浏览全部资源
扫码关注微信
中国海洋大学 信息科学与工程学部 物理与光电工程学院,山东 青岛 266100
[ "王昊天(1994-),男,黑龙江绥化人,硕士研究生,2019年于哈尔滨工业大学获得学士学位,主要从事水下显微图像处理方面的研究。E-mail: wanghaotian@stu.ouc.edu.cn" ]
[ "叶旺全(1991-),男,安徽宣城人,讲师,博士,2013年,2019年分别于中国海洋大学获得学士、博士学位,主要从事光谱类传感器一体化控制系统研制及光谱图像数据处理相关研究。E-mail: yewangquan@ouc.edu.cn" ]
收稿日期:2022-03-01,
修回日期:2022-03-20,
纸质出版日期:2022-06-25
移动端阅览
王昊天,刘庆省,陈亮等.改进的CycleGAN网络用于水下显微图像颜色校正[J].光学精密工程,2022,30(12):1499-1508.
WANG Haotian,LIU Qingsheng,CHEN Liang,et al.Improved CycleGAN network for underwater microscopic image color correction[J].Optics and Precision Engineering,2022,30(12):1499-1508.
王昊天,刘庆省,陈亮等.改进的CycleGAN网络用于水下显微图像颜色校正[J].光学精密工程,2022,30(12):1499-1508. DOI: 10.37188/OPE.20223012.1499.
WANG Haotian,LIU Qingsheng,CHEN Liang,et al.Improved CycleGAN network for underwater microscopic image color correction[J].Optics and Precision Engineering,2022,30(12):1499-1508. DOI: 10.37188/OPE.20223012.1499.
针对海洋水体及悬浮颗粒物吸收和散射所导致的水下显微图像的颜色信息失真问题,本文提出了一种改进的循环一致性对抗网络(Cycle-consistent Adversarial Network, CycleGAN)算法,实现对水下目标物图像的颜色校正。通过在原始水下降质图像和重构水下图像之间加入R、G、B三个通道的结构相似性(Structure Similarity Index Measure, SSIM)损失函数,度量二者图像之间的信息损失,进而实现R、G、B三个通道颜色的精准调控,不仅增强了CycleGAN网络的整体性能,也提高了生成器生成图像的质量。然后,利用水下多色自制标靶及天然矿石的显微图像组成的训练数据集对本文所提的改进网络进行训练,所得的模型可用于实际矿石样品表面的显微图像颜色校正。结果表明,本文所提的改进的CycleGAN算法较其它方法在颜色校正方面有着明显的优势。与传统的Retinex算法相比,处理后的图像峰值信噪比(Peak Signal-to-Noise Ratio, PSNR)和结构相似性指标分别提高41.85%、35.62%,而且,从主观视觉角度可发现经过校正的水下显微图像与空气中图像颜色相似度最高。综上,本文方法可以有效地对水下目标物图像进行颜色校正,并提升水下显微图像的质量,有望在海洋地质和海洋生物学方面得到应用。
The absorption and scattering of light by marine water and suspended particles lead to the distortion of color in underwater microscopic images. This paper presents an improved cycle generative adversarial network (CycleGAN) algorithm for effectively correcting the color of microscopic images of underwater targets. The structural similarity index (SSIM) loss function, which measures the loss of color information among images, of the R, G, and B channels was added between the original underwater images and the reconstructed images. Therefore, the color of the R, G and B channels was accurately regulated. This enhanced not only the overall performance of the CycleGAN, but also the quality of images produced by the generator. Subsequently, the improved network was trained by using a training data set, which consisted of underwater multicolor self-made target images and microscopic images of natural stones. The trained network model was used to correct the color of the microscopic images of underwater stones. The results showed that the improved CycleGAN algorithm had distinct advantages in color correction over other methods. The peak signal-to-noise ratio and SSIM of the images processed by using this algorithm were 41.85% and 35.62% higher than those processed by using the traditional Retinex algorithm, respectively. Moreover, in terms of subjective vision, the corrected underwater microscopic images had the highest color similarity with the images taken in air. In conclusion, this method can effectively correct the color of underwater target images and improve the quality of underwater microscopic images. It can be applied in marine geology and marine biology.
