基于双向扩散与冲击滤波的雾天图像增强算法

doi:10.19678/j.issn.1000-3428.0048606

摘要/Abstract

摘要： 由传统暗原色先验图像去雾方法得到的图像偏暗,质量不高。为此,建立包含双向扩散和自适应冲击滤波的电报方程模型。将边缘检测器与冲击滤波相结合,权重系数由图像的梯度特征自适应选取以构成锐化项,使图像根据不同区域的特征自适应地增强。加入保真项确保增强图像保留原图像的主要特征,防止图像失真。在此基础上,用有限差分法对模型进行数值求解从而得到增强图像。对雾天图像进行的实验结果表明,相对基于暗原色先验理论的去雾算法、基于自适应冲击滤波的增强算法,该算法在视觉上有明显的增强效果,能够提高图像亮度,降低噪声影响,改善图像质量。

关键词: 雾天图像增强, 电报方程, 暗原色先验, 双向扩散, 自适应冲击滤波, 边缘检测器

Abstract: The image obtained by the traditional dark channel prior image defogging fog method is dark and the quality is not high.To solve this problem,a telegraph equation model containing bidirectional diffusion and adaptive shock filtering is established.The edge detector is combined with impulse filtering and the weight coefficient is adaptively selected from the gradient feature of the image to form the sharpening term,so that the image can be enhanced adaptively according to the characteristics of different regions.Adding fidelity items to ensure that the enhanced image preserves the main features of the original image and prevents distortion of the image.On this basis,the finite difference method is used to solve the model numerically to obtain the enhanced image.Experimental results on foggy images show that,compared with the defogging algorithm based on dark channel prior theory and the enhancement algorithm based on adaptive impulse filtering,the proposed algorithm has obvious visual enhancement effect,which can improve the image brightness,reduce the noise effect and improve the image quality.

Key words: foggy image enhancement, telegraph equation, dark channel prior, bidirectional diffusion, adaptive shock filtering, edge detector

中图分类号:

TP391.41

张然,赵凤群. 基于双向扩散与冲击滤波的雾天图像增强算法[J]. 计算机工程, 2018, 44(10): 221-227.

ZHANG Ran,ZHAO Fengqun. Foggy Image Enhancement Algorithm Based on Bidirectional Diffusion and Shock Filtering [J]. Computer Engineering, 2018, 44(10): 221-227.

