1.南京工程学院 计算机工程学院, 江苏 南京 211167
2.西安交通大学 信息与通信工程学院, 陕西 西安 710049
[ "姚军财(1979-),男,博士, 教授。毕业于西安交通大学,获得博士学位,主要从事图像和视频技术, 光信息处理技术,机器学习,计算机视觉与模式识别等方面的研究工作。E-mail: yaojcnj@njit.edu.cn" ]
[ "申 静(1981-),女,硕士,副教授。主要从事图像技术,信息安全,光信息处理技术,计算机视觉与模式识别等方面的研究工作。E-mail: shenjnj@njit.edu.cn" ]
收稿:2025-04-03,
修回:2025-06-18,
纸质出版:2025-09-25
移动端阅览
姚军财,申静.基于图像画面信息及其视觉感知的无参考图像质量评价[J].光学精密工程,2025,33(18):2944-2961.
YAO Juncai,SHEN Jing.No reference image quality assessment based on image tableau information and their visual perception[J].Optics and Precision Engineering,2025,33(18):2944-2961.
姚军财,申静.基于图像画面信息及其视觉感知的无参考图像质量评价[J].光学精密工程,2025,33(18):2944-2961. DOI: 10.37188/OPE.20253318.2944. CSTR: 32169.14.OPE.20253318.2944.
YAO Juncai,SHEN Jing.No reference image quality assessment based on image tableau information and their visual perception[J].Optics and Precision Engineering,2025,33(18):2944-2961. DOI: 10.37188/OPE.20253318.2944. CSTR: 32169.14.OPE.20253318.2944.
为了提出一种符合视觉感知且精度、泛化性和复杂性综合效益较高的图像质量评价(IQA)方法,以实现更好地控制图像处理并满足其实际应用需求,结合人眼视觉系统(HVS)的对比敏感、亮度感知非线性、视觉感知舒适度和纹理复杂度感知等特性,基于图像亮度、色度、纹理、清晰度和局部对比度等画面信息和特征,提出了一种无参考IQA方法及其模型BCTCSP。在该方法中,首先分析图像亮度、灰度分布、颜色深度及其饱和度、亮度非线性感知、视觉感知舒适度等与图像质量之间的关系,提出图像亮度色度及其视觉感知对IQA贡献和影响的量化和计算方法;再结合灰度梯度共生矩阵计算和统计图像纹理特征,并采用纹理加权平均和HVS复杂目标感知模型,提出量化和计算图像纹理信息熵及其视觉感知对IQA的贡献和影响的方法;接着,计算图像每一点的对比度值和觉察阈值,结合HVS的对比敏感度特性及其模型和掩蔽特性,量化和计算图像局部对比度及其视觉感知对IQA的贡献和影响;之后,采用锐度、信噪比、高频成分占比和分辨率4个因子描述图像清晰度,提出其量化和计算方法,得到图像画面的清晰度指标;最后综合4个方面的因素,构建IQA模型,量化其度量标准。同时,采用6个国际开源数据库(TID2013,CSIQ,LIVE,IVC,SPAQ和Koniq 10k)中6430幅失真图像进行测试和验证,并就精度、复杂性、泛化性、以及其模型效果方面,与28个现有典型IQA模型进行对比。实验结果表明,所提BCTCSP模型的精度PLCC值在6个数据库中最低可达0.892 1,最高达到0.966 4,6个数据库的加权PLCC达到0.917 4,其综合效益高于该28个现有IQA模型。综合理论和实验结果表明,BCTCSP是一种有效的、性能优越的无参考IQA模型。
It aimed to propose an image quality assessment (IQA) method that conformed to visual perception and had high comprehensive benefits of accuracy, generalization, and complexity, which would better control image processing and meet its practical application needs. Based on the image tableau information and their features such as brightness, chromaticity, texture, clarity, and local contrast, and considering human perception effects such as contrast sensitivity, non-linear perception of brightness, visual comfort, and texture complexity perception, a no-reference IQA method, namely BCTCSP, was proposed. In BCTCSP, firstly, by analyzing the relationship between image quality and image brightness, grayscale distribution, color depth and saturation, non-linear perception of brightness, and visual perception comfort, a quantitative and computational method was proposed to obtain the contribution and impact of image brightness, chromaticity, and visual perception on IQA. Then, combining the gray-gradient co-occurrence matrix to calculate and statistically analyze image texture features, and using texture weighted averaging and the HVS complex object perception model, a method was proposed to quantify and calculate the contribution and impact of image texture information entropy and its visual perception on IQA. Next, the contrast value and detection threshold of each point in the image were calculated, subsequently combining the contrast sensitivity characteristics and their models, and masking properties of HVS, the contribution and impact of local contrast and visual perception of the image on IQA were quantified and calculated. Afterwards, four factors including sharpness, signal-to-noise ratio, proportion of high-frequency components, and resolution, were used to describe the clarity of the image, and their quantification and calculation methods were proposed to obtain the clarity index of the image. Finally, synthesizing four factors, an IQA model was constructed, and its measurement standards were quantified. Meanwhile, 6 430 distorted images from 6 open databases (TID2013, CSIQ, LIVE, IVC, SPAQ, and Koniq-10k) were tested and verified, and in terms of accuracy, complexity, generalization, and their comprehensive benefits, BCTCSP was compared with 28 existing and typical IQA models. The experimental results show that the accuracy PLCC of the proposed model reaches a minimum of 0.892 1, a maximum of 0.966 4 among the 6 databases, and the weighted PLCC of 6 databases reaches 0.917 4. Its comprehensive benefits are higher than those of the 28 existing IQA models. The comprehensive results indicate that the proposed model is an effective and high-performance NR-IQA model.
ZHAI G T , MIN X K . Perceptual image quality assessment: a survey [J]. Science China Information Sciences , 2020 , 63 ( 11 ): 211301 . doi: 10.1007/s11432-019-2757-1 http://dx.doi.org/10.1007/s11432-019-2757-1
ZHOU M L , LANG S J , ZHANG T P , et al . Attentional feature fusion for end-to-end blind image quality assessment [J]. IEEE Transactions on Broadcasting , 2023 , 69 ( 1 ): 144 - 152 . doi: 10.1109/tbc.2022.3204235 http://dx.doi.org/10.1109/tbc.2022.3204235
李佳欣 , 段发阶 , 傅骁 , 等 . 基于纹理奇异值分解的全参考图像质量评价 [J]. 光学 精密工程 , 2025 , 33 ( 1 ): 107 - 122 . doi: 10.37188/ope.20253301.0107 http://dx.doi.org/10.37188/ope.20253301.0107
LI J X , DUAN F J , FU X , et al . Full-reference image quality assessment based on texture singular value decomposition [J]. Opt. Precision Eng. , 2025 , 33 ( 1 ): 107 - 122 . (in Chinese) . doi: 10.37188/ope.20253301.0107 http://dx.doi.org/10.37188/ope.20253301.0107
CHANDLER D M , HEMAMI S S . VSNR: a wavelet-based visual signal-to-noise ratio for natural images [J]. IEEE Transactions on Image Processing , 2007 , 16 ( 9 ): 2284 - 2298 . doi: 10.1109/tip.2007.901820 http://dx.doi.org/10.1109/tip.2007.901820
WANG Z , BOVIK A C , SHEIKH H R , et al . Image quality assessment: from error visibility to structural similarity [J]. IEEE Transactions on Image Processing , 2004 , 13 ( 4 ): 600 - 612 . doi: 10.1109/tip.2003.819861 http://dx.doi.org/10.1109/tip.2003.819861
ZHANG L , ZHANG L , MOU X Q , et al . FSIM: a feature similarity index for image quality assessment [J]. IEEE Transactions on Image Processing , 2011 , 20 ( 8 ): 2378 - 2386 . doi: 10.1109/tip.2011.2109730 http://dx.doi.org/10.1109/tip.2011.2109730
XUE W F , ZHANG L , MOU X Q , et al . Gradient magnitude similarity deviation: a highly efficient perceptual image quality index [J]. IEEE Transactions on Image Processing , 2014 , 23 ( 2 ): 684 - 695 . doi: 10.1109/tip.2013.2293423 http://dx.doi.org/10.1109/tip.2013.2293423
ZHANG L , SHEN Y , LI H Y . VSI: a visual saliency-induced index for perceptual image quality assessment [J]. IEEE Transactions on Image Processing , 2014 , 23 ( 10 ): 4270 - 4281 . doi: 10.1109/tip.2014.2346028 http://dx.doi.org/10.1109/tip.2014.2346028
GAO Y X , MIN X K , CAO Y Q , et al . No-reference image quality assessment: obtain MOS from image quality score distribution [J]. IEEE Transactions on Circuits and Systems for Video Technology , 2025 , 35 ( 2 ): 1840 - 1854 . doi: 10.1109/tcsvt.2024.3485684 http://dx.doi.org/10.1109/tcsvt.2024.3485684
LIU Y , YIN X H , WANG Y , et al . HVS-based perception-driven No-reference omnidirectional image quality assessment [J]. IEEE Transactions on Instrumentation and Measurement , 2022 , 72 : 5003111 . doi: 10.1109/tim.2022.3232792 http://dx.doi.org/10.1109/tim.2022.3232792
SHEIKH H R , WANG Z , BOVIK A C . LIVE Image and Video Quality Assessment Database [EB/OL]. ( 2021 - 6 - 20 ). http://live.ece.utexas.edu/research/quality http://live.ece.utexas.edu/research/quality .
ZHANG L , ZHANG L , BOVIK A C . A feature-enriched completely blind image quality evaluator [J]. IEEE Transactions on Image Processing , 2015 , 24 ( 8 ): 2579 - 2591 . doi: 10.1109/tip.2015.2426416 http://dx.doi.org/10.1109/tip.2015.2426416
MA K D , LIU W T , ZHANG K , et al . End-to-end blind image quality assessment using deep neural networks [J]. IEEE Transactions on Image Processing , 2018 , 27 ( 3 ): 1202 - 1213 . doi: 10.1109/tip.2017.2774045 http://dx.doi.org/10.1109/tip.2017.2774045
SHEN W H , ZHOU M L , LUO J , et al . Graph-represented distribution similarity index for full-reference image quality assessment [J]. IEEE Transactions on Image Processing , 2024 , 33 : 3075 - 3089 . doi: 10.1109/tip.2024.3390565 http://dx.doi.org/10.1109/tip.2024.3390565
PONOMARENKO N , JIN L , IEREMEIEV O , et al . Tampere Image Database 2013 TID2013, version 1.0 [OL]. ( 2015-03-23 ). http://www.ponomarenko.info/tid2013. htm http://www.ponomarenko.info/tid2013.htm . doi: 10.1016/j.image.2014.10.009 http://dx.doi.org/10.1016/j.image.2014.10.009
LARSON E C , CHANDLER D M . The CSIQ Image Database [EB/OL]. ( 2021-6-20 ). http://vision. okstate.edu/?loc=csiq http://vision.okstate.edu/?loc=csiq .
YANG J C , BIAN Z L , LIU J C , et al . No-reference quality assessment for screen content images using visual edge model and AdaBoosting neural network [J]. IEEE Transactions on Image Processing , 2021 , 30 : 6801 - 6814 . doi: 10.1109/tip.2021.3098245 http://dx.doi.org/10.1109/tip.2021.3098245
YAO J C . Measurements of human vision contrast sensitivity to opposite colors using a cathode ray tube display [J]. Chinese Science Bulletin , 2011 , 56 ( 23 ): 2425 - 2432 . doi: 10.1007/s11434-011-4595-8 http://dx.doi.org/10.1007/s11434-011-4595-8
BARTEN P G J . Evaluation of subjective image quality with the square-root integral method [J]. Journal of the Optical Society of America A , 1990 , 7 ( 10 ): 2024 - 2031 . doi: 10.1364/josaa.7.002024 http://dx.doi.org/10.1364/josaa.7.002024
NADENAU M . Integration of Human Color Vision Models into High Quality Image Compression [D]. PhD thesis , École Polytechnique Fédérale de Lausanne, Switzerland , 2000 .
MADHUSUDANA P C , BIRKBECK N , WANG Y L , et al . Image quality assessment using contrastive learning [J]. IEEE Transactions on Image Processing , 2022 , 31 : 4149 - 4161 . doi: 10.1109/tip.2022.3181496 http://dx.doi.org/10.1109/tip.2022.3181496
曾海飞 , 韩昌佩 , 李凯 , 等 . 改进的梯度阈值图像清晰度评价算法 [J]. 激光与光电子学进展 , 2021 , 58 ( 22 ): 285 - 293 . doi: 10.3788/lop202158.2211001 http://dx.doi.org/10.3788/lop202158.2211001
ZENG H F , HAN C P , LI K , et al . Improved gradient threshold image sharpness evaluation algorithm [J]. Laser & Optoelectronics Progress , 2021 , 58 ( 22 ): 285 - 293 . (in Chinese) . doi: 10.3788/lop202158.2211001 http://dx.doi.org/10.3788/lop202158.2211001
江本赤 , 卞仕磊 , 史晨阳 , 等 . 基于色貌尺度相位一致性的全参考图像质量评价 [J]. 光学 精密工程 , 2023 , 31 ( 10 ): 1509 - 1521 . doi: 10.37188/ope.20233110.1509 http://dx.doi.org/10.37188/ope.20233110.1509
JIANG B C , BIAN S L , SHI C Y , et al . Full reference image quality assessment based on color appearance-based phase consistency [J]. Opt. Precision Eng. , 2023 , 31 ( 10 ): 1509 - 1521 . (in Chinese) . doi: 10.37188/ope.20233110.1509 http://dx.doi.org/10.37188/ope.20233110.1509
CALLET P L , Autrusseau F . Subjective Quality Assessment IRCCyN/IVC Database [EB/OL]. ( 2021-6-20 ). http://www2. irccyn. ec-nantes. fr/ivcdb/ http://www2.irccyn.ec-nantes.fr/ivcdb/ . doi: 10.4018/9781599048697.ch009 http://dx.doi.org/10.4018/9781599048697.ch009
FANG Y M , ZHU H W , ZENG Y , et al . Perceptual quality assessment of smartphone photography [C]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 13 - 19 , 2020 . Seattle, WA, USA. IEEE , 2020 .
HOSU V , LIN H H , SZIRANYI T , et al . KonIQ-10k: an ecologically valid database for deep learning of blind image quality assessment [J]. IEEE Transactions on Image Processing , 2020 , 29 : 4041 - 4056 . doi: 10.1109/tip.2020.2967829 http://dx.doi.org/10.1109/tip.2020.2967829
WU J J , MA J P , LIANG F H , et al . End-to-end blind image quality prediction with cascaded deep neural network [J]. IEEE Transactions on Image Processing , 2020 , 29 : 7414 - 7426 . doi: 10.1109/tip.2020.3002478 http://dx.doi.org/10.1109/tip.2020.3002478
SU S L , YAN Q S , ZHU Y , et al . Blindly assess image quality in the wild guided by a self-adaptive hyper network [C]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 13 - 19 , 2020 . Seattle, WA, USA. IEEE , 2020 .
YOU J Y , KORHONEN J . Transformer for image quality assessment [C]. 2021 IEEE International Conference on Image Processing (ICIP). 19-22,2021 , Anchorage, AK, USA. IEEE , 2021 : 1389 - 1393 . doi: 10.1109/icip42928.2021.9506075 http://dx.doi.org/10.1109/icip42928.2021.9506075
YANG Y , DING Y Q , CHENG M , et al . No-reference quality assessment for contrast-distorted images based on gray and color-gray-difference space [J]. ACM Transactions on Multimedia Computing, Communications, and Applications , 2023 , 19 ( 2 ): 1 - 20 . doi: 10.1145/3555355 http://dx.doi.org/10.1145/3555355
SUN S M , YU T , XU J H , et al . GraphIQA: learning distortion graph representations for blind image quality assessment [J]. IEEE Transactions on Multimedia , 2022 , 25 : 2912 - 2925 . doi: 10.1109/tmm.2022.3152942 http://dx.doi.org/10.1109/tmm.2022.3152942
BAKUROV I , BUZZELLI M , SCHETTINI R , et al . Full-reference image quality expression via genetic programming [J]. IEEE Transactions on Image Processing , 2023 , 32 : 1458 - 1473 . doi: 10.1109/tip.2023.3244662 http://dx.doi.org/10.1109/tip.2023.3244662
DING K Y , ZHONG R J , WANG Z H , et al . Adaptive structure and texture similarity metric for image quality assessment and optimization [J]. IEEE Transactions on Multimedia , 2023 , 26 : 5398 - 5409 . doi: 10.1109/tmm.2023.3333208 http://dx.doi.org/10.1109/tmm.2023.3333208
LIAO X R , WEI X K , ZHOU M L , et al . Image quality assessment: measuring perceptual degradation via distribution measures in deep feature spaces [J]. IEEE Transactions on Image Processing , 2024 , 33 : 4044 - 4059 . doi: 10.1109/tip.2024.3409176 http://dx.doi.org/10.1109/tip.2024.3409176
WANG Z S , YUAN L , ZHAI G T . Channel attention for No-reference image quality assessment in DCT domain [J]. IEEE Signal Processing Letters , 2024 , 31 : 1274 - 1278 . doi: 10.1109/lsp.2024.3392671 http://dx.doi.org/10.1109/lsp.2024.3392671
CHEN B L , ZHU H W , ZHU L Y , et al . Debiased mapping for full-reference image quality assessment [J]. IEEE Transactions on Multimedia , 2025 , 27 : 2638 - 2649 . doi: 10.1109/tmm.2025.3535280 http://dx.doi.org/10.1109/tmm.2025.3535280
BEZERRA S A C , BEZERRA JÚNIOR S A C , DE S PIO J L , et al . Perceptual error logarithm: an efficient and effective analytical method for full-reference image quality assessment [J]. IEEE Access , 2025 , 13 : 68587 - 68606 . doi: 10.1109/access.2025.3560918 http://dx.doi.org/10.1109/access.2025.3560918
HU B , CHEN W Z , ZHENG J , et al . No-reference image quality assessment via inter-level adaptive knowledge distillation [J]. IEEE Transactions on Broadcasting , 2025 , 71 ( 2 ): 581 - 592 . doi: 10.1109/tbc.2025.3549985 http://dx.doi.org/10.1109/tbc.2025.3549985
MA P C , LIU L X , XIAO C Z , et al . Omnidirectional image quality assessment with mutual distillation [J]. IEEE Transactions on Broadcasting , 2025 , 71 ( 1 ): 264 - 276 . doi: 10.1109/tbc.2024.3503435 http://dx.doi.org/10.1109/tbc.2024.3503435
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
