摘要
显著目标检测旨在辨别出自然图像中的显著区域。为了提高检测效果,提出了基于字典和加权低秩恢复的显著目标检测。首先,在低秩恢复模型中融入字典,以更好地将低秩矩阵和稀疏矩阵分离;然后,获取颜色、位置和边界连接先验对应的稀疏矩阵,根据其显著值生成先验系数;最后,将3个先验用自适应系数组合的方式构造权重矩阵,并融入到低秩恢复模型中。在4个具有挑战性的数据集上将其与11种算法进行比较,实验结果表明,所提算法的效果最好。
Salient object detection intends to identify salient areas in natural images.In order to improve detection results,a method based on dictionary and weighted low-rank recovery for salient object detection was proposed.Firstly,a dictionary is incorporated into the low rank recovery model to separate the low rank matrix from the sparse matrix better.Secondly,sparse matrices corresponding to the color,location and boundary connectivity priors are obtained,and the adaptive coefficients are generated by their saliency values.Finally,a weighted matrix is constructed by adaptive coefficients with three priors,and the matrix is merged into the low rank recovery model.Compared with eleven state-of-theart methods in four challenging databases,the experiment results show that the proposed approach outperforms the state-of-the-art solutions.
作者
马晓迪
吴茜茵
金忠
MA Xiao- di, WU Xi- yin, JIN Zhong(School of Computer Science and Engineering,Nanjing University of Science and Technology, Nanjing 2100.94, China） （Key Laboratory of Intelligent Perception and System for High Dimensional Information of Ministry of Education, Nanjing University of Science and Technology,Nanjing 210094 ,China)
出处
《计算机科学》
CSCD
北大核心
2018年第B06期146-150,161,共6页
Computer Science
基金
国家自然科学基金(61602244
61702262
61602444
91420201
61472187)
国家重点基础研究发展计划(2014CB349303)
国家预研领域基金(6140312010101)资助
关键词
字典
背景先验
加权低秩恢复
自适应系数
Dictionary
Background prior
Weighted low rank recovery
Adaptive coefficient
