1.武汉科技大学 信息科学与工程学院, 湖北 武汉 430081
2.武汉科技大学 教育部冶金自动化与检测技术工程研究中心, 湖北 武汉 430081
[ "黄子蒙(1995—),男,湖北黄冈人,硕士研究生,2018年于武汉科技大学城市学院获得学士学位,主要从事图像增强方面的研究。E-mail: 1666451195@qq.com." ]
[ "徐望明(1979—),男,湖北武汉人,博士,高级工程师,正高级实验师, 2013年于武汉科技大学大学获得博士学位,主要从事图像处理与模式识别等方面的研究。E-mail:xuwangming@wust.edu.cn" ]
扫 描 看 全 文
黄子蒙, 徐望明, 但愿. 基于对称亮度映射和虚拟多曝光融合的非均匀光照图像增强[J]. 液晶与显示, 2022,37(12):1580-1589.
HUANG Zi-meng, XU Wang-ming, DAN Yuan. Non-uniform illumination image enhancement
黄子蒙, 徐望明, 但愿. 基于对称亮度映射和虚拟多曝光融合的非均匀光照图像增强[J]. 液晶与显示, 2022,37(12):1580-1589. DOI: 10.37188/CJLCD.2022-0172.
HUANG Zi-meng, XU Wang-ming, DAN Yuan. Non-uniform illumination image enhancement
针对非均匀光照图像存在局部过暗或过亮区域而导致图像对比度低、细节不清晰和可视化效果差的问题,提出了一种基于对称亮度映射和虚拟多曝光融合的图像增强方法。该方法通过颜色空间转换保留输入图像的色度和饱和度分量并分离出亮度分量进行增强。根据相机响应模型,采用图像信息熵和平均梯度最大化原则估计最优曝光比,设计了一种对称亮度映射函数用于虚拟生成对应的最优增强曝光图像和减弱曝光图像,从而与原始亮度分量一起组成具有不同曝光的图像序列,再使用带细节提升的多曝光融合方法对该图像序列重构即得到增强结果。实验结果表明,本文方法在7个公开数据集上的图像信息熵、平均梯度、图像对比度、颜色一致性评价指标均值分别为7.644,9.209,450.683,0.962,均优于对比方法,获得了动态范围高、对比度强、细节清晰和可视化效果好的增强结果。
Aiming at the problems of low contrast, unclear details and poor visualization in non-uniform illumination images due to over-dark or over-bright local regions, an image enhancement method ,via, symmetric brightness mapping and virtual multi-exposure fusion is proposed. A color space conversion is used to retain the hue and saturation components and separate the brightness component of the input image for enhancement processing. According to the camera response model, the principle of image information entropy and average gradient maximization is adopted to estimate the optimal exposure ratio. A pair of symmetrical brightness mapping functions are designed to generate virtually corresponding images with the enhanced exposure and reduced exposure, forming an image sequence with different exposures together with the original brightness component. Then, a multi-exposure fusion method with detail enhancement is applied to the image sequence to reconstruct the enhanced result. Experimental results indicate that the average values of evaluation indices such as image information entropy, average gradient, image contrast, and color consistency of the proposed method are 7.644, 9.209, 450.683 and 0.962 on seven public datasets respectively, which are superior to those of the contrast method and achieve enhanced results with high dynamic range, strong contrast, clear details and good visualization.
非均匀光照图像增强亮度映射函数多曝光融合
non-uniform illuminationimage enhancementbrightness mapping functionmulti-exposure fusion
王浩,张叶,沈宏海,等.图像增强算法综述[J].中国光学,2017,10(4):438-448. doi: 10.3788/co.20171004.0438http://dx.doi.org/10.3788/co.20171004.0438
WANG H, ZHANG Y, SHEN H H, et al. Review of image enhancement algorithms [J]. Chinese Optics, 2017, 10(4): 438-448. (in Chinese). doi: 10.3788/co.20171004.0438http://dx.doi.org/10.3788/co.20171004.0438
陈莹,朱明.多子直方图均衡微光图像增强及FPGA实现[J].中国光学,2014,7(2):225-233. doi: 10.3788/co.20140702.0225http://dx.doi.org/10.3788/co.20140702.0225
CHEN Y, ZHU M. Multiple sub-histogram equalization low light level image enhancement and realization on FPGA [J]. Chinese Optics, 2014, 7(2): 225-233. (in Chinese). doi: 10.3788/co.20140702.0225http://dx.doi.org/10.3788/co.20140702.0225
LAND E H. The Retinex theory of color vision [J]. Scientific American, 1977, 237(6): 108-128. doi: 10.1038/scientificamerican1277-108http://dx.doi.org/10.1038/scientificamerican1277-108
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. doi: 10.1109/tip.2013.2261309http://dx.doi.org/10.1109/tip.2013.2261309
FU X Y, ZENG D L, HUANG Y, et al. A weighted variational model for simultaneous reflectance and illumination estimation [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 2782-2790. doi: 10.1109/cvpr.2016.304http://dx.doi.org/10.1109/cvpr.2016.304
YING Z Q, LI G, REN Y R, et al. A new low-light image enhancement algorithm using camera response model [C]//Proceedings of the IEEE International Conference on Computer Vision Workshops. Venice: IEEE, 2017: 3015-3022. doi: 10.1109/iccvw.2017.356http://dx.doi.org/10.1109/iccvw.2017.356
YING Z Q, LI G, REN Y R, et al. A new image contrast enhancement algorithm using exposure fusion framework [C]//17th International Conference on Computer Analysis of Images and Patterns. Ystad: Springer, 2017: 36-46. doi: 10.1007/978-3-319-64698-5_4http://dx.doi.org/10.1007/978-3-319-64698-5_4
徐望明,刘召,伍世虔,等.基于虚拟多曝光融合的不均匀光照图像增强方法[J].华中科技大学学报(自然科学版),2020,48(8):79-84,90.
