计算机科学 ›› 2022, Vol. 49 ›› Issue (5): 98-104.doi: 10.11896/jsjkx.210100224
鹿婷, 侯国家, 潘振宽, 王国栋
LU Ting, HOU Guo-jia, PAN Zhen-kuan, WANG Guo-dong
摘要： 因为水的吸收和散射效应,导致水下图像普遍存在模糊、低对比度和色彩不均衡等问题,而自然图像质量评价方法没有考虑水下成像的特殊性,难以应用于水下图像;同时目前有效的水下图像的质量评价方法较少,且存在一定局限性。针对此问题,提出了一种新的与主观感知密切相关的无参考水下图像质量评价方法,选择与视觉感知相关性高的色度特征(Col)、基于人类大脑视觉皮层的对比度特征(Con)、反映图像信息丰富程度的清晰度特征(Sharp)这3种属性,来构成水下图像质量评价模型,简称CCS。这些视觉特征对水的物理特性比较敏感,而且人类视觉系统(Human Visual System,HVS)易受色彩、对比度和边缘结构等视觉特性变化的影响。为了验证所提方法的性能,在自建小型水下图像数据集上与CPDB,BRISQUE,UCIQE,UIQM这4种无参考评价算法进行了大量的对比实验,在与主观评价相关性度量方面,CCS方法比UIQM方法的RMSE度量指标提升了大约13%,比UCIQE和UIQM方法的PLCC,SROCC和KROCC度量指标提升均超过10%。实验结果表明,CCS算法与人类视觉感知具有高度一致性,能有效、准确地评估水下图像的质量。
中图分类号:
| [1]LIU R S,FAN X,ZHU M,et al.Real-World Underwater Enhancement:Challenges,Benchmarks,and Solutions Under Natural Light[J].IEEE Transactions on Circuits and Systems for Video Technology,2020,30(12):4861-4875. [2]HOU G J,ZHAO X,PAN Z K,et al.Benchmarking Underwater Image Enhancement and Restoration,and Beyond[J].IEEE Access,2020,8:122078-122091. [3]CHEN L L,ZHU F,SHENG B,et al.Quality Evaluation of Co-lor Image Based on Discrete Quaternion Fourier Transform[J].Computer Science,2018,45(8):70-74. [4]WANG S,YU W,TIAN C.Blind quality metric of super-resolution reconstructed images based on multi-order structure representation[J].Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition),2021,33(2):280-288. [5]WANG Z,BOVIK A C,SHEIKH H R,et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Transaction on Image Processing,2004,13(4):600-612. [6]PANETTA K,GAO C,AGAIAN S.No reference color image contrast and quality measures[J].IEEE Transaction on Consumer Electronics,2013,59(3):643-651. [7]YANG Y S,SANG Q B.No-reference Color Noise Images Qua-lity Assessment Without Learning[J].Computer Science,2020,47(10):161-168. [8]CHEN X,LI L D,LI Q Y,et al.No-reference Quality Assessment of Depth Images Based on Natural Scenes Statistics[J].Computer Science,2019,46(6):256-262. [9]MITTAL A,MOORTHY A K,BOVIK A C.No-ReferenceImage Quality Assessment in the Spatial Domain[J].IEEE Tran-sactions on Image Progressing,2012,21(12):4695-4708. [10]MA K,LIU W,ZHANG K,et al.End-to-End Blind Image Qua-lity Assessment Using Deep Neural Networks[J].IEEE Tran-sactions on Image Progressing,2018,27(3):1202-1213. [11]FANG Y,MA K,WANG Z,et al.No-reference Quality Assessment of Contrast-Distorted Images Based on Natural Scene Statistics[J].IEEE Signal Processing Letters,2014,22(7):838-842. [12]FU Y Y.Color image quality measures and retrieval[M]//New Jersey Institute of Technology.Newark,NJ,United States,2006. [13]CHOI L K,YOU J,BOVIK A C.Referenceless Prediction ofPerceptual Fog Density and Perceptual Image Defogging[J].IEEE Transactions on Image Processing,2015,24(11):3888-3901. [14]TANG S Q,LI C L,TIAN Q.Underwater image quality assessment based on human visual[C]//2020 13th International Congress on Image and Signal Processing,BioMedical Engineering and Informatics(CISP-BMEI).2020:378-382. [15]YANG M,SOWMYA