全参考型低照度图像质量评价池化策略

宋明珠; 曲宏松; 李兰民; 张贵祥; 金光

doi:10.3788/OPE.20172514.0160

您当前的位置：

首页 >

文章列表页 >

全参考型低照度图像质量评价池化策略

更新时间：2020-08-13

- 全参考型低照度图像质量评价池化策略
- Pooling strategy for quality evaluation of full-reference model low illumination image
- 光学精密工程 2017年25卷第12z期页码：160-167
- 作者机构：
  
  1. 中国科学院长春光学精密机械与物理研究所,吉林长春,中国,130033
  2. 中国科学院大学北京,中国,100049
  3. 山东航天电子技术研究所,山东烟台,264670
- 作者简介：
- 基金信息：
  
  科技部重点专项资金资助项目（No.2016YFB0501202）();吉林省科技发展计划资助项目（No.20170101164JC）()
- DOI：10.3788/OPE.20172514.0160
  中图分类号： TP391.4
- 收稿日期：2017-08-28，
  
  修回日期：2017-09-21，
  
  纸质出版日期：2017-12-31
- 稿件说明：
移动端阅览
宋明珠, 曲宏松, 李兰民等. 全参考型低照度图像质量评价池化策略[J]. 光学精密工程, 2017,25(12z): 160-167

SONG Ming-zhu, QU Hong-song, LI Lan-min etc. Pooling strategy for quality evaluation of full-reference model low illumination image[J]. Editorial Office of Optics and Precision Engineering, 2017,25(12z): 160-167
宋明珠, 曲宏松, 李兰民等. 全参考型低照度图像质量评价池化策略[J]. 光学精密工程, 2017,25(12z): 160-167 DOI： 10.3788/OPE.20172514.0160.

SONG Ming-zhu, QU Hong-song, LI Lan-min etc. Pooling strategy for quality evaluation of full-reference model low illumination image[J]. Editorial Office of Optics and Precision Engineering, 2017,25(12z): 160-167 DOI： 10.3788/OPE.20172514.0160.

摘要

为了设计一种更适用于低照度成像条件下的全参考型图像质量评价方法，针对人眼视觉注意特性及低照度成像的失真特点，提出了基于上下文感知的低照度图像质量评价池化策略。通过不同失真类型下采取不同空间尺度特定权重的方式对图像中的主要对象及其上下文信息进行加权，获取的权重图用于池化特征相似性度量的局部质量图，进而获取最终的质量得分。实验结果表明，本文方法更满足人眼视觉特性，均方根误差达0.623 1，皮尔森线性相关系数达0.885 7，肯德尔等级相关系数达0.704 9，斯皮尔曼等级相关系数达0.885 6，与其他5种主流方法对比，具有最优的主观视觉一致性；同时，针对低照度图像主要的失真类型，4种客观评价指标均优于对比方法。

Abstract

In order to design method for image quality evaluation of full-reference model more suitable under condition of low illumination imaging

aimed at attention characteristic for human vision and distortion characteristic of low illumination imaging

pooling strategy for quality evaluation with low illumination image based on context-aware was proposed. Through different distortion types

main object and its context information in image were provided with weighting by adopting specific weight methods in different spaces

and obtained Weighting Graph was used for Local Quality Diagram for similarity measurement of pooling characteristic to obtain final quality score. The experimental result shows that method in the Thesis is more satisfying to human visual characteristic

and root-mean-square error reaches 0.623 1

with Pearson linear correlation coefficient reaching 0.885 7

Kendall rank correlation coefficient reaching 0.704 9

Spearman rank correlation coefficient reaching 0.885 6. Compared with other five mainstream methods

it has the optimal subjective visual consistence; at the same time

aimed at main distortion type of low illumination image

four kinds of objective evaluation indexes are superior to contrast method.

关键词

Keywords

references

WANG ZH, 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.

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.

LI Q H, FANG Y M, XU J T. A novel spatial pooling strategy for image quality assessment[J]. Journal of Computer Science and Technology, 2016, 31(2):225-234.

WANG Z, SIMONCELLI E P, BOVIK A C. Multiscale structural similarity for image quality assessment[C]. Conference Record of the 37th Asilomar Conference on Signals, Systems and Computers, IEEE, 2003:1398-1402.

CHEN G H, YANG CH L, XIE SH L. Gradient-based structural similarity for image quality assessment[C]. Proceedings of 2006 IEEE International Conference on Image Processing, IEEE, 2006:2929-2932.

HUANG Y, CHEN X, DING X H. A harmonic means pooling strategy for structural similarity index measurement in image quality assessment[J]. Multimedia Tools and Applications, 2016, 75(5):2769-2780.

刘国军, 高立霞, 陈丽奇. 广义平均的全参考型图像质量评价池化策略[J]. 光学精密工程, 2017, 25(3):742-748. LIU G J, GAO L X, CHEN L Q. Pooling strategy for full-reference IQA via general means[J]. Opt. Precision Eng., 2017, 25(3):742-748. (in Chinese)

ZHANG ZH, LIU SH, LI A. Image quality assessment via adaptive pooling[C]. Proceedings of the 2015 International Conference on Communications, Signal Processing, and Systems, Springer, 2016:709-714.

姚军财, 刘贵忠. 结合人眼对比度敏感视觉特性的视频质量客观评价[J]. 光学精密工程, 2016, 24(3):659-667. YAO J C, LIU G ZH. Video quality objective assessment combined contrast sensitivity characteristics of human visual system[J]. Opt. Precision Eng., 2016, 24(3):659-667. (in Chinese)

GOFERMAN S, ZELNIK-MANOR L, TAL A. Context-Aware saliency detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(10):1915-1926.

SHEIKH H R, BOVIK A C. Image information and visual quality[J]. IEEE Transactions on Image Processing, 2006, 15(2):430-444.

HORE A, ZIOU D. Image quality metrics:PSNR vs. SSIM[C]. Proceedings of the 20th International Conference on Pattern Recognition, IEEE, 2010:2366-2369.

浏览量

425

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

晶圆定位标记光学成像的自适应聚焦评价

基于纹理奇异值分解的全参考图像质量评价

用于夜间撒布地雷探测的可见光偏振图像融合

基于色貌尺度相位一致性的全参考图像质量评价

基于特定偏振态成像的水下图像去散射方法