基于数据库和客观方法对夜间雾化增强图像的感知质量评估
PDF下载 (153)刘 倩,李新玥,何周燕.基于数据库和客观方法对夜间雾化增强图像的感知质量评估[J].宁波大学学报(理工版),2024,37(4):74-83.DOI:10.20098/j.cnki.1001-5132.2023.0711
LIU Qian,LI Xinyue,HE-ZHOU Yan.Perceptual quality assessment of night-time haze enhanced images: database and objective method[J].Journal of Ningbo University(Natural Science & Engineering Edition),2024,37(4):74-83.DOI:10.20098/j.cnki.1001-5132.2023.0711
| Title: | Perceptual quality assessment of night-time haze enhanced images: database and objective method |
| 作者: | 刘 倩, 李新玥, 何周燕 |
| Author(s): | LIU Qian, LI Xinyue, HE-ZHOU Yan |
| 关键词: | 夜间雾化增强图像; 图像质量评价; 光散射加权局部二值模式直方图 |
| Keywords: | night-time haze enhanced images; images quality assessment; light scattering-weighted histogram of local binary pattern |
| 分类号: | TP391 |
| DOI: | 10.20098/j.cnki.1001-5132.2023.0711 |
| 文献标识码: | A |
| 摘要: | 为提高夜间雾化图像的质量, 对夜间雾化增强图像的主客观质量评估进行探索. 首先构建夜间雾化增强图像质量评估数据库并进行主观分析, 然后提出一种基于夜间成像特性的无参考图像质量评估方法. 新方法在辉光图像上提取光散射和颜色特征, 再在增强图像上提取雾密度和纹理特征. 结果表明, 新方法性能优于现有其他先进的无参考图像质量评估方法. |
| Abstract: | To improve the quality of night-time haze images, we study the subjective and objective quality assessment of night-time haze enhanced images. First, a quality assessment database of night-time haze enhanced images is constructed and analyzed subjectively. Subsequently, a novel no-reference image quality assessment method is proposed based on the night-time imaging characteristics. By using the new assessment method, the light scattering and color features in glow images are extracted, and in enhanced images the haze density features and texture features are extracted. The experimental results show that the new method performs better than the other advanced no-reference image quality evaluation methods that are currently available. |
| 参考文献 /References: | [1] JIANG Q P, XU J W, MAO Y, et al. Deep decomposition and bilinear pooling network for blind night-time image quality evaluation[EB/OL]. [2023-03-21]. 2022: arXiv: 2205.05880. http://arxiv.org/abs/2205.05880.pdf. [2] YANG Y, XIANG T, GUO S W, et al. EHNQ: subjective and objective quality evaluation of enhanced night-time images[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33(9):4645-4659. [3] XIANG T, YANG Y, GUO S W. Blind night-time image quality assessment: subjective and objective approaches [J]. IEEE Transactions on Multimedia, 2020, 22(5):1259- 1272. [4] LIM J S. Two-dimensional signal and image processing [D]. USA, Cambridge: Massachusetts Institute of Technology, 1990. [5] 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. [6] XU J, HOU Y K, REN D W, et al. STAR: a structure and texture aware retinex model[J]. IEEE Transactions on Image Processing, 2020, 29:5022-5037. [7] GUO C, LI C, GUO J, 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, WA, USA. IEEE, 2020: 1777-1786. [8] LU K, ZHANG L H. TBEFN: a two-branch exposure- fusion network for low-light image enhancement[J]. IEEE Transactions on Multimedia, 2020, 23:4093-4105. [9] ZHANG F, LI Y, YOU S, et al. Learning temporal consistency for low light video enhancement from single images[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, TN, USA. IEEE, 2021:4965-4974. [10] ZHANG J, CAO Y, WANG Z F. Nighttime haze removal based on a new imaging model[C]//2014 IEEE International Conference on Image Processing (ICIP). Paris, France. IEEE, 2014:4557-4561. [11] ZHANG J, CAO Y, FANG S, et al. Fast haze removal for nighttime image using maximum reflectance prior[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA. IEEE, 2017: 7016-7024. [12] SHI Z H, ZHU M M, GUO B, et al. Nighttime low illumination image enhancement with single image using bright/dark channel prior[J]. EURASIP Journal on Image and Video Processing, 2018, 2018(1):1-15. [13] HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12):2341- 2353. [14] QIN X, WANG Z, BAI Y, et al. FFA-net: feature fusion attention network for single image dehazing[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7):11908-11915. [15] ZHU Q