An Improved Retinex Method for Low Light Image Enhancement


  • Halaharvi Keerthi Dept. of Computer Science, Dayananda Sagar University, Bangalore, Karnataka, India
  • Sreepathi B. Head of the Department of Information Science, Rao Bahadur Y. Mahabaleswarappa Engineering College, Bellary, Karnataka, India


— low / dark light image, single scale retinex, surveillance system, multiscale retinex.


Enhancement of low-light image is difficult because it must account for not just brightness recovery but also more sophisticated concerns such as colour distortion and noise that are often hidden in dark. Increasing the brightness of a low-light image, even slightly, can make these artefacts more noticeable. Image enhancement in low-light circumstance from the surveillance system plays a very important role for the security purpose. This is an active research topic, where many algorithms are proposed for magnifying the intensity of dark images. To overcome this issue a unique end-to-end attention-guided technique based on retinex is proposed. Here many effective image enhancement methods are ground on retinex theory. Subsequently diverse algorithms are used such as single scale retinex (SSR), multiscale retinex (MSR), multiscale retinex with color restoration (MSRCR) models.  color space model is applied with retinex algorithm. To boost the quality and brightness of image; gamma correction with multiple values are used before applying Improved Multi Scale Retinex with CIELAB color (IMSRLab) on image. Extensive testing on standard LOL datasets demonstrates that our method is capable of delivering high fidelity enhancement outcomes for lowlight images, and that it outperforms existing state-of-the-art methods both statistically and visually. These findings were gleaned from comparisons of the two methods using the LOL datasets.


Download data is not yet available.


Land E H, Mccann J. Lightness And Retinex Theory. Journal Of Optical Society Of America, 1971, 61 (1) : 2032 -2040.

Jobson D J, Rahman Z, Woodell G A. Properties And Performance Of A Center/ Surround Retinex[J]. Ieee Transactions On Image Processing, 1997, 6 (3) : 451 - 462.

Rahman Zia2ur, Jobson D J, Woodell G A. Retinex Processing For Automatic Image Enhancement [J]. Journal Of Electronic Imaging, 2004, 13 (1) : 100 - 110.

Jobson D J, Rahman Z, Woodell Ga. A Multiscale Retinex For Bridging The Gap Between Color Image Sand The Human Observation Of Scenes[J]. Ieee Transactions Image Processing: Special Issue On Color Processing, 1997, 6 (7) : 965 - 976.

Rahman Z, Jobson D J, Woodell Ga. A Multiscale Retinex For Color Rendition And Dynamic Range Comp Ression [C] / / Sp Ie International Symposium On Op Tical Science, Engineering And Instrumentation. Bellingham, Wa: Society Of Photo2op Tical Instrumentation Engineers: Sp Ie, 1996, 2847: 183 - 191.

W. Y. Chen Wei, Wenjing Wang and J. Liu, “Deep retinex decomposition for low-light enhancement,” in British Machine Vision Conference. British Machine Vision Association, 2018.

Lee S. An Efficient Content-Based Image Enhancement In The Compressed Domain Using Retinex Theory[J]. IEEE Transaction On Circuits And Systems For Video Technology, 2007, 17 (2): 199 - 213.

S. Wang, J. Zheng, H.M. Hu, B. Li, “Naturalness preserved enhancement algorithm for non-uniform illumination images”, IEEE Transactions on Image Processing, 22 (2013), pp. 3538-3548.

X. Fu, D. Zeng, Y. Huang, Y. Liao, X. Ding, J. Paisley A fusion-based enhancing method for weakly illuminated images Signal Processing, 129 (2016), pp. 82-96.

K. He, J. Sun, and X. Tang, “Single image haze removal using dark channel prior,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 12, pp. 2341–2353, 2011.

X. Dong, G. Wang, Y. Pang et al., “Fast efficient algorithm for enhancement of low lighting video,” in Proceedings of the 2011 IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6, Barcelona, Spain, July 2011.

