一种基于Boosting模型的图像去雾算法

张骏; 李培华; 章盛; 吉涛

doi:doi:10.19453/j.cnki.1005-488x.2019.01.012

光电子技术, 2019, 39 (1): 52, 网络出版: 2019-04-11

一种基于Boosting模型的图像去雾算法

Single image Haze Removal Algorithm Based on Boosting Model

论文大纲

张骏 ^*李培华章盛吉涛

作者单位

中国航空工业集团公司华东光电有限公司, 特种显示国家实验室, 国家特种显示工程技术研究中心, 安徽芜湖 241002

Boosting模型图像增强极优增强器学习率 boosting model image enhancement superior enhancer learning rate

摘要

分析了Boosting提升模型, 提出一种以去雾后图像均方误差与信息熵比值为选择标准, 对多类不同的去雾算法进行排序, 并根据设定的阈值, 从多类的去雾算法中, 选择合适的去雾算法作为“极优增强器”, 再通过对优化学习率的方法。更新“极优增强器”的权重, 采取线性组合, 构建了最优去雾算法。经实验表明, 该算法实现了去雾后图像对比度和图像的信息损失之间的平衡。提升了图像对比度, 凸显了图像细节, 最大程度的减小了图像信息的损失。

Abstract

The Boosting lifting model was analyzed. A selection criterion for the ratio of the mean square error and the entropy of the image after the defogging, and the different kinds of different defogging algorithms were sort out. According to the set the threshold, the appropriate defogging algorithm was selected as the "extreme best intensifier" from the multiple defogging algorithm. By optimizing the learning rate, the weight of the "optimal enhancer"was updated.A linear combination to construct an optimal fog removal algorithm was exopted was adopted. Experiments show that the algorithm achieves the balance between image contrast and image loss after fog removal. The image contrast is enhanced, the image details are highlighted, and the loss of image information is reduced to the greatest extent.

参考文献

[1] 李航, 统计学习方法［M］, 北京: 清华大学出版社, 2012.3.

[2] William K P. Digital Image Processing［M］.Beijing: China Machine Press, 2015.158-196.

[3] 王浩, 张叶, 沈宏海, 等.图像增强算法综述［J］.中国光学.2017.4(10): 438-448.

[4] CHAN T F, SHEN J H.图像处理与分析［M］.陈文斌, 程晋, 译.北京: 科学出版社, 2011.

[5] 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: 355-368.

[6] Youngbae Kim, Yeong Jun Koh, Chulwo Lee, et al..Dark image enhancement based onpairwise target contrast and multi-scale detail boosting［C］.Image Processing(ICIP), quebec City, QC, Carade.2015: 2088-2093.

[7] SHEN C T, HWAHG W L. Color image enhancement using Retinex with robust envelope［C］.16th IEEE International Conference on Image Process, Cairo, Egypt, 2009: 3141-3144.

[8] Loza A, Bull D R, Hill P R, et al.. Automatic contrast enhancement of low-light images based on local statistics of wavelet coefficients［J］.Digital Signal Process, 2013, 23(6): 1856-1866.

[9] He Kaiming, Sun Jian, Tang Xiaoou. Single Image Haze Removal Using Dark Channel Prior［J］IEEE transactions on pattern anakysis and machine intelligence. 2011.10: 2341-2353.

[10] Kim Jin-Hwan, Jang Won-Dong, Sim Jae-Young. Optimized contrast enhancement for real-time image and video dehazing［J］.J.Vis.Commun.Image R.2013.24: 410-425.

[11] Kim J H, Sim J Y, Kim C S. Single image dehazing based on contrast enhancement［C］.in: Proc. IEEE ICIP, Prague, Czech. Republic, 2012, pp.969-972.

[12] JANG J H.Contrast-enhanced fusion of multisensor images using subband-decomposed multiscale retinex［C］.IEEE Transaction on Image Processing, Cairo, Egypt, 2012, 21(8): 3479-3490.

[13] Gonzale S A M, Grigoryan A M.Fast Retinex for color image enhancement: Methods and algorithms［J］.SPIE, 2015, 9411: 1-12.

[14] 蒋伟, 胡学刚.基于对数图像处理和二阶微分的图像增强新模型［J］.西南大学学报(自然科学版).2009, 31(9): 142-146

[15] Chen B H, Huang S C, Li C Y, et al. Haze removal using radial basis function networks for visibility restoration applications［J］. IEEE transactions on neural networks and learning systems, 2017 (99): 1-11

[16] He L, Zhao J, Zheng N, et al. Haze removal using the difference-structure-preservation prior［J］. IEEE Transactions on Image Processing, 2017, 26(3): 1063-1075.

张骏, 李培华, 章盛, 吉涛. 一种基于Boosting模型的图像去雾算法[J]. 光电子技术, 2019, 39(1): 52. ZHANG Jun, LI Peihua, ZHANG Sheng, JI Tao. Single image Haze Removal Algorithm Based on Boosting Model[J]. Optoelectronic Technology, 2019, 39(1): 52.

一种基于Boosting模型的图像去雾算法

关于本站 Cookie 的使用提示

全站搜索

一种基于Boosting模型的图像去雾算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索