Abstract：Low-light images suffer from low visibility and poor visual quality.To improve the quality of low-light images,a method based on convolution analysis sparse representation and phase congruency was proposed.This method is based on the Retinex model and improves the problem of insufficient constraints.More concretely,we used the convolutional analysis sparse representation whose filters were hand-crafted and learned from the input to estimate the illumination image.Then,by using the monogenic phase congruency,the reflection image was calculated via the phase congruency residual minimization to enhance weak details.Through joint constraints and optimization,the resulting reflection image served as the final enhancement result.Experiments on a number of challenging low-light images are presented to reveal the efficacy of our method and show its superiority over several state-of-the-arts on both subjective and objective assessments.
[1] 黄伟国,张永萍,毕威,等.梯度稀疏和最小平方约束下的低照度图像分解及细节增强[J].电子学报,2018,46(2):424-432. HUANG Wei-guo,ZHANG Yong-ping,BI Wei,et al.Low light image decomposition and enhancement under gradient sparse and least square constraint[J].Acta Electronica Sinica,2018,46(2):424-432.(in Chinese)
[2] Singh K,Kapoor R.Image enhancement using exposure based sub image histogram equalization[J].Pattern Recognition Letters,2014,36(1):10-14.
[3] 丁畅,董丽丽,许文海.图像梯度场双区间均衡化的细节增强[J].电子学报,2017,45(5):1165-1174. DING Chang,DONG Li-li,XU Wen-hai.Image details enhancement by gradient field bi-interval equalization[J].Acta Electronica Sinca,2017,45(5):1165-1174.(in Chinese)
[4] Liang Z,Xu J,Zhang D,et al.A hybrid l1-l0 layer decomposition model for tone mapping[A].IEEE International Conference on Computer Vision and Pattern Recognition[C].Salt Lake City,Utah,USA,2018.4758-4766.
[5] Yue H,Yang J,Sun X,et al.Contrast enhancement based on intrinsic image decomposition[J].IEEE Trans on Image Processing,2017,26(8):3981-3994.
[6] Jobson D,Rahman Z,Woodel G A.Properties and performance of a center/surround Retinex[J].IEEE Trans on Image Processing,1997,6(3):451-462.
[7] Ying Z,Li G,Ren Y,et al.A new low-light image enhancement algorithm using camera response model[A].IEEE International Conference on Computer Vision and Pattern Recognition[C].Venice,Italy,2017.3015-3022.
[8] Kimmel R,Elad M,Shaked D,et al.A variational framework for Retinex[J].International Journal of Computer Vision,2003,52(1):7-23.
[9] Fu X,Zeng D,Huang Y,et al.A weighted variational model for simultaneous reflectance and illumination estimation[A].IEEE International Conference on Computer Vision and Pattern Recognition[C].Las Vegas,NV,USA,2016.2782-2790.
[10] Guo X,Li Y,Ling H.LIME:Low-light image enhancement via illumination map estimation[J].IEEE Trans on Image Processing,2016,26(2):982-993.
[11] Cai B,Xu X,Guo K,et al.A joint intrinsic-extrinsic prior model for Retinex[A].IEEE International Conference on Computer Vision and Pattern Recognition[C].Venice,Italy,2017.4020-4029.
[12] Wang L,Xiao L,Liu H,et al.Variational Bayesian method for Retinex[J].IEEE Trans on Image Processing,2014,23(8):3381-3396.
[13] Li M,Liu J,Yang W,et al.Structure-revealing low-light image enhancement via robust Retinex model[J].IEEE Trans on Image Processing,2018,27(6):2828-2841.
[14] 张杰,周浦城,薛模根.基于方向性全变分Retinex的低照度图像增强[J].计算机辅助设计与图形学学报,2018,30(10):1943-1953. Zhang Jie,Zhou Pucheng,Xue Mogen.Low-light image enhancement based on directional total variation Retinex[J].Journal of Computer-Aided Design & Computer Graphics,2018,30(10):1943-1953.(in Chinese)
[15] Gu S,Meng D,Zuo W,et al.Joint convolutional analysis and synthesis sparse representation for single image layer separation[A].IEEE International Conference on Computer Vision and Pattern Recognition[C].Venice,Italy,2017.1717-1725.
[16] Chen Y,Ranft R,Pock T.Insights into analysis operator learning:From patch-based sparse models to higher order MRFs[J].IEEE Trans on Image Processing,2014,23(3):1060-1072.
[17] 伍政华,孙明健,顾宗山,等.基于二阶广义方向性全变分的图像超分辨率重建方法[J].电子学报,2017,45(11):2625-2632. WU Zheng-hua,SUN Ming-jian,GU Zong-shan,et al.Second-order directional total generalized variation regularization for image super-resolution[J].Acta Electronica Sinica,2017,45(11):2625-2632.(in Chinese)
[18] Roth R,Black M J.Fields of experts[J].International Journal of Computer Vision,2009,82(2):205-229.
[19] Olshausen B A,Field D J.Emergence of simple-cell receptive field properties by learning a sparse code for natural images[J].Nature,1996,381(6583):607-609.
[20] Kovesi P.Image features from phase congruency[J].VIDERE:Journal of Computer Vision Research,1999,1(3):1-26.
[21] Santhaseelan V,Asari V K.Utilizing local phase information to remove rain from video[J].International Journal of Computer Vision,2015,112(1):71-89.
[22] Felsberg M,Sommer G.The monogenic signal[J].IEEE Trans on Signal Processing,2001,49(12):3136-3144.
[23] Ruderman D L,Cronin T W,Chiao C C.Statistics of cone responses to natural images:Implications for visual coding[J].Journal of the Optical Society of America,1998,15(8):2036-2045.
[24] Mittal A,Soundararajan R,Bovik A.Making a completely blind image quality analyzer[J].IEEE Signal Processing Letters,2013,22(3):209-212.
[25] Gu K,Wang S,Zhai G.Blind quality assessment of tone-mapped images via analysis of information,naturalness and structure[J].IEEE Trans on Multimedia,2016,18(3):432-443.
[26] Narvekar N D,Karam L J.A no-reference image blur metric based on the cumulative probability of blur detection(CPBD)[J].IEEE Trans on Image Processing,2011,20(9):2678-2683.
[27] 王相海,赵晓阳,毕晓昀,等.小波域多角度轮廓模板变分模型的单幅图像超分辨率重建[J].电子学报,2018,46(9):2256-2262. WANG Xiang-hai,ZHAO Xiao-yang,BI Xiao-jun,et al.Single image super-resolution reconstruction approach based on multi-angle contour templates variational calculus model in wavelet domain[J].Acta Electronica Sinica,2018,46(9):2256-2262.(in Chinese)
[28] Luo M R,Cui G,Rigg B.The development of the CIE2000 colour-difference formula:CIEDE2000[J].Color Research & Application,2001,26(5):340-350.
2020, Vol. 48 