A.An Underwater Colour Image QualityEvaluation Metric[J].IEEE Transactions on Image Processing,2015,24(12):6062-6071. [16]PANETTA K,GAO C,AGAIAN S.Human-Visual-System-Inspired Underwater Image Quality Measures[J].IEEE Journal of Oceanic Engineering,2016,41(3):541-551. [17]SONG W,LIU S,HUANG D M,et al.Non-reference underwater video quality assessment method for small size samples[J].Journal of Image and Graphics,2020,25(9):1787-1799. [18]GALDRAN A,PARDO D,PICÓN A,et al.Automatic Red-Channel underwater image restoration[J].Journal of Visual Communication & Image Representation,2015,26:132-145. [19]GATTS C,RIZZI A,MARINI D.ACE:An Automatic ColorEqualization Algorithm[C]//Conference on Colour in Graphics.2002. [20]GROEN I I A,GHEBREAB S,PRINS H,et al.From image sta-tistics to scene gist:Evoked neural activity reveals transition from low-level natural image structure to scene category[J].J. Neurosci,2013,33(48):18814-18824. [21]PANETTA K,SAMANI A,AGAIAN S S.Choosing the Optimal Spatial Domain Measure of Enhancement for Mammogram Images[J].International Journal of Biomed Imaging,2014,937849:1-8. [22]CODEVILLA F M,BOTELHO S S D C,JR P D,et al.Underwater Single Image Restoration Using Dark Channel Prior[C]//2014 Symposium on Automation and Computation for Naval,Offshore and Subsea (NAVCOMP).IEEE,2016:18-21. [23]IQBAL K,ABDUL S R,OSMAN M,et al.Underwater Image Enhancement Using an Integrated Colour Model[J].International of Computer Ence,2007,32(2):239-244. [24]LIU L,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. [25]PENG Y T,COSMAN P C.Underwater Image RestorationBased on Image Blurriness and Light Absorption[J].IEEE Transactions on Image Processing,2017,26(4):1579-1594. [26]LIU X,ZHANG H,CHEUNG Y M,et al.Efficient Single Image Dehazing and Denosing:An Efficient Multi-scale Correlated Wavelet Approach[J].Computer Vision and Image Understanding,2017,162(8):23-33. [27]MERTENS L E,REPLOGLE F S.Use of point spread and beam spread functions for analysis of imaging systems in water[J].Journal of the Optical Society of America,1977,67(8):1105-1117. [28]ANCUTI C,ANCUTI C O,HABER T,et al.Enhancing underwater imagesand videos by fusion[C]//IEEE Conferencec on Computer Vision & Pattern Recognition.IEEE,2012:81-88. [29]LI C Y,GUO J C,CONG R M,et al.Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution Prior[J].IEEE Transactions on Image Processing,2016,25(12):5664-5677. [30]PAN P W,YUAN F,CHENG E.Underwater image de-scatte-ring and enhancing using dehazenet and HWD[J].Journal of Marine Science and Technology,2018,26(4):531-540. [31]FU X Y,CAO X Y.Underwater image enhancement with glo-bal-local networks and compressed-histogram equalization[J].Signal Processing:Image Communication,2020,86:115892. [32]LI X J,HOU G J,TAN L,et al.A Hybrid Framework for Underwater Image Enhancement[J].IEEE Access,2020,8:197448-197462. [33]SUN W,ZHOU F,LIAO Q.MDID:A multiply distorted image database for image quality assessment[J].Pattern Recognition,2017,61:153-168. [34]NARVKAR N D,KARAM L J.A No-Reference Image BlurMetric Based on the Cumulative Probability of Blur Detection (CPBD)[J].IEEE Transactions on Image Processing,2011,20(9):1678-1683. |
