首页 > 论文 > 激光与光电子学进展 > 57卷 > 20期(pp:201022--1)

基于注意力机制和卷积神经网络的低照度图像增强

Low-Light Image Enhancement Based on Attention Mechanism and Convolutional Neural Networks

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为了提高低照度图像的清晰度和避免颜色失真,提出了基于注意力机制和卷积神经网络(CNN)的低照度图像增强算法,以改善图像质量。首先根据Retinex模型合成训练数据,将原始图像从RGB (red-green-blue)颜色空间变换到HSI (hue-saturation-intensity)颜色空间,然后结合注意力机制和CNN构建A-Unet模型以增强亮度分量,最后将图像从HSI颜色空间变换到RGB颜色空间,得到增强图像。实验结果表明,所提算法可以有效改善图像质量,提高图像的清晰度,避免颜色失真,在合成低照度图像和真实低照度图像的实验中均能取得较好的效果,主观和客观评价指标均优于对比算法。

Abstract

To improve the clarity of low-light images and avoid color distortion, a low-light image enhancement algorithm based on the attention mechanism and convolutional neural network (CNN) is proposed to improve image quality. First, the training data is synthesized based on the Retinex model, and the original image is transformed from RGB (red-green-blue) color space to HSI (hue-saturation-intensity) color space. Then, an A-Unet model is constructed to enhance the brightness component by combining the attention mechanism and CNN. Finally, the enhanced image is obtained by transforming images from the HSI color space to the RGB color space. Experimental results show that the proposed algorithm can effectively improve the image quality, improve the image clarity, and avoid the color distortion. Good results can be obtained in the experiments of synthesizing low-light images and real low-light images, and the subjective and objective evaluation indexes are better than that of the comparison algorithm.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP391

DOI:10.3788/LOP57.201022

所属栏目:图像处理

基金项目:国家自然科学基金;

收稿日期:2020-03-02

修改稿日期:2020-04-15

网络出版日期:2020-10-01

作者单位    点击查看

吴若有:上海海洋大学信息学院, 上海 201306
王德兴:上海海洋大学信息学院, 上海 201306
袁红春:上海海洋大学信息学院, 上海 201306

联系人作者:王德兴(dawang@shou.edu.cn); 袁红春(dawang@shou.edu.cn);

备注:国家自然科学基金;

【1】Li L H, Lun M Z, Lian J, et al. Convolutional neural network-based vehicle detection method [J]. Journal of Jilin University (Engineering and Technology Edition). 2017, 47(2): 384-391.
李琳辉, 伦梅智, 连静, 等. 基于卷积神经网络的道路车辆检测方法 [J]. 吉林大学学报: 工学版. 2017, 47(2): 384-391.

【2】Li Q Z, Liu Q. Adaptive enhancement algorithm for low illumination images based on wavelet transform [J]. Chinese Journal of Lasers. 2015, 42(2): 0209001.
李庆中, 刘清. 基于小波变换的低照度图像自适应增强算法 [J]. 中国激光. 2015, 42(2): 0209001.

【3】Celik T, Tjahjadi T. Contextual and variational contrast enhancement [J]. IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society. 2011, 20(12): 3431-3441.

【4】Lee C, Lee C, Kim C S. Contrast enhancement based on layered difference representation of 2D histograms [J]. IEEE Transactions on Image Processing. 2013, 22(12): 5372-5384.

【5】Dong X, Wang G, Pang Y, et al. Fast efficient algorithm for enhancement of low lighting video[C]∥2011 IEEE International Conference on Multimedia and Expo, July 11-15, 2011, Barcelona, Spain. New York: , 2011, 12301290.

【6】Li Y, Brown M S. Single image layer separation using relative smoothness[C]∥2014 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2014, Columbus, OH, USA. New York: , 2014, 2752-2759.

【7】Wang S H, Zheng J, Hu H M, et al. Naturalness preserved enhancement algorithm for non-uniform illumination images [J]. IEEE Transactions on Image Processing. 2013, 22(9): 3538-3548.

【8】Guo X J, Li Y, Ling H B. LIME: low-light image enhancement via illumination map estimation [J]. IEEE Transactions on Image Processing. 2017, 26(2): 982-993.

