after decomposition, a contrast gain is added to reflectance for contrast enhancement, and a Laplacianbased gamma correction is added to illumination for prevent color cast. The recombination of the modified reflectance and illumination become the final result.
The remainder of this paper is organized as follows. The Retinex theory and the proposed SSVR algorithm are introduced in Section 2. Experimental results and comparison of SSVR with other methods are devoted in Section 3. Finally, Section 4 concludes the paper.
2 The proposed algorithm
2.1 Retinex theory
Recently, more and more attention has been paid to color image processing. However, general enhancement algorithms process the image in greyscale values that do not consider the color information. Retinex methods have been proposed for color images based on human visual system (HVS).
where s = log(S), l = log(L), r = log(R). The Retinex obtains the reflectance component channel by channel [6].
2.2 A spatially adaptive retinex variational model
However, directly applying equation (3–4) cannot effectively obtain the expected reflectance and illumination. The reason for this is that the criterion for selective smoothing depends on the gradient module, which is unable to fully demarcate between texture edges and boundary edges in real scenes. Some of the textures could have higher gradients than some boundaries and, hence, weaker diffusivities. In this paper, we propose a novel adaptive Retinex variational model. Instead of the gradient module, a surround suppression mechanism, which is a human visual property, is introduced to achieve this goal. The proposed strategy preserves the boundary areas in the illumination so that halo artifacts are prevented. It also preserves textural details in the reflectance to prevent from illumination compression, which further contributes to the contrast enhancement in the resulting image. In addition, strong regularization strength is enforced to eliminate uneven intensities in the homogeneous areas. The split Bregman optimization algorithm was employed to solve the proposed model.
2.3 Surround suppression mechanism

First, a weighting function ω _{ σ } is defined as follows:

Then, the suppression term t (x, y) for each pixel is calculated by convolving the gradient module with the weighting function ω _{ σ }(x, y):

Finally, we define the suppressed gradient value B(x, y) and T(x, y) as follows:
In equations (9–10), suppression term t(x, y) is small for the boundary edges and large for the texture edges. Here, α _{ t } is the suppression strength factor, which directly influences the suppression effect. B(x, y) can successfully assign high values in the boundary areas, T(x, y) assigns high values in the texture areas. So, B(x, y) and T(x, y) are regarded as boundary and texture templates, respectively.
2.4 Surround suppression variational retinex model
2.5 Split Bregman algorithm for the proposed model
3 Algorithm 1
Step 1: Initialize \( {u}^0=0,\ j=0,\ \mathrm{and}\ {b}_1^0=\left({b}_{1 h}^0,{b}_{1 v}^0\right)=0, \) where “h” and “v” stands for the horizontal axis and the vertical axis, respectively.
Step 3: If (‖u ^{ j + 1} − u ^{ j }‖/‖u ^{ j + 1}‖) ≤ ε _{ u }, r ^{ i + 1/2} = u ^{ j + 1}, r ^{ i + 1} = min(r ^{ i + 1/2}, 0); otherwise, go to Step 2.
where λ is a nonnegative parameter, and b _{2} is the Bregman parameter. The computation procedure is detailed in Algorithm 2.
4 Algorithm 2
Step 1: Initialize \( {w}^0=0,\ j=0,\ \mathrm{and}\ {b}_2^0=\left({b}_{2 h}^0,{b}_{2 v}^0\right)=0, \) where “h” and “v” stand for the horizontal axis and the vertical axis, respectively.
Step 3: If (‖w ^{ j + 1} − w ^{ j }‖/‖w ^{ j + 1}‖) ≤ ε _{ w }, l ^{ i + 1/2} = w ^{ j + 1}, l ^{ i + 1} = max(l ^{ i + 1/2}, s); otherwise, go to Step 2.
 1.
Given that the input image s, initialize l ^{0} = s. For i = 0, 1, 2,……
 2.
Given l ^{ i }, solve the subproblem (14) to get r ^{ i + 1/2} by using Algorithm 1. Then, update r ^{ i + 1} by r ^{ i + 1} = min(r ^{ i + 1/2}, 0)
 3.
Go back to (2) until (‖r ^{ j + 1} − r ^{ j }‖/‖r ^{ j + 1}‖) ≤ ε _{ r } and (‖l ^{ j + 1} − l ^{ j }‖/‖l ^{ j + 1}‖) ≤ ε _{ l } are satisfied.
4.1 Contrast gain and gamma correction
Most Retinex based enhancement algorithms estimate the reflectance component as the final result. However, reflectance should be within [0~1], which means that it cannot completely contains the whole information of input image. Moreover, illumination component represents ambience information [35, 36].