XU W M, LIU Z, WU S Q, et al. Non-uniform illumination image enhancement method based on virtual multi-exposure fusion [J]. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2020, 48(8): 79-84, 90. (in Chinese)
王兴瑞,朴燕,王雨墨.复合残差网络在低照度图像增强中的技术研究[J].液晶与显示,2022,37(4):508-518. doi: 10.37188/CJLCD.2021-0228http://dx.doi.org/10.37188/CJLCD.2021-0228
WANG X R, PIAO Y, WANG Y M. Technical research of composite residual network in low illumination image enhancement [J]. Chinese Journal of Liquid Crystals and Displays, 2022, 37(4): 508-518. (in Chinese). doi: 10.37188/CJLCD.2021-0228http://dx.doi.org/10.37188/CJLCD.2021-0228
CHEN C, MCClOSKEY S, YU J Y. Analyzing modern camera response functions [C]//2019 IEEE Winter Conference on Applications of Computer Vision (WACV). Waikoloa: IEEE, 2019: 1961-1969. doi: 10.1109/wacv.2019.00213http://dx.doi.org/10.1109/wacv.2019.00213
YANG Y, CAO W, WU S Q, et al. Multi-scale fusion of two large-exposure-ratio images [J]. IEEE Signal Processing Letters, 2018, 25(12): 1885-1889. doi: 10.1109/lsp.2018.2877893http://dx.doi.org/10.1109/lsp.2018.2877893
杨作廷,阮萍,翟波.基于图像熵的高动态范围场景的自动曝光算法[J].光子学报,2013,42(6):742-746. doi: 10.3788/gzxb20134206.0742http://dx.doi.org/10.3788/gzxb20134206.0742
YANG Z T, RUAN P, ZHAI B. Auto-exposure algorithm for scenes with high dynamic range based on image entropy [J]. Acta Photonica Sinica, 2013, 42(6): 742-746. (in Chinese). doi: 10.3788/gzxb20134206.0742http://dx.doi.org/10.3788/gzxb20134206.0742
王绍权.低照度视频图像增强技术研究[D].兰州:兰州交通大学,2020.
WANG S Q. Research on low illumination video image enhancement technology [D]. Lanzhou: Lanzhou Jiaotong University, 2020. (in Chinese)
LEE C, LEE C, KIM C S. Contrast enhancement based on layered difference representation [C]//2012 19th IEEE International Conference on Image Processing. Orlando: IEEE, 2012: 965-968. doi: 10.1109/icip.2012.6467022http://dx.doi.org/10.1109/icip.2012.6467022
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. doi: 10.1109/tip.2016.2639450http://dx.doi.org/10.1109/tip.2016.2639450
VONIKAKIS V, KOUSKOURIDAS R, GASTERATOS A. On the evaluation of illumination compensation algorithms [J]. Multimedia Tools and Applications, 2018, 77(8): 9211-9231. doi: 10.1007/s11042-017-4783-xhttp://dx.doi.org/10.1007/s11042-017-4783-x
LI C Y, GUO J C, PORIKLI F, et al. LightenNet: a convolutional neural network for weakly illuminated image enhancement [J]. Pattern Recognition Letters, 2018, 104: 15-22. doi: 10.1016/j.patrec.2018.01.010http://dx.doi.org/10.1016/j.patrec.2018.01.010
WANG R X, ZHANG Q, FU C W, et al. Underexposed photo enhancement using deep illumination estimation [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 6842-6850. doi: 10.1109/cvpr.2019.00701http://dx.doi.org/10.1109/cvpr.2019.00701
0
浏览量
135
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构