基于Retinex模型的低光照图像增强算法研究
Research on Low-Light Image Enhancement Algorithm Based on Retinex Model
DOI: 10.12677/CSA.2022.124091, PDF,   
作者: 吕国亮, 罗 玉：广东工业大学，计算机学院，广东 广州
关键词: 低光照图像；Retinex；深度学习；图像增强；Low-Light Image； Retinex； Deep Learning； Image Enhancement
摘要: 在弱光或者逆光环境下，光学成像设备获取的图像不仅会导致视觉体验不佳，还可能造成可见度低、颜色失真和存在测量噪声的影响，降低视觉系统后续处理的性能。为了提高图像的可见度和视觉系统的性能，本文提出了一种基于Retinex模型的端对端的低光照图像增强算法。该算法改进了基于最大熵的Retinex模型，并采用自适应动态调整曲线增强该模型分解的光照图的对比度，并融合分解出的反射图得到最终的增强图像。该算法是非常轻量级的，训练时间仅需80 s。实验结果表明，该方法与现有代表性方法相比，在视觉效果和常用的四个客观图像评估指标上，均有很强的竞争优势。
Abstract: Images acquired from optical imaging devices in a low-light or back-lit environment usually lead to poor visual experience. The poor visual visibility and the attendant contrast or color distortion may degrade the performance of the subsequent vision processing. To enhance the visibility of low-light image and mitigate the degradation of vision systems, this paper proposes an end-to-end low-light image enhancement algorithm based on the Retinex model. The proposed algorithm improves the Retinex model based on maximum entropy, and uses adaptive dynamic adjustment curve to enhance the contrast of the illumination map decomposed by the model, and then merges the decomposed reflection map to obtain the final enhanced image. The network architecture of the proposed algorithm is very lightweight, and the training time only needs 80 seconds. Experimental results show that compared with the existing representative methods, this method has a strong competitive advantage in terms of visual effects and four commonly used objective image evaluation indicators.
文章引用：吕国亮, 罗玉. 基于Retinex模型的低光照图像增强算法研究[J]. 计算机科学与应用, 2022, 12(4): 895-903. https://doi.org/10.12677/CSA.2022.124091

参考文献

[1] Cai, J.X., Wang, R.H. and Huang, Y.Y. (2008) Application of Brightness Normalization in Image Processing. Journal of Guangdong University of Technology, 25, 65-68.
[2] Abdullah-Al-Wadud, M., Kabir, M.H., Dewan, M.A.A. and Chae, O. (2007) A dynamic Histogram Equalization for Image Contrast Enhancement. IEEE Transactions on Consumer Electronics, 53, 593-600. [Google Scholar] [CrossRef] 
[3] Guo, X.J., Li, Y. and Ling, H. (2016) LIME: Low-Light Image Enhancement via Illumination Map Estimation. IEEE Transactions on Image Processing, 26, 982-993. [Google Scholar] [CrossRef] 
[4] Fu, X.Y., Zeng, D.L., Huang, Y., Zhang, X.-P. and Ding, X. (2016) A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Vegas, 27-30 June 2016, 2782-2790. [Google Scholar] [CrossRef] 
[5] Zhang, X.D., Shen, P.Y., Luo, L.L., Zhang, L. and Song, J. (2012) Enhancement and Noise Reduction of Very Low Light Level Images. 21st International Conference on International Conference on Pattern Recognition, Tsukuba, 11-15 November 2012, 2034-2037.