In this step, input image is first divided into nonoverlapping 12*12 subblocks. σ(x, y) is corresponding variance within current subblock, σ _{max} is maximum variance of all subblocks. R _{max} is maximum pixel value. λ is an adjusted parameter which is set 0.1 empirically.
5 Experimental results and evaluation
5.1 Subjective assessment
5.2 Objective assessment
6 Conclusions
This paper proposes a surround suppression variational Retinex enhancement algorithm for image enhancement of nonuniform illumination images, which not only enhances the contrast of the image but also preserves the color constancy. Surround suppression mechanism, which performs well in accordance with constraining the TV regularization strength of the reflectance and illumination. Moreover, in order to prevent light flickering caused by varying apparently scenes, a Laplacianbased gamma correction is conducted on the estimated illumination, which contributes to the color constancy preservation in the output image result. Experimental results demonstrate that the proposed algorithm is better than the existing algorithms.
Declarations
Acknowledgements
The authors would like to thank Image Engineering andVideo Technology Lab for the support.
Funding
This work was supported by the Major Science Instrument Program of the National Natural Science Foundation of China under Grant 61527802, the General Program of National Nature Science Foundationof China under Grants 61371132, and 61471043, and the International S&T Cooperation Program of China under Grants 2014DFR10960.
Authors’ contributions
ZR and TX came up with the algorithm and improved the algorithm. In addition, ZR wrote and revised the paper. HW implemented the algorithm of LHE, AL, and ALTM for image enhancement and recorded the data. All authors read and approved the final manuscript.
Competing interests
The authors declare that they have no competing interests.
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
Authors’ Affiliations
References
 L Tao, Tompkins R, Asari V K. An illuminancereflectance model for nonlinear enhancement of color images[C]//, 2005, p. 159Google Scholar
 T Celik, T Tjahjadi, Contextual and variational contrast enhancement.[J]. IEEE Trans Image Process A Publication of the IEEE Signal Processing Soc 20(12), 3431–3441 (2011)MathSciNetView ArticleGoogle Scholar
 Y Lu, F Xie, Y Wu et al., No reference uneven illumination assessment for dermoscopy images[J]. Signal Process Letters IEEE 22(5), 534–538 (2015)View ArticleGoogle Scholar
 J. Tao, Y. Pingxian, G. Peng, et al. An enhancement algorithm for video surveillance image based on multiscale Retinex[C]// International Conference on Computational and Information Sciences. IEEE Comput Soc, 2225 (2011)Google Scholar
 C Wen, J Lee, Y Liao, Adaptive quartile sigmoid function operator for color image contrast enhancement color and imaging conference. Soc Imaging Sci Tech 2001, 280–285 (2001)Google Scholar
 F. Drago, K. Myszkowski, T. Annen. Adaptive logarithmic mapping for displaying high contrast scenes. Computer Graphics Forum. Blackwell Publishing, Inc, 2003, 22, 419426.Google Scholar
 TK Kim, JK Paik, BS Kang, Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering. IEEE Trans Consum Electron 44, 82–87 (1998)View ArticleGoogle Scholar
 CC Ting, BF Wu, ML Chung et al., Visual contrast enhancement algorithm based on histogram equalization. Sensors 15, 16981–16999 (2015)View ArticleGoogle Scholar
 G Deng, A generalized unsharp masking algorithm. IEEE Trans Image Process 20, 1249–1261 (2011)MathSciNetView ArticleGoogle Scholar
 E Land, J Mccann, Lightness and Retinex theory. J Opt Soc Am 61, 1–11 (1971)View ArticleGoogle Scholar
 L Wang, L Xiao, H Liu, Z Wei, Variational Bayesian method for retinex. IEEE Trans Image Process 23, 3381–3396 (2014)MathSciNetView ArticleGoogle Scholar
 E Provenzi, LD Carli, A Rizzi, D Marini, Mathematical definition and analysis of the retinex algorithm. J Opt Soc Amer A 22, 2613–2621 (2005)MathSciNetView ArticleGoogle Scholar
 E Provenzi, M Fierro, A Rizzi, LD Carli, D Gadia, D Marini, Random spray retinex: a new retinex implementation to investigate the local properties of the model. IEEE Trans Image Process 16, 162–171 (2007)MathSciNetView ArticleGoogle Scholar