【9】Yue H J, Yang J Y, Sun X Y, et al. Contrast enhancement based on intrinsic image decomposition [J]. IEEE Transactions on Image Processing. 2017, 26(8): 3981-3994.

【10】Kang S B, Kapoor A, Lischinski D. Personalization of image enhancement[C]∥2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 13-18, 2010, San Francisco, CA, USA. New York: , 2010, 1799-1806.

【11】Song R X, Li D, Wang X C. Low illumination image enhancement algorithm based on HSI color space [J]. Journal of Graphics. 2017, 38(2): 217-223.
宋瑞霞, 李达, 王小春. 基于HSI颜色空间的低照度图像增强算法 [J]. 图学学报. 2017, 38(2): 217-223.

【12】Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM. 2017, 60(6): 84-90.

【13】Li S M, Lei G Q, Fan R. Depth map super-resolution reconstruction based on convolutional neural network [J]. Acta Optica Sinica. 2017, 37(12): 1210002.
李素梅, 雷国庆, 范如. 基于卷积神经网络的深度图超分辨率重建 [J]. 光学学报. 2017, 37(12): 1210002.

【14】Tao L, Zhu C, Xiang G, et al. LLCNN: , 2017, 17614346.

【15】Ma H Q, Ma S P, Xu Y L, et al. Low-light image enhancement based on deep convolutional neural network [J]. Acta Optica Sinica. 2019, 39(2): 0210004.
马红强, 马时平, 许悦雷, 等. 基于深度卷积神经网络的低照度图像增强 [J]. 光学学报. 2019, 39(2): 0210004.

【16】Woo S, Park J, Lee J Y, et al. CBAM: convolutional block attention module[M]. ∥Computer Vision - ECCV 2018. Cham: , 2018, 3-19.

【17】Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation[M]. ∥Lecture Notes in Computer Science: , 2015, 234-241.

【18】-08-23)[ 2020-03-02] . https: ∥arxiv. 2019, org/abs/1908: 08681.

【19】Zhang M R, Lucas J, Hinton G, 1 step back[EB/OL], et al. -12-03)[2020-03-02] . https: ∥arxiv. 2019, org/abs/1907: 08610.

【20】Lin T Y, Maire M, Belongie S, et al. -02-21)[2020-03-02] . https: ∥arxiv. 2015, org/abs/1405: 0312.

【21】Xue W F, Zhang L, Mou X Q, et al. Gradient magnitude similarity deviation: a highly efficient perceptual image quality index [J]. IEEE Transactions on Image Processing. 2014, 23(2): 684-695.

【22】Ying Z Q, Li G. -11-02)[2020-03-02] . https: ∥arxiv. 2017, org/abs/1711: 00591.

【23】Yeganeh H, Wang Z. Objective quality assessment of tone-mapped images [J]. IEEE Transactions on Image Processing. 2013, 22(2): 657-667.

【24】Mittal A, Soundararajan R, Bovik A C. Making a “completely blind” image quality analyzer [J]. IEEE Signal Processing Letters. 2013, 20(3): 209-212.

【25】Liu L X, Liu B, Huang H, et al. No-reference image quality assessment based on spatial and spectral entropies [J]. Signal Processing: Image Communication. 2014, 29(8): 856-863.

【26】Lee C, Lee C, Kim C S. Contrast enhancement based on layered difference representation[C]∥2012 19th IEEE International Conference on Image Processing. September 30-October 3, 2012, Orlando, FL, USA. New York: , 2012, 965-968.

【27】Ma K D, Zeng K, Wang Z. Perceptual quality assessment for multi-exposure image fusion [J]. IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society. 2015, 24(11): 3345-3356.

引用该论文

Wu Ruoyou,Wang Dexing,Yuan Hongchun. Low-Light Image Enhancement Based on Attention Mechanism and Convolutional Neural Networks[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201022

吴若有,王德兴,袁红春. 基于注意力机制和卷积神经网络的低照度图像增强[J]. 激光与光电子学进展, 2020, 57(20): 201022

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF