基于RetinexNet红外图像增强算法的优化
Optimization of Infrared Image Enhancement Algorithm Based on RetinexNet
DOI: 10.12677/CSA.2022.1212284, PDF,    国家自然科学基金支持
作者: 卢 磊*, 倪 林#：东华大学信息与科学技术学院，数字化纺织服装技术教育部工程研究中心，上海
关键词: 红外图像；RetinexNet算法；注意力机制；循环残差结构；U-Net；Infrared Image； RetinexNet Algorithm； Attention Mechanism； Cyclic Residual Structure； U-Net
摘要: 针对红外图像信噪比低，对比度不足的问题，本文旨在红外图像增强，在对已有的比较流行的图像增强技术的研究的基础上，提出了引入无参数的注意力机制模块(SimAM)和使用加入循环残差结构(RRB)的U-Net代替的原始RetinexNet增强网络的图像增强算法。首先，通过在分解网络部分引入注意力机制提高空间特征提取能力，得到图像的光照分量和反射分量。其次，将光照分量和反射分量送入加入循环残差结构的U-Net增强网络，得到增强后的光照分量。最后，将增强后的光照分量和去噪后的反射分量相乘输出增强的红外图像。实验结果表明，与传统Retinex算法和原始RetinexNet算法相比，该算法能够有效提高对比度，丰富图像细节纹理，提高了红外图像的质量。
Abstract: Aiming at the problems of low signal-to-noise ratio and insufficient contrast of infrared image, this paper aims at infrared image enhancement. On the basis of the research on the existing popular image enhancement technologies, an image enhancement algorithm is proposed, which introduces a parameterless attention mechanism module (SimAM) and uses U-Net with a cyclic residual structure (RRB) to replace the original RetinexNet enhancement network. Firstly, the attention mechanism is introduced into the decomposition network to improve the spatial feature extraction ability, and the illumination component and reflection component of the image are obtained. Secondly, the light component and reflection component are fed into the U-Net enhancement network with cyclic residual structure to obtain the enhanced light component. Finally, the enhanced infrared image is output by multiplying the enhanced illumination component and the denoised reflection component. The experimental results show that compared with the traditional Retinex algorithm and the original RetinexNet algorithm, this algorithm can effectively improve the contrast, enrich the image details and texture, and improve the quality of infrared images.
文章引用：卢磊, 倪林. 基于RetinexNet红外图像增强算法的优化[J]. 计算机科学与应用, 2022, 12(12): 2795-2803. https://doi.org/10.12677/CSA.2022.1212284

参考文献

[1] 万智萍. 结合视觉特性与灰度拉伸的直方图均衡化红外图像算法[J]. 计算机工程与设计, 2016, 37(3): 714-719. [Google Scholar] [CrossRef] 
[2] Li, S., Jin, W.Q., Li, L. and Li, Y.Y. (2018) An Improved Contrast Enhancement Algorithm for Infrared Images Based on Adaptive Double Plateaus Histogram Equalization. Infrared Physics and Technology, 90, 164-174. [Google Scholar] [CrossRef] 
[3] 贾亚雯. 自适应裁剪直方图分段均衡化图像增强[D]: [硕士学位论文]. 西安: 西安邮电大学, 2021.[CrossRef] 
[4] Wang, Z.J., Luo, Y.Y., Jiang, S.Z., et al. (2020) Improved Adaptive Infrared Image Enhancement Algorithm Based on Guided Filtering. Spectroscopy and Spectral Analysis, 40, 3463-3467.
[5] 梁栋, 顾杰宁, 张陈, 王胜. 基于小波变换的红外热成像图像处理的无损检测技术[J]. 物联网技术, 2020, 10(3): 37-39. [Google Scholar] [CrossRef] 
[6] Land, E.H. (1977) The Retinex Theory of Color Vision. Scientific American, 237, 108-128. [Google Scholar] [CrossRef] [PubMed]
[7] Choi, Y., Kim, N., Hwang, S. and Kweon, I.S. (2016) Thermal Image Enhancement Using Convolutional Neural Network. 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, 9-14 October 2016, 223-230. [Google Scholar] [CrossRef] 
[8] Kuang, X.D., Sui, X.B., Liu, Y., Chen, Q. and Gu, G.H. (2019) Single Infrared Image Enhancement Using a Deep Convolutional Neural Network. Neurocomputing, 332, 119-128. [Google Scholar] [CrossRef] 
[9] Lore, K.G., Akintayo, A. and Sarkar, S. (2017) LLNet: A Deep Autoencoder Approach to Natural Low-Light Image Enhancement. Pattern Recognition, 61, 650-662. [Google Scholar] [CrossRef] 
[10] Wei, C., Wang, W.J., Yang, W.H. and Liu, J.Y. (2018) Deep Retinex Decomposition for Low-Light Enhancement. arXiv: 1808.04560 [cs.CV].
https://arxiv.org/abs/1808.04560
[11] Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab, N., Hornegger, J., Wells, W. and Frangi, A., Eds., Medical Image Computing and Computer-MICCAI2015, Lecture Notes in Computer Science, Springer, Cham, Vol. 9351, 234-241. [Google Scholar] [CrossRef] 
[12] Li, M., Zhou, R.J. and Tian, Z.J. (2020) A Thermal In-frared Image Enhancement Method Based on Histogram. Infrared Technology, 42, 880-885. [Google Scholar] [CrossRef] 
[13] Liang, X.N., Tian, Y., Yan, S.Y., Wang, K., Guo, C.L. and Du, B.L. (2018) A Real-Time Infrared Image Enhancement Algorithm Based on Improved CLAHE. 2018 International Conference on Image and Video Processing, and Artificial Intelligence, Vol. 10836, Shanghai, 29 October 2018. [Google Scholar] [CrossRef] 
[14] 李佳, 李少娟, 段小虎, 姚远, 李骥阳, 王立志. 基于Retinex理论与概率非局部均值的红外图像增强方法[J]. 光子学报, 2020, 49(4): 187-196.