计算机科学 ›› 2022, Vol. 49 ›› Issue (1): 187-193.doi: 10.11896/jsjkx.210600090

• 计算机图形学&多媒体 • 上一篇    下一篇

基于低秩矩阵估计的暗光图像增强模型

王以涵, 郝世杰, 韩徐, 洪日昌   

  1. 合肥工业大学计算机与信息学院 合肥230601
  • 收稿日期:2021-06-09 修回日期:2021-09-10 出版日期:2022-01-15 发布日期:2022-01-18
  • 通讯作者: 郝世杰(hfut.hsj@gmail.com)
  • 作者简介:2020111042@mail.hfut.edu.cn
  • 基金资助:
    国家自然科学基金(61772171)

Low-light Image Enhancement Model with Low Rank Approximation

WANG Yi-han, HAO Shi-jie, HAN Xu, HONG Ri-chang   

  1. School of Computer Science and Information Engineering,Hefei University of Technology,Hefei 230601,China
  • Received:2021-06-09 Revised:2021-09-10 Online:2022-01-15 Published:2022-01-18
  • About author:WANG Yi-han,born in 1999,postgra-duate student.Her main research inte-rests include image processing and pattern recognition.
    HAO Shi-jie,born in 1983,Ph.D,asso-ciate professor,is a member of China Computer Federation.His main research interests include image proces-sing and pattern recognition.
  • Supported by:
    National Key R & D Program of China(2019YFC1521400),National Natural Science Foundation of China(61902229,61872294),International Science and Technology Cooperation Project of Shaanxi(2020KW-006) and Fundamental Research Funds for the Central Universities(GK202103084).

摘要: 在暗光或逆光拍照时,获得的图像常常出现过暗或光照分布不均的现象,导致图像视觉质量较差。基于Retinex模型的暗光增强模型能实现有效地光照增强。但此类暗光增强模型也存在一些问题,即待处理图像中暗光区域的可视度虽然得到了有效改善,但其中隐藏的噪声也被放大和凸显,依旧影响了增强结果的视觉质量。为解决这一问题,构建了基于低秩矩阵估计的暗光图像增强模型。首先,构建包含噪声项的Retinex模型并对其进行交替优化,将暗光图像分解为光照层I以及反射层R。在这一过程中,利用低秩矩阵估计实现了对R层的噪声抑制。其次,考虑到在去噪过程中产生的图像细节被模糊的问题,进一步利用光照层I作为导向图,来融合包含和不包含去噪效果的两种增强图像,实现兼顾噪声抑制和图像原有细节保持的效果。与多种类型的暗光增强方法进行对比,所提模型在直观视觉比较和客观量化指标比较方面均取得了较好的结果。

关键词: 暗光图像, Retinex模型, 低秩矩阵估计, 融合

Abstract: Due to the influence of low lightness,the images acquired at dim or backlight conditions tend to have poor visual quality.Retinex-based low-light enhancement models are effective in improving the scene lightness,but they are often limited in hand-ling the over-boosted image noise hidden in dark regions.To solve this issue,we propose a Retinex-based low-light enhancement model incorporating the low-rank matrix approximation.First,the input image is decomposed into an illumination layer I and a reflectance layer R according to the Retinex assumption.During this process,the image noise in R is suppressed via low-rank-based approximation.Then,aiming to preserve the image details in the bright regions and suppress the noise in the dark regions simultaneously,a post-fusion under the guidance of I is introduced.In experiments,qualitative and quantitative comparisons with other low-light enhancement models demonstrate the effectiveness of our method.

Key words: Low-light image, Retinex model, Low rank matrix approximation, Fusion

中图分类号: 

