结合Al-Alaoui算子和改进暗通道的图像去雾算法  

A Image Dehazing Algorithm Combined with Al-Alaoui Operator and Improved Dark Channel

作　　者：张伟 李琪 袁晓[1] ZHANG Wei;LI Qi;YUAN Xiao(College of Electronics and Information Engineering,Sichuan University,Chengdu 610064,China)

机构地区：[1]四川大学电子信息学院,四川成都610064

出　　处：《现代信息科技》2024年第8期151-155,共5页Modern Information Technology

摘　　要：针对传统图像去雾方法去雾效果有限、存在光晕效应、色彩失真等不足,文章提出一种结合Al-Alaoui算子的改进暗通道先验去雾算法。算法首先用Al-Alaoui算子对图像做卷积滤波增强处理,再用改进的四叉树搜索方法求大气光估值,同时使用引导滤波细化介质透射率。最后,使用优化的大气光值和透射率对已增强图像复原。经过对比分析,新算法在主客观方面都有明显提升。Aiming at the problems of limited effect,halo effect and color distortion in traditional image dehazing methods,a priori dehazing algorithm combined with Al-Alaoui operator and improved dark channel is proposed in this paper.Firstly,Al-Alaoui operator is used to enhance the image by convolution filtering,then the improved quadtree search method is used to estimate the atmospheric light,and the guided filter is used to refine the medium transmittance.Finally,the enhanced image is restored using the optimized atmospheric light value and transmittance.After comparative analysis,the new algorithm has obvious improvement in both subjective and objective aspects.

关 键 词：分数阶 Al-Alaoui算子 四叉树 暗通道 图像去雾 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]