NOZAKI T , NAGASE T , USHIKUBO T , et al . Microbial sulfate reduction plays an important role at the initial stage of subseafloor sulfide mineralization [J]. Geology , 2021 , 49 ( 2 ): 222 - 227 . doi: 10.1130/g47943.1 http://dx.doi.org/10.1130/g47943.1
SINHA R K , KRISHNAN K P , THOMAS F A , et al . Polyphasic approach revealed complex bacterial community structure and function in deep sea sediment of ultra-slow spreading Southwest Indian Ridge [J]. Ecological Indicators , 2019 , 96 : 40 - 51 . doi: 10.1016/j.ecolind.2018.08.063 http://dx.doi.org/10.1016/j.ecolind.2018.08.063
NIKOLAUS R , AMMERMAN J W , MACDONALD I R . Distinct pigmentation and trophic modes in beggiatoa from hydrocarbon seeps in the gulf of Mexico [J]. Aquatic Microbial Ecology , 2003 , 32 : 85 - 93 . doi: 10.3354/ame032085 http://dx.doi.org/10.3354/ame032085
ZHANG R , GUI X Y , CHENG H Y , et al . Underwater image recovery utilizing polarimetric imaging based on neural networks [J]. Applied Optics , 2021 , 60 ( 27 ): 8419 . doi: 10.1364/ao.431299 http://dx.doi.org/10.1364/ao.431299
WU S C , LUO T , JIANG G Y , et al . A two-stage underwater enhancement network based on structure decomposition and characteristics of underwater imaging [J]. IEEE Journal of Oceanic Engineering , 2021 , 46 ( 4 ): 1213 - 1227 . doi: 10.1109/joe.2021.3064093 http://dx.doi.org/10.1109/joe.2021.3064093
HAN R Y , GUAN Y , YU Z B , et al . Underwater image enhancement based on a spiral generative adversarial framework [J]. IEEE Access , 2020 , 8 : 218838 - 218852 . doi: 10.1109/access.2020.3041280 http://dx.doi.org/10.1109/access.2020.3041280
ZONG X H , CHEN Z H , WANG D D . Local-CycleGAN: a general end-to-end network for visual enhancement in complex deep-water environment [J]. Applied Intelligence , 2021 , 51 ( 4 ): 1947 - 1958 . doi: 10.1007/s10489-020-01931-w http://dx.doi.org/10.1007/s10489-020-01931-w
FU X Y , CAO X Y . Underwater image enhancement with global-local networks and compressed-histogram equalization [J]. Signal Processing: Image Communication , 2020 , 86 : 115892 . doi: 10.1016/j.image.2020.115892 http://dx.doi.org/10.1016/j.image.2020.115892
SONG W , WANG Y , HUANG D M , et al . Enhancement of underwater images with statistical model of background light and optimization of transmission map [J]. IEEE Transactions on Broadcasting , 2020 , 66 ( 1 ): 153 - 169 . doi: 10.1109/tbc.2019.2960942 http://dx.doi.org/10.1109/tbc.2019.2960942
褚金奎 , 张培奇 , 成昊远 , 等 . 基于特定偏振态成像的水下图像去散射方法 [J]. 光学 精密工程 , 2021 , 29 ( 5 ): 1207 - 1215 . doi: 10.37188/OPE.20212905.1207 http://dx.doi.org/10.37188/OPE.20212905.1207
CHU J K , ZHANG P Q , CHENG H Y , et al . De-scattering method of underwater image based on imaging of specific polarization state [J]. Opt. Precision Eng. , 2021 , 29 ( 5 ): 1207 - 1215 . (in Chinese) . doi: 10.37188/OPE.20212905.1207 http://dx.doi.org/10.37188/OPE.20212905.1207
ZHUANG P X , DING X H . Underwater image enhancement using an edge-preserving filtering Retinex algorithm [J]. Multimedia Tools and Applications , 2020 , 79 ( 25/26 ): 17257 - 17277 . doi: 10.1007/s11042-019-08404-4 http://dx.doi.org/10.1007/s11042-019-08404-4