[6] Jobson, D.J., Rahman, Z. and Woodell, G.A. (1997) A Multiscale Retinex for Bridging the Gap between Color Images and the Human Observation of Scenes. IEEE Transactions on Image Process, 6, 965-976. [Google Scholar] [CrossRef] [PubMed]
[7] Jobson, D.J., Rahman, Z. and Woodell, G.A. (1997) Properties and Per-formance of a Center/Surround Retinex. IEEE Transactions on Image Process, 6, 451-462. [Google Scholar] [CrossRef] [PubMed]
[8] Wang, S.H., Zheng, J., Hu, H.M. and Li, B. (2013) Naturalness Preserved Enhancement Algorithm for Non-Uniform Illumination Images. IEEE Transactions on Image Process, 22, 3538-3548. [Google Scholar] [CrossRef] 
[9] Zhang, K., Zuo, W.M., Chen, Y.J., Meng, D. and Zhang, L. (2017) Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. IEEE Transactions on Image Pro-cess, 26, 3142-3155. [Google Scholar] [CrossRef] 
[10] Qian, R., Tan, R.T., Yang, W.H., Su, J. and Liu, J. (2018) Atten-tive Generative Adversarial Network for Raindrop Removal from Asingle Image. 2018 IEEE/CVF Conference on Com-puter Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 2482-2491. [Google Scholar] [CrossRef] 
[11] Li, R.D., Pan, J.S., Li, Z.C. and Tang, J. (2018) Single Image Dehazing via Conditional Generative Adversarial Network. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018 8202-8211. [Google Scholar] [CrossRef] 
[12] Lore, K.G., Akintayo, A. and Sarkar, S. (2017) LLNet: A Deep Autoencoder Approach to Natural Low-Light Image En-hancement. Pattern Recognition, 61, 650-662. [Google Scholar] [CrossRef] 
[13] Wang, R.X., Zhang, Q., Fu, C.W., Shen, X., Zheng, W. -S. and Jia, J. (2019) Underexposed Photo Enhancement Using Deep Illumi-nation Estimation. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, 15-20 June 2019, 6842-6850. [Google Scholar] [CrossRef] 
[14] Jiang, Y.F., Gong, X.Y., Liu, D., Cheng, Y., Fang, C., Shen, X., et al. (2021) EnlightenGAN: Deep Light Enhancement without Paired Supervision. IEEE Transac-tions Image on Processing, 30, 2340-2349. [Google Scholar] [CrossRef] 
[15] Guo, C., Li, C.Y., Guo, J.C., Chen, C.L., Hou, J., Kwong, S., et al. (2020) Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement. 2020 IEEE/CVF Conference on Computer Vision Pattern Recognition, Seattle, 13-19 June 2020, 1777-2020. [Google Scholar] [CrossRef] 
[16] Zhang, Y., Di, X.G., Zhang, B. and Wang, C. (2020) Self-Supervised Image Enhancement Network: Training with Low Light Images Only. arXiv preprint arXiv:2002.11300.
[17] Yang, W.H., Wang, S.Q., Fang, Y.M., Wang, Y. and Liu, J. (2020) From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light image Enhancement. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, 13-19 June 2020, 3060-3069. [Google Scholar] [CrossRef] 
[18] Zhang, Y.H., Zhang, J.W. and Guo, X.J. (2019) Kindling the Darkness: A Practical Low-light Image Enhancer. Proceedings of the 27th ACM International Conference on Multi-media, Nice, 21-25 October 2019, 1632-1640. [Google Scholar] [CrossRef] 
[19] Chen, W., Wang, W.J., Yang, W.H. and Liu, J. (2018) Deep Reti-nex Decomposition for Low-Light Enhancement. arXiv preprint arXiv:1808.04560.
[20] Odena, A., Dumoulin, V. and Olah, C. (2016) Deconvolution and Checkerboard Artifacts. Distill, 1, Article No. e3. [Google Scholar] [CrossRef] 
[21] Wang, Z., Bovik, A.C., Sheikh H, R. and Simoncelli, E.P. (2004) Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Transactions on Image Process, 13, 600-612. [Google Scholar] [CrossRef] 
[22] Mittal, A., Soundararajan, R. and Bovik, A.C. (2013) Making a “Completely Blind” Image Quality Analyzer. IEEE Signal Process Letters, 20, 209-212. [Google Scholar] [CrossRef]