| [1] | 杨小琴, 刘国军, 郭建慧, 马文涛. 基于随机森林的空域-频域联合特征全参考彩色图像质量评价方法 Full Reference Color Image Quality Assessment Method Based on Spatial and Frequency Domain Joint Features with Random Forest 计算机科学, 2021, 48(8): 99-105. https://doi.org/10.11896/jsjkx.200700106 |
| [2] | 朱玲莹, 桑庆兵, 顾婷婷. 基于视差信息的无参考立体图像质量评价 No-reference Stereo Image Quality Assessment Based on Disparity Information 计算机科学, 2020, 47(9): 150-156. https://doi.org/10.11896/jsjkx.190700213 |
| [3] | 杨云铄, 桑庆兵. 无需学习的无参考彩色噪声图像质量评价方法 No-reference Color Noise Images Quality Assessment Without Learning 计算机科学, 2020, 47(10): 161-168. https://doi.org/10.11896/jsjkx.190900051 |
| [4] | 陈曦, 李雷达, 李巧月, 韩习习, 祝汉城. 基于自然场景统计的深度图像质量无参考评价方法 No-reference Quality Assessment of Depth Images Based on Natural Scenes Statistics 计算机科学, 2019, 46(6): 256-262. https://doi.org/10.11896/j.issn.1002-137X.2019.06.038 |
| [5] | 张文博,侯晓荣. 基于高斯分布的大气光估计算法 Estimation Algorithm of Atmospheric Light Based on Gaussian Distribution 计算机科学, 2018, 45(4): 301-305. https://doi.org/10.11896/j.issn.1002-137X.2018.04.051 |
| [6] | 闻武,左凌轩. 基于色彩特征的无参考彩色图像质量评价 Blind Color Image Quality Assessment Base on Color Characteristics 计算机科学, 2017, 44(Z6): 151-156. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.035 |
| [7] | 熊润生,李朝锋,张伟. 基于小波变换的无参考立体图像质量评价 No-reference Stereoscopic Image Quality Assessment Based on Wavelet Transform 计算机科学, 2015, 42(9): 282-284. https://doi.org/10.11896/j.issn.1002-137X.2015.09.055 |
| [8] | 华东,余宏生. 数字融合图像质量的视觉信息保真度客观评价方法 Digital Fusion Image Quality Objective Assessment Method Based on Visual Information Fidelity 计算机科学, 2014, 41(Z6): 224-226. |
| [9] | 桑庆兵,梁狄林,吴小俊,李朝锋. 基于膨胀的梯度结构相似度图像质量评价方法 Gradient Structural Similarity Image Assessment Index Based on Dilation 计算机科学, 2014, 41(6): 287-290. https://doi.org/10.11896/j.issn.1002-137X.2014.06.057 |
| [10] | 常嘉义,秦瑞,李庆,陈大鹏. 全景鸟瞰拼接图像的质量评价方法 Image Quality Assessment of Panoramic Image 计算机科学, 2014, 41(6): 278-281. https://doi.org/10.11896/j.issn.1002-137X.2014.06.055 |
| [11] | 褚江,陈强. 自然图像颜色空间统计规律性研究 Research on Natural Scene Statistics in Color Space 计算机科学, 2014, 41(11): 309-312. https://doi.org/10.11896/j.issn.1002-137X.2014.11.061 |
| [12] | 王颖慧,刘万军. 基于MSB和HVS的空域信息隐藏算法的研究 Study of Spatial Information Hiding Algorithm Based on MSB and HVS 计算机科学, 2012, 39(9): 89-93. |
| [13] | 徐国梁，谭庆平. 基于非理想打印机模型的半色调化图像质量评价方法研究 Quality Assessment for Halftone Image Based on Non-ideal Printer Model 计算机科学, 2010, 37(10): 228-232. |
| [14] | 刘红军,杨胜,夏太武. 一种基于视觉模型的DCT域公开水印算法 DCT Based Public Watermarking Algorithm with Visual Model 计算机科学, 2009, 36(7): 281-283. https://doi.org/10.11896/j.issn.1002-137X.2009.07.069 |
| [15] | 吉国力,倪晓明. 基于Haar小波变换高频特征的图像质量评价算法 Image Quality Assessment Algorithm Based on High Frequency Band of Haar Wavelet Transform 计算机科学, 2009, 36(10): 262-264. |
|
||
首页