BAO Zhaohua,GAO Yuxiang,XIA Chaoyu,et al.Night Image Enhancement Algorithm based on Improved Dark Channel Prior Method[J].Journal of Chengdu University of Information Technology,2020,35(01):31-35.[doi:10.16836/j.cnki.jcuit.2020.01.006]
基于暗通道先验理论及其改进算法的夜间图像增强处理
- Title:
- Night Image Enhancement Algorithm based on Improved Dark Channel Prior Method
- 文章编号:
- 2096-1618(2020)01-0031-05
- Keywords:
- image enhancement; dark channel prior; atmospheric light value; initial transmittance; orientation filter
- 分类号:
- TP391.4
- 文献标志码:
- A
- 摘要:
- 针对现有夜间图像增强处理算法对夜间图像处理时图像存在暗区域过度增强、噪声同样被放大及图像失真等导致图像质量变差的情况,结合夜间图像的特点,提出将暗通道先验理论应用于夜间图像增强处理,并对暗通道先验算法中大气光值和初始透射率计算方法进行改进,同时引入导向滤波完善图像细节部分的增强。实验结果表明,基于暗通道先验理论的改进算法对夜间图像处理不仅有很好的视觉效果,在图像结构相似度(SSIM)和图像峰值信噪比(PSNR)也有明显提高,而均方误差(MSE)基本相当。
- Abstract:
- When the image is processed by the existing night image enhancement processing algorithm, the image quality is deteriorated due to excessive enhancement of dark area, amplification of noise and image distortion,in this paper, combining the characteristics of the image at night, put forward the views that applying the prior theory of the dark channel to image enhancement processing at night, and the dark channel prior algorithm in atmospheric optical value calculation method and the initial transmission rate were improved also,guided filtering is introduced to improve the enhancement of image details. Experimental results show that the improved algorithm based on the dark channel prior theory not only has a good visual effect on night image processing, but also significantly improves the image structure similarity(SSIM)and image peak signal to noise ratio(PSNR), and the mean square error(MSE)is basically the same.
参考文献/References:
[1] 李宏宇,朱一峰,黄怡.基于Retinex改进的夜间图像增强算法[J].长春理工大学学报(自然科学版),2018,41(6):104-108.
[2] Lin H N, Shi Z W. Multi-scaleretinex improvement for nighttime image enhancement[J]. Optik International Journal for Light and Electron Optics, 2014, 125(24): 7143-7148.
[3] Dong X, Wang G, Pang Y, et al. Fast efficient algorithm for enhancement of low lighting video[C].Proceedings of the 12th IEEE International Conference on Multimedia and Exposition.Los Alamitos: IEEE Computer Society Press, 2011.
[4] 朱俊.基于Retinex的改进夜视高光抑制视频增强算法[J].计算机与数字工程,2018,46(6):1208-1211.
[5] Koschmieder H. Theorie der Horizontalen Sichtweite[J]. Beitr Phys Freien Atm, 1925,12: 171-181.
[6] He K M, Sun J, Tang X O. Single image haze removal using dark channel prior[C].Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. LosAlamitos: IEEE Computer Society Press, 2009: 1956-1963.
[7] He K M, Sun J, Tang X O. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397-1409.
[8] 高银, 云利军, 石俊生, 等. 基于各向异性高斯滤波的暗原色理论雾天彩色图像增强算法[J]. 计算机辅助设计与图形学学报, 2015, 27(9): 1701-1706.
[9] Tan R T. Visibility in bad weather from a single image[C].Proceedings of the 26th IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2008.
[10] 张红颖,袁晓鹏.基于YUV 色彩空间的Retinex 夜间图像增强算法[J].科学技术与工程,2014,14(30):71-75.
备注/Memo
收稿日期:2019-03-28