  • TP391
[1]LIU J Y,XU D J,YANG W H,et al.Benchmarking Low-Light Image Enhancement and Beyond[J].International Journal of Computer Vision,2021,129(4):1153-1184.
[2]REN X T,YANG W H,CHENG W H,et al.LR3M:RobustLow-Light Enhancement via Low-Rank Regularized Retinex Model[J].IEEE Transactions on Image Processing,2020,29:5862-5876.
[3]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.
[4]WEI C,WANG W,YANG W H,et al.Deep Retinex Decomposition for Low-Light Enhancement[C]//British Machine Vision Conference.British Machine Vision Association,2018.
[5]CHANG J,REN Y,HE C Z.Improved Multifocus Image Fusion Algorithm for Bilateral Filtering Retinex[J].Journal of Image and Graphics,2020,25(3):432-441.
[6]CHENG H D,SHI X J.A Simple and Effective Histo-gram Equalization Approach to Image Enhancement[J].Digital Signal Processing,2004,14(2):158-170.
[7]FU X Y,ZENG D L,HUANG Y,et al.A Fusion-Based Enhancing Method for Weakly Illuminated Images[J].Signal Proces-sing,2016,129(1):82-96.
[8]CAI B L,XU X M,GUO K L,et al.A Joint Intrinsic-Extrinsic Prior Model for Retinex[C]//2017 IEEE International Confe-rence on Computer Vision (ICCV).IEEE,2017:4020-4029.
[9]PAN W Q,TU J J,GAN Z L,et al.Low Light Images Enhancement Based on Retinex Adaptive Reflectance Estimation and LIPS Post-processing[J].Computer Science,2019,46(8):327-331.
[10]JIANG Z T,WU X,ZHANG S Q.Low-Illumination Image Enhancement Based on MR-VAE[J].Chinese Journal ofCompu-ters,2020,43(7):1328-1339.
[11]WANG W J,WEI C,YANG W H,et al.GLADNet:Low-Light Enhancement Network with Global Awareness[C]//2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018).IEEE,2018:751-755.
[12]JIANG Y F,GONG X Y,LIU D,et al.EnlightenGAN:Deep Light Enhancement Without Paired Supervision[J].IEEE Transactions on Image Processing,2021,30:2340-2349.
[13]GUO C L,LI C Y,GUO J C,et al.Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle:IEEE,2020:1777-1786.
[14]GU S H,XIE Q,MENG D Y,et al.Weighted Nuclear Norm Minimization and Its Applications to Low Level Vision[J].International Journal of Computer Vision,2017,121(1):183-208.
[15]XU L,ZHANG L,ZHANG D,et al.Multi-Channel Weighted Nuclear Norm Minimization for Real Color Image Denoising[C]//2017 IEEE International Conference on Computer Vision (ICCV).IEEE,2017:1105-1113.
[16]GU S H,ZHANG L,ZUO W M,et al.Weighted Nuclear Norm Minimization with Application to Image Denoising[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2014:2862-2869.
[17]LI X,QIONG Y,YANG X,et al.Structure Extraction fromTexture via Relative Total Variation[J].ACM Transactions on Graphics,2012,31(6):1-10.
[18]HE K M,SUN J,TANG X O.Single Image Haze RemovalUsing Dark Channel Prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(12):2341-2353.
[19]HE K M,SUN J,TANG X O.Guided Image Filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(6):1397-1409.
[20]BOYD S,PARIKH N,CHU E,et al.Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers[M].Now Publishers Inc,2011:1-122.
[21]MA K D,LI H,YONG H W,et al.Robust Multi-ExposureImage Fusion:A Structural Patch Decomposition Approach[J].IEEE Transactions on Image Processing,2017,26(5):2519-2532.
[22]LV F F,LU F,WU J H,et al.MBLLEN:Low-light Image/Vi-deo Enhancement Using CNNs[C]//British Machine Vision Conference.British Machine Vision Association,2018:220.