S. G. Narasimhan and S. K. Nayar, “Chromatic framework for vision in bad weather,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR '00), pp. 598–605, Hilton Head Island, SC, USA, June 2000.

L. Li, R. Wang, W. Wang, and W. Gao, “A low-light image enhancement method for both denoising and contrast enlarging,” in Proceedings of the IEEE International Conference on Image Processing, ICIP 2015, pp. 3730–3734, Canada, September 2015.

Y. Jiang, X. Gong, D. Liu, Y. Cheng, C. Fang, X. Shen, J. Yang, P. Zhou, and Z. Wang, “Enlightengan: Deep light enhancement without paired supervision,” IEEE Transactions on Image Processing, vol. 30, pp. 2340–2349, 2021.

R. Kimmel, M. Elad, D. Shaked, R. Keshet, And I. Sobel, “A Vibrational Framework for Retinex,” International Journal of Computer Vision, Vol. 52, No. 1, Pp. 7–23, 2003.

D. Zosso, G. Tran, And S. Osher, “A Unifying Retinex Model Based On Non-Local Differential Operators,” In Proceedings of the Computational Imaging Xi, Burlingame, Calif, USA, February 2013.

W. Ma and S. Osher, “A Tv Bregman Iterative Model of Retinex Theory,” Inverse Problems and Imaging, Vol. 6, No. 4, Pp. 697–708, 2012.

H. Wen, D. Bi, S. Ma, And L. He, “Variational Retinex Algorithm for Infrared Image Enhancement with Staircase Effect Suppression and Detail Enhancement,” Guangxue Xuebao/Acta Optica Sinica, Vol. 36, No. 9, 2016.

X. Fu, D. Zeng, Y. Huang, X.P. Zhang, X. Ding, “A weighted variational model for simultaneous reflectance and illumination estimation”, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016), pp. 2782-2790.

M. Li, J. Liu, W. Yang, X. Sun, Z. Guo, “Structure-revealing low-light image enhancement via robust retinex model”, IEEE Transactions on Image Processing, 27 (2018), pp. 2828-2841.

X. Guo, Y. Li, and H. Ling, “LIME: Low-light image enhancement via illumination map estimation,” IEEE Transactions on Image Processing, vol. 26, no. 2, pp. 982–993, Feb 2017.

M. Pizer, E.P. Amburn, J.D. Austin, R. Cromartie, A. Geselowitz, T. Greer, B. ter Haar Romeny, J.B. Zimmerman, K. Zuiderveld, “Adaptive histogram equalization and its variations

Computer Vision”, Graphics, and Image Processing, 39 (1987), pp. 355-368

C. Wang, Z. Ye, “Brightness preserving histogram equalization with maximum entropy: a variational perspective”, IEEE Transactions on Consumer Electronics, 51 (2005), pp. 1326-1334.

H. Ibrahim, N.S.P. Kong, “Brightness preserving dynamic histogram equalization for image contrast enhancement”, IEEE Transactions on Consumer Electronics, 53 (2007), pp. 1752-1758.

J.T. Lee, C. Lee, J.Y. Sim, C.S. Kim, “Depth-guided adaptive contrast enhancement using 2d histograms”, 2014 IEEE International Conference on Image Processing (ICIP), IEEE (2014), pp. 4527-4531.

Y. T. Kim, “Contrast enhancement using brightness preserving bi-histogram equalization,” IEEE Trans. Consum. Electron., vol. 43, no. 1, pp. 1–8, 1997.

Various types of low-light images. (a) and (e) cloudy; (b) uneven illumination; (c) and (d) night time; (f) daybreak and nightfall.




How to Cite

H. . Keerthi and S. B., “An Improved Retinex Method for Low Light Image Enhancement”, Int J Intell Syst Appl Eng, vol. 10, no. 1s, pp. 418–428, Oct. 2022.