 G Gianini, A Rizzi, E Damiani, A Retinex model based on absorbing Markov chains. Inf Sci 327, 149–174 (2015)MathSciNetView ArticleGoogle Scholar
 DJ Jobson, Z Rahman, GA Woodell, Properties and performance of the center/surround retinex. IEEE Trans Image Process 6, 451–462 (1997)View ArticleGoogle Scholar
 Z Rahman, DJ Jobson, GA Woodell, Multiscale retinex for color image enhancement, in Proc. ICIP, 1996, pp. 1003–1006Google Scholar
 ZU Rahman, DJ Jobson, GA Woodell, Retinex processing for automatic image enhancement. J Electron Imag 13, 100–110 (2004)View ArticleGoogle Scholar
 ZU Rahman, DJ Jobson, GA Woodell, Investigating the relationship between image enhancement and image compression in the context of the multiscale retinex. J Vis Commun Image Represent 22, 237–250 (2011)View ArticleGoogle Scholar
 J Frankle, J McCann, Method and apparatus for lightness imaging. U.S. Patent 4 384 336, 1983, p. 17Google Scholar
 JJ McCann, Lessons learned from Mondrians applied to real images and color gamuts, in Proc. 7th Color Imag. Conf, 1999, pp. 1–8Google Scholar
 B Funt, F Ciurea, J McCann, Retinex in MATLAB^{TM}. J Electron Imag 13, 48–57 (2004)View ArticleGoogle Scholar
 K Horn, Determining lightness from an image. Comput Graphics Image Process 3, 277–299 (1974)View ArticleGoogle Scholar
 JM Morel, AB Petro, C Sbert, A PDE formalization of retinex theory. IEEE Trans Image Process 19, 2825–2837 (2010)MathSciNetView ArticleGoogle Scholar
 D Zosso, A unifying retinex model based on nonlocal differential operators. IS&T/SPIE Electronic Imaging. Int Soc Optics Photonics 8657, 865702–865702 (2013)Google Scholar
 R Kimmel, M Elad, D Shaked, R Keshet, I Sobel, A variational framework for retinex. Int J Comput Vis 52, 7–23 (2003)View ArticleMATHGoogle Scholar
 MK Ng, W Wang, A total variation model for retinex. SIAM J Imag Sci 4, 345–365 (2011)MathSciNetView ArticleMATHGoogle Scholar
 Y Lu, F Xie, Y Wu, No reference uneven illumination assessment for dermoscopy images. IEEE Signal Processing Letters 22, 534–538 (2015)View ArticleGoogle Scholar
 X Lan, H Shen, L Zhang, A spatially adaptive retinex variational model for the uneven intensity correction of remote sensing images. Signal Process 101, 19–34 (2014)View ArticleGoogle Scholar
 H Li, L Zhang, H Shen, A perceptually inspired variational method for the uneven intensity correction of remote sensing images. IEEE Trans Geosci Remote Sens 50, 3053–3065 (2012)View ArticleGoogle Scholar
 W Wang, C He, A Variational model with barrier functionals for Retinex. Siam Journal on Imaging Sciences 8, 1955–1980 (2015)MathSciNetView ArticleMATHGoogle Scholar
 G Papari, P Campisi, A Neri, A multiscale approach to contour detection by texture suppression. Proceedings of SPIE  The International Society for Optical Engineering 6064, 60640D–60640D12 (2006)Google Scholar
 C Grigorescu, N Petkov, MA Westenberg, Contour and boundary detection improved by surround suppression of texture edges. Image & Vision Computing 22, 609–622 (2004)View ArticleGoogle Scholar
 C Tsiotsios, M Petrou, On the choice of the parameters for anisotropic diffusion in image processing. Pattern Recogn 46, 1369–1381 (2013)View ArticleGoogle Scholar
 T Goldstein, S Osher, The split Bregman method for L1regularized problems. Siam Journal on Imaging Sciences 2, 323–343 (2009)MathSciNetView ArticleMATHGoogle Scholar
 B. Li, S. Wang, Y. Geng. Image enhancement based on Retinex and lightness decomposition. IEEE Int Conf Image Process, 34173420 (2011)Google Scholar
 S Wang, J Zheng, HM Hu, Naturalness preserved enhancement algorithm for nonuniform illumination images. IEEE Trans Image Process 22, 3538–48 (2013)View ArticleGoogle Scholar
 H Ahn, B Keum, D Kim, Adaptive local tone mapping based on retinex for high dynamic range images. Consumer Electronics (ICCE), 2013 IEEE International Conference on, 2013, pp. 153–156Google Scholar
 C ChungCheng, T ChihChung, Contrast enhancement algorithm based on gap adjustment for histogram equalization. Sensors 16, 936 (2016)View ArticleGoogle Scholar
 C Ting, B Wu, M Chung, C Chiu, Y Wu, Visual contrast enhancement algorithm based on histogram equalization. Sensors 15, 16981–16999 (2015)View ArticleGoogle Scholar