[23]WANG Y F,LIU H M,FU Z W.Low-Light Image Enhancement via the Absorption Light Scattering Model[J].IEEE Transactions on Image Processing,2019,28(11):5679-5690.
[24]WANG R X,ZHANG Q,FU C W,et al.Underexposed Photo Enhancement Using Deep Illumination Estimation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2019:6842-6850.
[25]FU X Y,LIAO Y H,ZENG D L,et al.A Probabilistic Method for Image Enhancement With Simultaneous Illumination and Reflectance Estimation[J].IEEE Transactions on Image Proces-sing,2015,24(12):4965-4977.
[26]YING Z Q,LI G,GAO W.A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement[DB/OL].https://arxiv.org/abs/1711.00591.
[27]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.
[28]ZHANG L,ZHANG L,MOU X Q,et al.FSIM:A Feature Similarity Index for Image Quality Assessment[J].IEEE Transactions on Image Processing,2011,20(8):2378-2386.
[29]GU K,QIAO J F,MIN X K,et al.Evaluating Quality of Screen Content Images Via Structural Variation Analysis[J].IEEE Transactions on Visualization and Computer Graphics,2018,24(10):2689-2701.
[30]WEI D,LIU H,CHEN G L,et al.Underwater Image Enhancement Based on Color Correction and Deblurring[J].Computer Science,2021,48(4):144-150.
[31]HUANG L W,WANG B,SONG T,et al.Reasearch on LowLight Color Image Enhancement Algorithm[J].Journal of Chongqing University of Technology(Natural Science),2020,34(1):219-225.
[32]LI C Y,GUO C L,HAN L H,et al.Low-Light Image and Video Enhancement Using Deep Learning:A Survey[DB/OL].https://arxiv.org/abs/2104.10729.
[1] 牛富生, 郭延哺, 李维华, 刘文洋. 基于序列特征融合的蛋白质可溶性预测[J]. 计算机科学, 2022, 49(1): 285-291.
[2] 周新民, 胡宜桂, 刘文洁, 孙荣俊. 基于多模态多层级数据融合方法的城市功能识别研究[J]. 计算机科学, 2021, 48(9): 50-58.
[3] 郑苏苏, 关东海, 袁伟伟. 融合不完整多视图的异质信息网络嵌入方法[J]. 计算机科学, 2021, 48(9): 68-76.
[4] 赫晓慧, 邱芳冰, 程淅杰, 田智慧, 周广胜. 基于边缘特征融合的高分影像建筑物目标检测[J]. 计算机科学, 2021, 48(9): 140-145.
[5] 张新峰, 宋博. 一种基于改进三元组损失和特征融合的行人重识别方法[J]. 计算机科学, 2021, 48(9): 146-152.
[6] 官铮, 邓扬琳, 聂仁灿. 光谱重建约束非负矩阵分解的高光谱与全色图像融合[J]. 计算机科学, 2021, 48(9): 153-159.
[7] 黄晓生, 徐静. 基于PCANet的非下采样剪切波域多聚焦图像融合[J]. 计算机科学, 2021, 48(9): 181-186.
[8] 张晓宇, 王彬, 安卫超, 阎婷, 相洁. 基于融合损失函数的3D U-Net++脑胶质瘤分割网络[J]. 计算机科学, 2021, 48(9): 187-193.
[9] 谢良旭, 李峰, 谢建平, 许晓军. 基于融合神经网络模型的药物分子性质预测[J]. 计算机科学, 2021, 48(9): 251-256.
[10] 乔颖婧, 高保禄, 史瑞雪, 刘璇, 王朝辉. 融合Tamura纹理特征的改进FCM脑MRI图像分割算法[J]. 计算机科学, 2021, 48(8): 111-117.
[11] 叶中玉, 吴梦麟. 融合时序监督和注意力机制的脉络膜新生血管分割[J]. 计算机科学, 2021, 48(8): 118-124.
[12] 王施云, 杨帆. 基于U-Net特征融合优化策略的遥感影像语义分割方法[J]. 计算机科学, 2021, 48(8): 162-168.
[13] 田嵩旺, 蔺素珍, 杨博. 基于多判别器的多波段图像自监督融合方法[J]. 计算机科学, 2021, 48(8): 185-190.
[14] 李琳, 刘学亮, 赵烨, 纪平. 结合乐高滤波器和SSD的低光照图像融合检测方法[J]. 计算机科学, 2021, 48(7): 213-218.
[15] 张曼, 李杰, 朱新忠, 沈霁, 成昊天. 基于改进DCGAN算法的遥感数据集增广方法[J]. 计算机科学, 2021, 48(6A): 80-84.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 张婧,周安民,刘亮,贾鹏,刘露平. Crash可利用性分析方法研究综述[J]. 计算机科学, 2018, 45(5): 5 -14 .
[2] 张翔, 王伟, 肖迪. 一种改进的具有色彩保护的多尺度Retinex图像增强算法[J]. 计算机科学, 2018, 45(10): 246 -249 .
[3] 印佳,程春玲,周剑. 基于极小独立支配集的多样化排序算法[J]. 计算机科学, 2017, 44(8): 181 -186 .
[4] 杨杰,燕雪峰,张德平. 基于Boosting的代价敏感软件缺陷预测方法[J]. 计算机科学, 2017, 44(8): 176 -180 .
[5] 王旭阳,尉醒醒. 基于本体和局部共现的查询扩展方法[J]. 计算机科学, 2017, 44(1): 214 -218 .
[6] 孙建坤,杨若瑜. 基于颜色直方图和小波变换的视频烟雾检测[J]. 计算机科学, 2014, 41(12): 251 -254 .
[7] 沈虎,吕绍和,王晓东,周兴铭. 一种应用干扰消除进行冲突消解的分布式无线MAC协议[J]. 计算机科学, 2014, 41(12): 60 -66 .
[8] 冯翔,马美怡,赵天玲,虞慧群. 基于复合免疫算法的入侵检测系统[J]. 计算机科学, 2014, 41(12): 43 -47 .
[9] 吴修国. 云计算环境下面向最小成本的数据副本策略[J]. 计算机科学, 2014, 41(10): 154 -159 .
[10] 刘建伟,黎海恩,罗雄麟. 概率图模型表示理论[J]. 计算机科学, 2014, 41(9): 1 -17 .