SUN Meiwei.Enhancement dark channel algorithm of fog image based onthe double -tolerance mechanisms[J].Journal of Yanbian University,2020,46(02):150-155.
基于双容差机制的快速暗原色理论雾天图像增强算法
- Title:
- Enhancement dark channel algorithm of fog image based on the double -tolerance mechanisms
- 文章编号:
- 1004-4353(2020)02-0150-06
- Keywords:
- dark channel theory; image enhancement; double -tolerance mechanisms; brightness region segmentation
- 分类号:
- TP751
- 文献标志码:
- A
- 摘要:
- 针对经典暗原色理论算法在处理雾天图像时出现的色调和亮度失真问题,提出了一种基于双容差机制的快速暗原色理论雾天图像增强算法.该算法首先通过容差机制分割图像,并根据阈值判断图像的明亮和非明亮区; 然后引入改进的高斯平滑滤波对透射率图像进行平滑处理,以此优化透射率图像; 最后通过引入容差机制对透射率图像进行修正,以此得到更加清晰的图像.将本文方法与经典的暗原色算法进行对比表明,本文方法在亮度、颜色保真度和时间效率上均优于暗原色算法,因此本文方法可为雾天图像的处理提供参考.
- Abstract:
- To deal with the image hue and brightness distortion problems in the classic dark channel theory algorithm, enhancement dark channel algorithm of color fog image based double -tolerance mechanisms is proposed. Firstly, the image is segmented by the tolerance mechanism and distinguishes between bright areas and dark channel areas according to the threshold. Then, the modified Gaussian filtering is introduced, and proposes the transmission image. At last, the transmission image is modified by introducing tolerance mechanism to get a clear image. The comparison between this algorithm and the classical dark primary color algorithm shows that this algorithm is better than dark primary color algorithm in brightness, color fidelity and time efficiency. Therefore, our algorithm can provide a reference for the image dehazing.
参考文献/References:
[1] WANG W, LI Z, WU S, et al. Hazy image decolorization with color contrast[J]. IEEE Transactions on Image Processing, 2019,29:1776 -1787.
[2] PIZER S M, AMBURN E P, AUSTIN J D, et al. Adaptive histogram equalization and its variations[J]. Computer Vision Graphics and Image Processing, 1987,39(3):355-368.
[3] BNARNARD J J, FUNT B V. Analysis and improvement of multi -scale retinex[C]//5th Color and Imaging Conference Final Program and Proceedings. Scottsdale: Soc Imaging Sci Technol, 1997:221-226.
[4] HE K, SUN J, TANG X. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010,33(12):2341-2353.
[5] MENG G, WANG Y, DUAN J, et al. Efficient image dehazing with boundary constraint and contextual regularization[C]//Proceedings of the IEEE International Conference on Computer Vision. Sydney: IEEE, 2013:617-624.
[6] 高银,云利军,石俊生,等.基于TV模型的暗原色理论雾天图像复原算法[J].中国激光,2015(8):273-278.
[7] 高银,云利军,石俊生,等.基于四阶PDE模型的暗原色理论雾天图像增强算法[J].南京理工大学学报(自然科学版),2015(5):544-549.
[8] GAO Y, SU Y, LI Q, et al. Single fog image restoration with multi -focus image fusion[J]. Journal of Visual Communication and Image Representation, 2018,55:586-595.
[9] HE K, SUN J, TANG X. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012,35(6):1397-1409.
[10] WU Q, ZHANG J, REN W, et al. Accurate transmission estimation for removing haze and noise from a single image[J]. IEEE Transactions on Image Processing, 2019,29:2583-2597.
[11] GEUSEBROEK J M, SMEULDERS A W M, VAN DE WEIJER J. Fast anisotropic gauss filtering[J]. IEEE Transactions on Image Processing, 2003,12(8):938-943.
备注/Memo
收稿日期: 2019-11-25
作者简介: 孙美卫(1975—),女,讲师,研究方向为数字图像处理.