基于LBP特征与图像显著性的散焦模糊区域检测  

Defocus blur detection based on LBP and saliency

作　　者：李浩伟 刘洪 梁建娟 刘本永 LI Haowei;LIU Hong;LIANG Jianjuan;LIU Benyong(College of Big Data and Information Engineering,Guizhou University,Guiyang 550025,China)

机构地区：[1]贵州大学大数据与信息工程学院,贵阳550025

出　　处：《智能计算机与应用》2023年第4期151-157,共7页Intelligent Computer and Applications

基　　金：贵州省基金(黔科合基础[2019]1063号);贵州大学引进人才科研项目(贵大人基合同字(2017)14号)。

摘　　要：针对当前散焦模糊区域检测算法对于均质清晰区域容易误判,边缘定位不够准确的问题,提出一种基于LBP特征与图像显著性的散焦模糊区域检测算法。首先,利用LBP特征和SLIC算法来获取SLBP模糊图,利用DRFI显著性检测算法来获取DRFI显著图;然后,利用SLBP模糊图和DRFI显著图来构造三元标识图,进而利用KNN抠图算法来获取模糊图;最后,借助于形态学运算和平滑滤波来细化模糊图。在公共模糊数据集上的实验结果表明,该算法能有效地检测出均质清晰区域,保留图像边缘细节,在检测精度和查全率指标上表现较好。Aiming at the problem that the current defocus blurred region detection methods are easy to misjudge homogeneoussharp regions,and can′t locate the edge accurately enough,a defocus blurred region detection method based on LBP and saliency is proposed.Firstly,LBP feature and SLIC algorithm are used to obtain SLBP blur map,DRFI saliency detection algorithm is used to obtain DRFI saliency map.Secondly,the trimap is obtained using SLBP blur map and DRFI saliency map,and then KNN matting algorithm is used to obtain a blur map.Finally,the blur map is refined with the help of morphological operations and smoothing filter.The experimental results on the public blur dataset show that the method can effectively detect homogeneous-sharp regions,retain the edge details of an image,and perform well in detection accuracy and recall.

关 键 词：散焦模糊 均质清晰区域 边缘定位 LBP 图像显著性 KNN抠图 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]