ZHU J Y , PARK T , ISOLA P , et al . Unpaired image-to-image translation using cycle-consistent adversarial networks [C]. 2017 IEEE International Conference on Computer Vision . 2229,2017 , Venice, Italy . IEEE , 2017 : 2242 - 2251 . doi: 10.1109/iccv.2017.244 http://dx.doi.org/10.1109/iccv.2017.244
杜振龙 , 沈海洋 , 宋国美 , 等 . 基于改进CycleGAN的图像风格迁移 [J]. 光学 精密工程 , 2019 , 27 ( 8 ): 1836 - 1844 . doi: 10.3788/ope.20192708.1836 http://dx.doi.org/10.3788/ope.20192708.1836
DU Z L , SHEN H Y , SONG G M , et al . Image style transfer based on improved CycleGAN [J]. Opt. Precision Eng. , 2019 , 27 ( 8 ): 1836 - 1844 . (in Chinese) . doi: 10.3788/ope.20192708.1836 http://dx.doi.org/10.3788/ope.20192708.1836
LU J Y , LI N , ZHANG S Y , et al . Multi-scale adversarial network for underwater image restoration [J]. Optics & Laser Technology , 2019 , 110 : 105 - 113 . doi: 10.1016/j.optlastec.2018.05.048 http://dx.doi.org/10.1016/j.optlastec.2018.05.048
LIU F , HAN P L , WEI Y , et al . Deeply seeing through highly turbid water by active polarization imaging [J]. Optics Letters , 2018 , 43 ( 20 ): 4903 - 4906 . doi: 10.1364/ol.43.004903 http://dx.doi.org/10.1364/ol.43.004903
AMER K O , ELBOUZ M , ALFALOU A . Phase Contrast Enhancement Combined with Dark Channel Prior for Underwater Target Recognition [J]. The Eurasia Proceedings of Science Technology Engineering and Mathematics , 2018 ( 4 ): 74 - 81 . doi: 10.1364/oe.27.000621 http://dx.doi.org/10.1364/oe.27.000621
聂瑛 , 何志毅 . 不同波长光源照明的水下成像及光学图像实时处理 [J]. 光学学报 , 2014 , 34 ( 7 ): 0710002 . doi: 10.3788/aos201434.0710002 http://dx.doi.org/10.3788/aos201434.0710002
NIE Y , HE Z Y . Underwater imaging and real-time optical image processing under illumination by light sources with different wavelengths [J]. Acta Optica Sinica , 2014 , 34 ( 7 ): 0710002 . (in Chinese) . doi: 10.3788/aos201434.0710002 http://dx.doi.org/10.3788/aos201434.0710002
王卫星 , 赵恒 . 结合改进Retinex及自适应分数阶微分的雾霾公路交通图像增强 [J]. 光学 精密工程 , 2020 , 28 ( 8 ): 1820 - 1834 . doi: 10.3788/OPE.20202808.1820 http://dx.doi.org/10.3788/OPE.20202808.1820
WANG W X , ZHAO H . Haze traffic image enhancement based on improved retinex and adaptive fractional differential [J]. Opt. Precision Eng. , 2020 , 28 ( 8 ): 1820 - 1834 . (in Chinese) . doi: 10.3788/OPE.20202808.1820 http://dx.doi.org/10.3788/OPE.20202808.1820
王冬云 , 唐楚 , 鄂世举 , 等 . 基于导向滤波Retinex和自适应Canny的图像边缘检测 [J]. 光学 精密工程 , 2021 , 29 ( 2 ): 443 - 451 . doi: 10.37188/OPE.20212902.0443 http://dx.doi.org/10.37188/OPE.20212902.0443
WANG D Y , TANG C , E S J , et al . Image edge detection based on guided filter Retinex and adaptive Canny [J]. Opt. Precision Eng. , 2021 , 29 ( 2 ): 443 - 451 . (in Chinese) . doi: 10.37188/OPE.20212902.0443 http://dx.doi.org/10.37188/OPE.20212902.0443
HORÉ A , ZIOU D . Image quality metrics: PSNR vs. SSIM [C]. 2010 20th International Conference on Pattern Recognition . 2326,2010 , Istanbul, Turkey . IEEE , 2010 : 2366 - 2369 . doi: 10.1109/icpr.2010.579 http://dx.doi.org/10.1109/icpr.2010.579
YANG M , SOWMYA A . An underwater color image quality evaluation metric [J]. IEEE Transactions on Image Processing , 2015 , 24 ( 12 ): 6062 - 6071 . doi: 10.1109/tip.2015.2491020 http://dx.doi.org/10.1109/tip.2015.2491020
0
浏览量
2261
下载量
3
CSCD
关联资源
相关文章
相关作者
相关机构