参考文献

［1］WONG C Y,JIANG G,RAHMAN M A,et al.Histogram equalization and optimal profile compression based approach for colour image enhancement［J］.Journal of Visual Communication and Image Representa-tion,2016,38:802-813.br/ ［2］MU D,CHAO X,GE H.Hybrid genetic algorithm based image enhancement technology［C］//Proceedings of 2011 IEEE International Conference on Internet Technology and Applications.Washington D.C.,USA:IEEE Press,2011:1-4.br/ ［3］WANG J W,LE N T,LEE J S,et al.Color face image enhancement using adaptive singular value decomposition in Fourier domain for face recognition［J］.Pattern Recognition,2016,57(C):31-49.br/ ［4］GORGEL P,SERTBAS A,UCAN O N.A wavelet-based mammographic image denoising and enhancement with homomorphic filtering［J］.Journal of Medical Systems,2010,34(6):993-1002.br/ ［5］EIN SHOKA A,KELASH H M,FARAGALLAH O S.Enhancement of IR images using homomorphic filtering in fast discrete curvelet transform［J］.International Journal of Computer Applications,2014,96(8):22-25.br/ ［6］WANG Y,WANG H,YIN C,et al.Biologically inspired image enhancement based on Retinex［J］.Neuro-computing,2016,177:373-384.br/ ［7］李权合,毕笃彦,马时平,等.基于Retinex和视觉适应性的图像增强［J］.中国图象图形学报,2010,15(12):1728-1732.br/ ［8］张新龙,汪荣贵,张璇,等.雾天图像增强计算模型及算法［J］.中国图象图形学报,2011,16(8):1359-1368.br/ ［9］XIAO J,PANG G,ZHANG Y,et al.Adaptive shock filter for image super-resolution and enhancement［J］.Journal of Visual Communication and Image Representa-tion,2016,38:168-177.br/ ［10］唐磊,赵春霞,王鸿南,等.路面图像增强的多偏微分方程融合法［J］.中国图象图形学报,2008,13(9):1661-1666.br/ ［11］LI B,XIE W.Adaptive fractional differential approach and its application to medical image enhancement［J］.Computers and Electrical Engineering,2015,45:324-335.br/ ［12］FATTAL R.Single image dehazing［J］.ACM Transactions on Graphics,2008,27(3):721-729.br/ ［13］EBTESAM M A,PENG G,HONG W.Fast image haze-removal algorithm based on the prior dark-channel［J］.Journal of Image and Graphics,2016,18(2):47-55.br/ ［14］陈俊君,徐冰.雾霾天气条件下的机器视觉图像清晰化研究［J］.计算机工程,2017,43(2):280-285.br/ ［15］桓宗圣,陶青川,田旺.野外视频监控图像去雾算法研究［J］.计算机工程,2014,40(2):240-245.br/ ［16］HE K,SUN J,TANG X.Single image haze removal using dark channel prior［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(12):2341-2353.br/ ［17］PARK H.An improved single image haze removal algorithm using image segmentation［J］.IEICE Transactions on Informationand Systems,2014,92:2554-2558.br/ ［18］LI Y,ZHANG Y,GENG A,et al.Infrared image enhancement based on atmospheric scattering model and histogram equalization［J］.Opticsand Laser Technology,2016,83:99-107.br/ ［19］OSHER S,RUDIN L I.Feature-oriented image enhancement using shock filters［J］.SIAM Journal on Numerical Analysis,1990,27(4):919-940.br/ ［20］NARASIMHAN S G,NAYAR S K.Contrast restoration of weather degraded images［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(6):713-724.br/ ［21］ZHANG W,LI J,YANG Y.A class of nonlocal tensor telegraph-diffusion equations applied to coherence enhancement［J］.Computers and Mathematics with Applications,2014,67(8):1461-1473.br/ ［22］GILBOA G,SOCHEN N,ZEEVI Y Y.Image sharpening by flows based on triple well potentials［J］.Journal of Mathematical Imaging and Vision,2004,20(1):121-131.br/ ［23］GILBOA G,SOCHEN N,ZEEVI Y Y.Real and complex PDE-based schemes for image sharpening and enhancement［J］.Advances in Imaging and Electron Physics,2005,136(4):80-109.br/ ［24］陈利霞.基于PDE的图像恢复模型和图像增强与分割算法研究［D］.西安:西安电子科技大学,2010.br/ ［25］BAI Y,ZHANG Q.Patch similarity modulus and difference curvature based fourth-order partial differential equation for image denoising［J］.Mathematical Problems in Engineering,2015(4):1-12.br/ ［26］CHEN Q,MONTESINOS P,SUN Q S,et al.Adaptive total variation denoising based on difference curvature［J］.Image and Vision Computing,2010,28(3):298-306.br/

[1]	王红茹, 张弓, 卢道华, 王佳. 基于背景光估计与颜色修正的水下图像增强[J]. 计算机工程, 2020, 46(10): 253-258.
[2]	杨斌,林志贤,郭太良. 基于改进容差机制的图像去雾算法[J]. 计算机工程, 2019, 45(1): 226-232.
[3]	陈俊君,徐冰. 雾霾天气条件下的机器视觉图像清晰化研究[J]. 计算机工程, 2017, 43(2): 280-285,292.
[4]	刘建磊. 基于变分模型的图像去雾方法[J]. 计算机工程, 2017, 43(11): 216-220,226.
[5]	王甫，郑亚平，刘天琪. 双向扩散机制融合时间延迟的图像加密算法[J]. 计算机工程, 2014, 40(7): 225-229,241.
[6]	桓宗圣，陶青川，田旺. 野外视频监控图像去雾算法研究[J]. 计算机工程, 2014, 40(2): 240-245.
[7]	徐少平;张华;江顺亮;熊宇虹. 抗高噪声彩色图像的Canny边缘检测器[J]. 计算机工程, 2009, 35(14): 22-24.