Abstract
Compared with the traditional Retinex model, the robust Retinex model considers the influence of additive Gaussian noise to improve the performance of low-light image enhancement with strong noise. However, the real noise model is not so simple. In order to describe the noise model more accurately, this paper considers the enhancement of low-light images under the influence of Poisson and Gaussian mixture noise, so as to better model the noise model and suppress the noise amplification. In order to smooth the noise in the reflection component, the current methods generally decompose the V-channel of the image converted to HSV color space to obtain the illuminance component and the reflection component, and then constrain the reflection component a priori such as sparse, low rank or nonlocal self-similarity based on matrix or vector operations. The problem is that the conversion of color space may lead to color distortion, and the matrix operation and vectorization operation by channel may damage the structural relationship of channel and space respectively, and may occupy a high memory. In order to better maintain the correlation between RGB image channels, the RGB image is directly represented in the form of tensor, processed in the RGB color space as a whole, and the tensor nuclear norm is used to impose a low rank constraint on the reflection component to suppress the noise. Compared with the contrast method, the proposed method achieves good visual and quantitative results in low-light image enhancement tasks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Land, E.H.: The retinex theory of color vision. Sci. Amer. 237(6), 108–128 (1977)
Barrow, H., Tenenbaum, J., Hanson, A., Riseman, E.: Recovering intrinsic scene characteristics. Comput. Vis. Syst. 2, 3–26 (1978)
Cai, B., Xu, X., Guo, K., Jia, K., Hu, B., Tao, D.: A joint intrinsic extrinsic prior model for retinex. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), October 2017, pp. 4000–4009 (2017)
Ren, X., Li, M., Cheng, W.-H., Liu, J.: Joint enhancement and denoising method via sequential decomposition. In: IEEE International Symposium on Circuits and Systems (ISCAS) 2018, pp. 1–5 (2018)
Jobson, D.J., Rahman, Z., Woodell, G.A.: A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Trans. Image Process. 6(7), 965–976 (1997)
Jobson, D.J., Rahman, Z., Woodell, G.A.: Properties and performance of a center/surround retinex. IEEE Trans. Image Process. 6(3), 451–462 (1997)
Morel, J.M., Petro, A.B., Sbert, C.: A PDE formalization of retinex theory. IEEE Trans. Image Process. 19(11), 2825–2837 (2010)
Land, E.H.: Recent advances in retinex theory and some implications for cortical computations: Color vision and the natural image. Proc. Nat. Acad. Sci. USA 80(16), 5163–5169 (1983)
Brainard, D.H., Wandell, B.A.: Analysis of the retinex theory of color vision. J. Opt. Soc. Am. A. Opt. Image. Sci. 3(10), 1651–1661 (1986)
Kimmel, R., Elad, M., Shaked, D., Keshet, R., Sobel, I.: A variational framework for Retinex. Int. J. Comput. Vis. 52(1), 7–23 (2003)
Provenzi, E., Marini, D., De Carli, L., Rizzi, A.: Mathematical definition and analysis of the retinex algorithm. J. Opt. Soc. Am. A. Opt. Image. Sci. 22(12), 2613–2621 (2005)
Ng, M.K., Wang, W.: A total variation model for retinex. SIAM J. Imag. Sci. 4(1), 345–365 (2011)
Fu, X., Zeng, Huang, Y., Zhang, X.-P., Ding, X.: A weighted variational model for simultaneous reflectance and illuminance estimation. In: Proceedings of IEEE Conference on Computational Vision and Pattern Recognition (CVPR), June 2016
