Improvements of image haze removal algorithm and its subjective and objective performance evaluation

Jia-tong LI; Yu-jin ZHANG

doi:10.3788/OPE.20172503.0735

您当前的位置：

首页 >

文章列表页 >

Improvements of image haze removal algorithm and its subjective and objective performance evaluation

更新时间：2020-07-07

- Improvements of image haze removal algorithm and its subjective and objective performance evaluation
- Optics and Precision Engineering Vol. 25, Issue 3, Pages: 735-741(2017)
- 作者机构：
  
  清华大学电子工程系, 北京 100084
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20172503.0735
  CLC： TP391.4
- Received：21 December 2016，
  
  Accepted：15 January 2017，
  
  Published：25 March 2017
- 稿件说明：
移动端阅览
Jia-tong LI, Yu-jin ZHANG. Improvements of image haze removal algorithm and its subjective and objective performance evaluation[J]. Optics and precision engineering, 2017, 25(3): 735-741.
DOI：

Jia-tong LI, Yu-jin ZHANG. Improvements of image haze removal algorithm and its subjective and objective performance evaluation[J]. Optics and precision engineering, 2017, 25(3): 735-741. DOI： 10.3788/OPE.20172503.0735.

摘要

本文主要研究了图像去雾技术以提高由于雾霾影响而导致的失真图像的主客观质量。对基于暗通道先验和大气散射模型的去雾算法进行了改进，设计了新的天空区域计算和透射率阈值确定方法，通过增强结果图的对比度和调整亮度，进一步降低了算法的失真。还通过对图像加雾，分别从主观质量评价和以结构相似度作为客观标准的客观评价两方面，用数理统计方法比较了各个相关算法的性能。实验表明，所提算法有效地降低了图像的失真（评价分最高），使去雾图像有较高的主观质量（总体评价分并列最高）。

Abstract

In this paper

a study was conducted in the image haze removal to improve the subjective quality of images distorted due to haze. First

the haze removal algorithm based on dark channel prior and atmospheric scattering model was improved

and a new method for calculation of the sky area and determination of the transmittance threshold was designed; then the distortion of such algorithm was further lowered by enhancing the image contrast and adjusting the brightness; finally

mathematical statistic method was used to compare the performance of each relevant algorithm by adding haze to the image

with subjective quality assessment and structural similarity as the objective criterion. The experiment in the existing haze images and the actually shot images indicates that the proposed algorithm can effectively reduce the distortion of images (with the highest assessment scores)

thus keeping the haze removed images with relatively high subjective quality (tying first in the overall assessment).

关键词

Keywords

references

HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior [C]. Proc. CVPR, 2009, 1956-1963.

郭璠, 唐琎, 蔡自兴.基于融合策略的单幅图像去雾算法[J].通信学报, 2014, 35(7): 199-207, 214.

GUO F, TANG J, CAI Z X. Single image defogging based on fusion strategy [J]. Journal on Communications, 2014, 35(7): 199-207, 214. (in Chinese)

褚宏莉, 李元祥, 周则明, 等.基于黑色通道的图像快速去雾优化算法[J].电子学报, 2013, 41(4): 791-797.

CHU H L, LI Y X, ZHOU Z M, et al.. Optimized fast dehazing method based on dark channel prior [J]. Acta Electronica Sinica, 2013, 41(4): 791-797.(in Chinese)

周理, 毕笃彦, 何林远.融合变分偏微分方程的单幅彩色图像去雾[J].光学精密工程, 2015, 23(5): 1466-1473.

ZHOU L, BI D Y, HE L Y. Single color image dehazing using variational partial differential equation [J]. Opt. Precision Eng., 2015, 23(5): 1466-1473. (in Chinese)

甘佳佳, 肖春霞.结合精确大气散射图计算的图像快速去雾[J].中国图象图形学报, 2013, 18(5): 583-590.

GAN J J, XIAO CH X. Fast image dehazing based on accurate scattering map [J].Journal of Image and Graphics, 2013, 18(5): 583-590. (in Chinese)

王一帆, 尹传历, 黄义明, 等.基于双边滤波的图像去雾[J].中国图象图形学报, 2014, 19(3): 386-392.

WANG Y F, YIN CH L, HUANG Y M, et al.. Image haze removal using a bilateral filter [J]. Journal of Image and Graphics, 2014, 19(3): 386-392. (in Chinese)

王伟鹏, 戴声奎.结合图像融合与分割的快速去雾[J].中国图象图形学报, 2014, 19(8): 1155-1161.

WANG W P, DAI SH K.Fast haze removal method based on image fusion and segmentation [J]. Journal of Image and Graphics, 2014, 19(8): 1155-1161. (in Chinese)

张冰冰, 戴声奎, 孙万源.基于暗原色先验模型的快速去雾算法[J].中国图象图形学报, 2013, 18(2): 184-188.

ZHANG B B, DAI SH K, SUN W Y. Fast image haze-removal algorithm based on the prior dark-channel [J]. Journal of Image and Graphics, 2013, 18(2): 184-188. (in Chinese)

史德飞, 李勃, 丁文, 等.基于地物波谱特性的透射率-暗原色先验去雾增强算法[J].自动化学报, 2013, 39(12): 2064-2070.

SHI D F, LI B, DING W, et al.. Haze removal and enhancement using transmittance-dark channel prior based on object spectral characteristic [J]. Acta Automatica Sinica, 2013, 39(12): 2064-2070. (in Chinese)

宋颖超, 罗海波, 惠斌, 等.尺度自适应暗通道先验去雾方法[J].红外与激光工程, 2016, 45(9): 286-297.

SONG Y CH, LUO H B, HUI B, et al.. Haze removal using scale adaptive dark channel prior [J]. Infrared and Laser Engineering, 2016, 45(9): 286-297. (in Chinese)

HE K M, SUN J, TANG X O. Guided image filtering [C]. Proc. ECCV, 2010, 1-14.

WANG Z, BOVIK A C, SHEIKH H R, et al.. Image quality assessment: from error visibility to structural similarity [J]. IEEE Trans. on Image Processing, 2004, 13(4): 600-612.

WANG P, BICAZAN D, GHOSH A. Rerendering landscape photographs [C]. Proc. CVMP, 2014, 13.

方雯, 刘秉瀚.多尺度暗通道先验去雾算法[J].中国体视学与图像分析, 2013, 18(3): 230-237.

FANG W, LIU B H.Image dehazing using multiscale dark channel prior [J]. Chinese Journal of Stereology and Image Analysis, 2013, 18(3): 230-237. (in Chinese)

赵秀芝, 谢德红, 潘康俊.彩色视觉相似性图像评价方法[J].计算机应用, 2013, 33(6): 1715-1718.

ZHAO X ZH, XIE D H, PAN K J.Color image quality assessment algorithm based on color structural similarity [J]. Journal of Computer Applications, 2013, 33(6): 1715-1718. (in Chinese)

数学百科全书编译委员会.数学百科全书[M].北京:科学出版社, 2000, 5:45-46.

The Committee of Encyclopedia of Mathematics. Encyclopedia of Mathematics [M].Beijing:Science Press, 2000, 5:45-46.(in Chinese)

Views

416

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Image dark channel prior haze removal based on minimum filtering and guided filtering

Related Author

Wang Wei-xing

Xiao Xiang

Chen Liang-qin

Related Institution

College of Physics and Information Engineering, Fuzhou University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