点击次数：

发布时间：2017-03-12

论文类型：期刊论文

论文编号：j.neucom.2015.03.122

发表时间：2016-01-15

发表刊物：Neurocomputing

所属单位：信息与通信工程学院

刊物所在地：Netherlands

学科门类：工学

一级学科：信息与通信工程

卷号：173

页面范围：406-417

ISSN号：0925-2312

关键字：saliency detection; Generative model; Discriminative model; Sparse coding

摘要：In this paper, we propose a visual saliency detection algorithm which incorporates both generative and discriminative saliency models into a unified framework First, we develop a generative model by defining image saliency as the sparse coding residual based on a learned background dictionary. Second, we introduce a discriminative model by solving an optimization problem
that exploits the intrinsic relevance of similar regions for regressing region-based saliency to the smooth state.Third, a weighted sum of multi-scale region-level saliency is computed as the pixel-level saliency, which genera