基于迹表示和正则化的显著目标检测算法  

Salient Object Detection via Trace Representation and Regularization

作　　者：马晓迪 吴茜茵 金忠[1,2] Ma Xiaodi;Wu Xiyin;Jin Zhong(School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094;Key Laboratory of Intelligent Perception and System for High-Dimensional Information of Ministry of Education,Nanjing University of Science and Technology,Nanjing 210094)

机构地区：[1]南京理工大学计算机科学与工程学院,南京210094 [2]南京理工大学高维信息智能感知与系统教育部重点实验室,南京210094

出　　处：《计算机辅助设计与图形学学报》2018年第11期2018-2025,共8页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(61373063;61375007;61233011;91420201;61472187);国家重点基础研究发展计划(2014CB349303)

摘　　要：显著目标检测旨在快速地辨别自然图像的显著区域.为了更完整地将图像的显著区域与背景分离,根据低秩恢复理论提出基于迹表示和正则化的显著目标检测算法.首先将核范数替换为矩阵的迹表示以获取更低秩的解;然后在模型中加入拉普拉斯正则化项,减少稀疏矩阵和低秩矩阵的联系;最后将位置、颜色和边界连接先验整合成权重矩阵,融入到矩阵分解模型中.在Matlab平台下的MSRA1K, SOD, ECSSD和iCoseg这4个数据集上与13种算法进行比较的实验结果表明,该算法优于其他算法.Salient object detection intends to identify salient areas in natural images.According to low rank recovery theory,we propose a method via trace representation and regularization for salient object detection to separate the salient areas of the image from the background more completely.Firstly,a trace representation of matrix is used to obtain lower rank solution rather than the nuclear norm.Secondly,a Laplacian regularization is merged into model to reduce connection between sparse matrix and low-rank matrix.Finally,the color,location and boundary connectivity priors are integrated into a weight matrix,which is incorporated into the matrix decomposition model.Comparing with thirteen state-of-the-art methods in four challenging databases:MSRA1K,SOD,ECSSD and iCoseg,the experimental results based on Matlab show that our approach outperforms the state-of-the-art methods.

关 键 词：迹表示 正则化 权重矩阵 低秩恢复 显著目标检测 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]