摘 要：针对现实场景中镜面高光图像信息丢失的问题，文章提出一种基于暗通道先验的镜面高光图像增强算法。该算法首先以暗通道先验算法为基础，重新更新了图像的全局光照分量以及边界约束；然后采用改进的引导滤波算法优化透射率；最后利用 CLAHE 算法增强图像的局部细节。实验结果表明，该方法可以有效增强镜面反射图像中的信息，其处理结果明显优于其他算法。
关键词：镜面高光图像增强；暗通道先验算法；CLAHE；引导滤波
DOI:10.19850/j.cnki.2096-4706.2022.20.019
中图分类号：TP391.9 文献标识码：A 文章编号：2096-4706（2022）20-0076-05
Enhancement Algorithm of Specular Highlight Image Based on Dark Channel Prior
ZHANG Zhe
(Shandong Huayu University of Technology, Dezhou 253034, China)
Abstract: In order to solve the problem of information loss of specular highlight image in real scene, a specular highlight image enhancement algorithm based on dark channel prior is proposed in this paper. The algorithm is based on dark channel prior algorithm, and the global illumination component and boundary constraint of image are updated again. Then an improved guided filtering algorithm is used to optimize the transmittance. Finally, CLAHE algorithm is used to enhance local details of the image. Experimental results show that this method can effectively enhance the information in the mirror reflection image, and its processing results are obviously better than other algorithms.
Keywords: specular highlight image enhancement; dark channel prior algorithm; CLAHE; guided filtering
参考文献：
[1] NAYAR S K，FANG X S，BOULT T. Separation of Reflection Components Using Color and Polarization [J].International Journal of Computer Vision，1997，21（3）：163-186.
[2] LIN S，LI Y Z，KANG S B，et al. Diffuse-Specular Separation and Depth Recovery from Image Sequences [C]//ECCV ‘02: Proceedings of the 7th European Conference on Computer Vision-Part III. Berlin：Springer-Verlag，2002：210-224.
[3] KLINKER G J，SHAFER S A，KANADE T. The measurement of highlights in color images [J].International Journal of Computer Vision，1992，2：309-334.
[4] KATSUSHI I，TAN R T，KO N. Separating reflection components based on chromaticity and noise analysis [J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2004，26（10）：1373-1379.
[5] TAN R T，IKEUCHI K. Reflection components decomposition of textured surfaces using linear basis functions [C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05).San Diego：IEEE，2005：125-131.
[6] MALLICK S P，ZICKLER T E，KRIEGMAN D J，et al. Beyond Lambert: Reconstructing Specular Surfaces Using Color [C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05). San Diego：IEEE，2005：619-626.
[7] MALLICK S P，ZICKLER T，BELHUMEUR P N， et al. Specularity Removal in Images and Videos: A PDE Approach [C]// ECCV’06: Proceedings of the 9th European conference on Computer Vision - Volume Part I. Berlin：Springer-Verlag，2006：550-563.
[8] MENG G F，WANG Y，DUAN J Y，et al. Efficient Image Dehazing with Boundary Constraint and Contextual Regularization [C]//2013 IEEE International Conference on Computer Vision. Sydney：IEEE，2013：617-624.
[9] SINGH G. Enhanced Mist Elimination using Dark Channel Prior and Gaussian Domain based Adaptive Gamma Correction [J]. International Journal of Computer Applications，2014，106（16）： 44-48.
[10] CHEN L，LIN S，ZHOU K，et al. Specular Highlight Removal in Facial Images [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu：IEEE，2017：2780-2789.
[11] SHEN H L，CAI Q Y. Simple and efficient method for specularity removal in an image [J].Applied Optics，2009，48（14）： 2711-2719.
[12] YANG Q X，WANG S N，AHUJA N. Real-Time Specular Highlight Removal Using Bilateral Filtering [C]//Computer Vision – ECCV 2010. Heraklion：Springer，2010：87-100.
[13] YAMAMOTO T，NAKAZAWA A. General Improvement Method of Specular Component Separation Using High-Emphasis Filter and Similarity Function [J].Ite Transactions on Media Technology & Applications，2019，7（2）：92-102.
[14] AKASHI Y，OKATANI T. Separation of reflection components by sparse non-negative matrix factorization [J].Computer Vision & Image Understanding，2016，146（may）：77-85.
[15] HE K M，SUN J，TANG X O. Single Image Haze Removal Using Dark Channel Prior [J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2011，33（12）：2341-2353.
[16] LU Z，LONG B Y，LI K，et al. Effective Guided Image Filtering for Contrast Enhancement [J].IEEE Signal Processing Letters， 2018，25（10）：1585-1589.
作者简介：张喆（1995—），女，汉族，天津人，助教，硕士研究生，主要研究方向：图像识别、机器视觉。