S, MAI J M, SHAO L. A fast single image haze removal algorithm using color attenuation prior[J]. IEEE Transactions on Image Processing, 2015, 24(11):3522- 3533. [16] ZHAI G T, SUN W, MIN X K, et al. Perceptual quality assessment of low-light image enhancement[J]. ACM Transactions on Multimedia Computing, Communica- tions, and Applications, 2021, 17(4):130. [17] MITTAL A, MOORTHY A K, BOVIK A C. No-reference image quality assessment in the spatial domain[J]. IEEE Transactions on Image Processing, 2012, 21(12):4695-4708. [18] MITTAL A, SOUNDARARAJAN R, BOVIK A C. Making a “completely blind” image quality analyzer[J]. IEEE Signal Processing Letters, 2013, 20(3):209-212. [19] LIU L X, 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. [20] XUE W F, MOU X Q, ZHANG L, et al. Blind image quality assessment using joint statistics of gradient magnitude and Laplacian features[J]. IEEE Transactions on Image Processing, 2014, 23(11):4850-4862. [21] FANG Y M, MA K D, WANG Z, et al. No-reference quality assessment of contrast-distorted images based on natural scene statistics[J]. IEEE Signal Processing Letters, 2015, 22(7):838-842. [22] YAN J, LI J, FU X. No-reference quality assessment of contrast-distorted images using contrast enhancement [EB/OL]. [2023-03-21]. 2019: arXiv: 1904.08879. http:// arxiv.org/abs/1904.08879.pdf. [23] LI Q H, LIN W S, FANG Y M. No-reference quality assessment for multiply-distorted images in gradient domain[J]. IEEE Signal Processing Letters, 2016, 23(4): 541-545. [24] WANG M H, HUANG Y J, ZHANG J L. Blind quality assessment of night-time images via weak illumination analysis[C]//2021 IEEE International Conference on Multimedia and Expo (ICME). Shenzhen, China. IEEE, 2021:1-6. [25] ZHANG J, CAO Y, ZHA Z J, et al. Nighttime dehazing with a synthetic benchmark[C]//2020 Proceedings of the 28th ACM International Conference on Multimedia. Seattle, WA, USA. ACM, 2020:2355-2363. [26] SCHÖLKOPF B. Learning with kernels: support vector machines, regularization, optimization, and beyond[M]. USA, Cambridge: MIT Press, 2003. [27] NARASIMHAN S G, NAYAR S K. Shedding light on the weather[C]//2003 IEEE Computer Society, Conference on Computer Vision and Pattern Recognition. Madison, WI, USA. IEEE, 2003:I. [28] LI Y, TAN R T, BROWN M S. Nighttime haze removal with glow and multiple light colors[C]//2015 IEEE International Conference on Computer Vision (ICCV). Santiago, Chile. IEEE, 2015:226-234. [29] OTSU N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1):62-66. [30] OJALA T, PIETIKAINEN M, MAENPAA T. Multi- resolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transac- tions on Pattern Analysis and Machine Intelligence, 2002, 24(7):971-987. [31] SONG C Y, HOU C P, YUE G H, et al. No-reference quality assessment of night-time images via the analysis of local and global features[C]//2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). Shenzhen, China. IEEE, 2021:1-6. [32] GROEN I I A, GHEBREAB S, PRINS H, et al. From image statistics to scene gist: evoked neural activity reveals transition from low-level natural image structure to scene category[J]. The Journal of Neuroscience, 2013, 33(48):18814-18824. [33] HARALICK R M, SHANMUGAM K, DINSTEIN I. Textural features for image classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1973(6): 610-621. [34] Video Quality Experts Group. Final report from the video quality experts group on the validation of objective models of video quality assessment[C]//VQEG Meeting. Ottawa, Canada, 2000. [35] MA K D, WU Q B, WANG Z, et al. Group MAD competition? a new methodology to compare objective image quality models[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA. IEEE, 2016:1664-1673. |
| 备注/Memo: | 收稿日期: 2023−07−19. 宁波大学学报（理工版）网址: http://journallg.nbu.edu.cn/ 基金项目: 浙江省自然科学基金（LQ23F010011）. 第一作者: 刘倩, 硕士研究生, 主要研究方向: 图像质量评价. E-mail: liuqian_1016@163.com *通信作者: 何周燕, 讲师, 主要研究方向: 多媒体信息处理、质量评估. E-mail: hezhouyan@nbu.edu.cn 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ |
