基于视觉损失的低照度增强图像多准则质量评价方法

doi:10.11896/jsjkx.241100114

摘要/Abstract

摘要： 低照度图像增强能提高图像的感知度和可解释性,对增强后图像的评价是衡量图像信息可靠性的有效手段,并对增强算法的参数选择、模型调整也有指导作用。但目前已有的图像质量评价方法没有针对低照度增强图像,导致评价结果与主观感受存在分歧。根据人眼视觉感知,分析增强后图像的视觉损失原因,提出了一种基于视觉损失的低照度增强图像多准则质量评价方法(Multi-criteria Based Low-light Enhanced Image Quality Assessment,MC-LEIQA)。该方法针对低照度图像增强过程中出现的亮度增益不足、伪影、伪轮廓和颜色偏移等视觉损失现象,以基于KL散度的自适应亮度增益度、基于方差与梯度的结构恢复度和颜色恢复度设计评价准则,并引入亮度自动感知的正偏移修正系数来实现低照度增强图像质量的准确性评价。通过消融实验验证了选取的评价指标的合理性和必要性,并进一步与主流图像质量评价方法在公开数据集上进行对比实验,结果表明所提方法针对低照度增强图像具备更高的评价准确性和有效性。

关键词: 低照度增强图像, 图像质量评价, 多准则融合, 图像视觉损失分析

Abstract: Low-light image enhancement improves the perception and interpretability of the images,and the assessment of the enhanced images impacts the image’s reliability and playing a guiding role in parameter selection and model adjustment of the enhancement algorithm.However,the existing image quality assessments are not completely for low-light enhanced images,which lead to discrepancies between the assessment results and subjective perceptions.In this paper,a multi-criterion based Low-light Enhanced Image Quality Assessment(MC-LEIQA) is proposedby analyzing of the visual loss factors based on human visual perception.According to the visual artifacts such as insufficient brightness gain,artifacts,false contours,and color shifts that occur during the process of enhancing low-light images,MC-LEIQA designs an assessment criterion based on the fusion of adaptive brightness gain degree using Kullback-Leibler divergence,structural recovery degree based on variance and gradient,and color recovery degree.Additionally,it introduces a correction coefficient for positive offset that incorporates automatic brightness perception to achieve accurate quality assessment of low-light enhanced images.Ablation experiments demonstrate the rationality and necessity of the selected assessment metrics in this study.Furthermore,comparative experiments with the classical image quality assessment methods on public datasets further validate that the proposed method exhibits higher assessment accuracy and effectiveness for low-light enhanced images.

Key words: Low-light image enhancement, Image quality assessment, Multi-criteria fusion, Image visual loss analysis

中图分类号:

TP391.41

陈岐, 孙瑾, 汪纪钢, 黄长城. 基于视觉损失的低照度增强图像多准则质量评价方法[J]. 计算机科学, 2025, 52(11A): 241100114-7. https://doi.org/10.11896/jsjkx.241100114

CHEN Qi, SUN Jin, WANG Jigang, HUANG Changcheng. Multi-criteria Quality Assessment Method for Low-illumination Enhanced Images Based on Visual Loss[J]. Computer Science, 2025, 52(11A): 241100114-7. https://doi.org/10.11896/jsjkx.241100114

参考文献

[1]LIU Y H.Research on image enhancement and quality assessment based on biological visual perception mechanism[D].Chengdu:University of Electronic Science and Technology of China,2018.
[2]WEI D,WANG P Q,WANG Z B,et al.Adaptive Image En-hancement Method for Coal-mine Underground Image Based on No-reference Quality Evaluation[J].IEEE Transactions on Instrumentation and Measurement,2024,73:1-17.
[3]LI A B,WU J J,LIU Y X,et al.Blind Image Quality Assessment Based on Perceptual Comparison[J].IEEE Transactions on Multimedia,2024,26:1-12.
[4]QU Q,LIANG H X,CHEN X M,et al.NeRF-NQA:No-Reference Quality Assessment for Scenes Generated by NeRF and Neural View Synthesis Methods[J].IEEE Transactions on Visualization and Computer Graphics,2024,30(5):2129-2139.
[5]SHEIKH H R,BOVIK A C.No-Reference Quality Assessment Using Natural Scene Statistics:JPEG2000[J].IEEE Transactions on Image Processing,2004,14(11):1918-1927.
[6]YU T H,LIU M Y.Image quality assessment method based on human visual system[J].Journal of Beijing University of Posts and Telecommunications,2023,46(2):129-136.
[7]YU M Z,TANG Z J,LIANG X P,et al.Perceptual HashingWith Deep and Texture Features[J].IEEE Multimedia,2024,31:65-75.
[8]ZHANG W X,MA K D,ZHAI G T,et al.Task-Specific Normalization for Continual Learning of Blind Image Quality Models[J].IEEE Transactions on Image Processing,2024,33:1898-1910.
[9]CHEN B L,ZHU H W,ZHU L Y,et al.Deep Feature StatisticsMapping for Generalized Screen Content Image Quality Assessment[J].IEEE Transactions on Image Processing,2024,33:3227-3241.
[10]CATANIA L,ALLEGRA D.Redefining Visual Quality:TheImpact of Loss Functions on INR-Based Image Compression[C]//IEEE International Conference on Image Processing(ICIP 2024).2024:1973-1979.
[11]HUYNH-THU Q,GHANBARI M.Scope of validity of PSNR in image/video quality assessment[J].Electronics Letters,2008,44(13):800-801.
[12]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.
[13]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.
[14]ZHANG R,ISOLA P,EFROS A A,et al.The Unreasonable Effectiveness of Deep Features as a Perceptual Metric[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2018:586-595.
[15]JIANG B,BIAN S L,SHI C Y,et al.Full-reference image quality assessment based on chroma scale phase consistency[J].Optics and Precision Engineering,2023,31(10):1509-1521.
[16]WANG K,YANG H,PAN Z K,et al.Full-reference stereoscopic image quality assessment model based on monocular and binocular visual information [J].Computer Engineering,2022,48(2):207-214,223.
[17]KIM H,YIM C.Swin Transformer Fusion Network for Image Quality Assessment[J].IEEE Access,2024,12:57741-57754.
[18]WU C,LIAO X F,YUE H,et al.Full-Reference Image Quality Assessment via Low-Level and High-Level Feature Fusion[J].International Journal of Pattern Recognition & Artificial Intelligence,2023,37(11):1-20.
[19]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.
[20]LAN X,JIA F,ZHUANG X,et al.Hierarchical degradation-aware network for full-reference image quality assessment [J].Information Sciences,2024(690):1-14.
[21]HAN H N,QIAN F,LU J W,et al.Image dehazing methodquality assessment[J].Optical and Precision Engineering,2022,30(6):721-733.
[22]XIA Y M,WANG Y F,WANG C.Phase consistency guidedfull-reference panoramic image quality assessment algorithm [J].Journal of Image and Graphics,2021,26(7):1625-1636.
[23]GU X J,LI Y B,LING H.LIME:Low-light image enhancement via illumination map estimation[J].IEEE Transactions on Image Processing,2016,26(2):982-993.
[24]WANG S H,ZHENG J,HU H M,et al.Naturalness preservedenhancement algorithm for non-uniform illumination images[J].IEEE Transactions on Image Processing,2013,22(9):3538-3548.
[25]LI C,GUO C,LOY C C.Learning to enhance low-light image via zero-reference deep curve estimation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,61:650-662.
[26]GUAN Y,CHEN X A,TIAN J D,et al.Low-light imageenhancement based on multi-exposure images generation[J].Robot,2023,45(4):422-430.
[27]LIN L P,YANG Z Y,WU M C,et al.Improved CLAHE image enhancement algorithm and FPGA implementation[J].Electronic Measurement Technology.2024,47(10):126-133.
[28]GU K,TAO D C,QIAO J F,et al.Learning a no-reference quality assessment model of enhanced images with big data[J].IEEE Transactions on Neural Networks and Learning Systems,2018,29(4):1301-1313.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed