Unsupervised Salient Object Extraction Based on Sparse Representation

LI Zhong-sheng; LI Ren-fa; CAI Ze-su; ZHAO Cheng-lin

doi:10.3969/j.issn.0372-2112.2012.06.005

您当前的位置：

首页 >

文章列表页 >

Unsupervised Salient Object Extraction Based on Sparse Representation

更新时间：2025-07-16

- Unsupervised Salient Object Extraction Based on Sparse Representation
- Acta Electronica Sinica Vol. 40, Issue 6, Pages: 1097-1102(2012)
- 作者机构：
  
  1. 邵阳学院信息工程系,湖南,邵阳,422000
  2. 湖南大学网络与信息安全湖南省重点实验室,湖南,长沙,410082
  3. 哈尔滨工业大学计算机学院,黑龙江,哈尔滨,150001
  4. 邵阳学院信息工程系湖南邵阳,422000
  5. 湖南大学网络与信息安全湖南省重点实验室湖南长沙,410082
  6. 哈尔滨工业大学计算机学院黑龙江哈尔滨,150001
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.60873047, No.61075076, No.61173036)
- DOI：10.3969/j.issn.0372-2112.2012.06.005
  CLC： TP311
- Published：2012
- 稿件说明：
移动端阅览
LI Zhong-sheng, LI Ren-fa, CAI Ze-su, et al. Unsupervised Salient Object Extraction Based on Sparse Representation[J]. Acta Electronica Sinica, 2012, 40(6): 1097-1102.
DOI：

LI Zhong-sheng, LI Ren-fa, CAI Ze-su, et al. Unsupervised Salient Object Extraction Based on Sparse Representation[J]. Acta Electronica Sinica, 2012, 40(6): 1097-1102. DOI： 10.3969/j.issn.0372-2112.2012.06.005.

摘要

针对现有显著对象提取算法时间复杂度高和未考虑显著对象的完整性等问题

提出了一种能适应资源有限环境的显著对象提取算法.首先建立了稀疏表示的数学模型

归纳出了显著对象与稀疏表示的对应关系、区域间的边能近似模式和邻接区域间的渐变模式.然后依据对应关系确定候选区域

依据渐变模式和边能近似模式实现显著对象的局部提取.对比实验证实:本文算法高速、精确地捕捉到了显著对象

并能在一定条件下保持显著对象的完整性.

Abstract

The existing salient object extraction algorithms had high time complexity and didnt take the integrity of the objects into account

and a salient object extraction algorithm is proposed

which is adaptive to the resource-constrained environment.The mathematic model of sparse representation is built.The corresponding relation between the salient objects and spare representation

edge energy approximation pattern among regions

and gradual change pattern between adjacent regions are induced.The candidate regions are determined based on the relation

and the salient objects are locally extracted based on gradual change pattern and edge energy approximation pattern.The contrast experiments indicate that the salient objects are captured accurately and the integrity of the salient objects are well-kept under given conditions with the proposed algorithm.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Spatiotemporal Fusion Algorithm of Remote Sensing Images Based on Cross-Scale Similarity Prior

Sparse ISAR Imaging Combined with Nearest Neighbor Graph Model

A Low Time Complexity Segment Routing Approach for Multi-Commodity Traffic Flow in Mega LEO Constellation

Sparse Representation Theory and Application in Underwater Acoustic Signal Processing

Research on PPI Network Construction and Complex Mining Algorithm Based on Dynamic Graph

Related Author

FANG Shuai

WAN Qi

CAO Yang

HU Chang-yu

CHEN Chun-feng

YI Wen-yi

DONG Yu-chen

LI Hui

Related Institution

School of Computer and Information, Hefei University of Technology

Anhui Province Key Laboratory of Industry Safety and Emergency Technology

Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology), Ministry of Education

University of Science and Technology of China

College of Electronic Information Engineering， Wuxi University

⁰