Xu, J., et al.: STAR: a structure and texture aware retinex model. IEEE Trans. Image Process. 29, 5022–5037 (2020)
Kolda, T.: Tensor decompositions and applications. Siam. Rev. 51, 455–500 (2009)
Peng, J., Xie, Q., Zhao, Q., Wang, Y., Yee, L., Meng, D.: Enhanced 3DTV regularization and its applications on HSI denoising and compressed sensing. IEEE Trans. Image Process. 29, 7889–7903 (2020). https://doi.org/10.1109/TIP.2020.3007840
Guo, X.: LIME: a method for low-light image enhancement. In: ACM (2016)
He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. IEEE Trans. Pattern Anal. Mach. Intell. 33(12), 2341–2353 (2011)
Land, E.: The retinex theory of color vision. Sci. Am. 237(6), 108–128 (1977)
Xu, L., Lu, C., Xu, Y., et al.: Image smoothing via L0 gradient minimization. In: SIGGRAPH Asia Conference. ACM (2011)
Li, M., Liu, J., Yang, W., Sun, X., Guo, Z.: Structure-revealing lowlight image enhancement via robust retinex model. IEEE Trans. Image Process. 27(6), 2828–2841 (2018)
Candes, E.J., Wakin, M.B., Boyd, S.P.: Enhancing sparsity by reweighted L1 minimization. J. Fourier Anal. Appl. 14(5–6), 877–905 (2008)
Barrett, R., et al.: Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods. SIAM (1994)
Kilmer, M.E., Martin, C.D.: Factorization strategies for third-order tensors. Linear Algebra Appl. 435(3), 641–658 (2011)
Lin, Z., Chen, M., Ma, Y.: The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices. arXiv:1009.5055
Kilmer, M.E., Braman, K., Hao, N., Hoover, R.C.: Third-order tensors as operators on matrices: a theoretical and computational framework with applications in imaging. SIAM J. Matrix Anal. App. 34(1), 148–172 (2013)
Fu, X., Liao, Y., Zeng, D., Huang, Y., Zhang, X.-P., Ding, X.: A probabilistic method for image enhancement with simultaneous illuminance and reflectance estimation. IEEE Trans. Image Process. 24(12), 4965–4977 (2015)
Mittal, A., Soundararajan, R., Bovik, A.C.: Making a ‘completely blind’ image quality analyzer. IEEE Signal Process. Lett. 20(3), 209–212 (2013)
Sheikh, H.R., Bovik, A.C.: Image information and visual quality. IEEE Trans. Image Process. 15(2), 430–444 (2006)
Wang, S., Zheng, J., Hu, H.-M., Li, B.: Naturalness preserved enhancement algorithm for non-uniform illuminance images. IEEE Trans. Image Process. 22(9), 3538–3548 (2013)
Lu, C., Feng, J., Chen, Y., Liu, W., Lin, Z., Yan, S.: Tensor Robust Principal Component Analysis with a New Tensor Nuclear Norm. IEEE Trans. Pattern Anal. Mach. Intell. 42(4), 925–938 (2020)
Ma, K., Zeng, K., Wang, Z.: Perceptual quality assessment for multi-exposure image fusion. IEEE Trans. Image Process. 24(11), 3345–3356 (2015)
Acknowledgments
This work was supported by the Guangdong Province Basic and Applied Basic Research Fund Project under Grant 2019A1515011041, Science and Technology Project of Guangzhou under Grant 202103010003, Science and Technology Project in key areas of Foshan under Grant 2020001006285, Xijiang Innovation Team of Zhaoqing under Grant XJCXTD3-2019-04B.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yang, W., Gao, H., Huang, S., Niu, S., Chen, H., Liang, G. (2022). Low-Light Image Enhancement Under Mixed Noise Model with Tensor Representation. In: Fang, L., Povey, D., Zhai, G., Mei, T., Wang, R. (eds) Artificial Intelligence. CICAI 2022. Lecture Notes in Computer Science(), vol 13604. Springer, Cham. https://doi.org/10.1007/978-3-031-20497-5_48
Download citation
DOI: https://doi.org/10.1007/978-3-031-20497-5_48
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20496-8
Online ISBN: 978-3-031-20497-5
eBook Packages: Computer ScienceComputer Science (R0)