一种基于加权稀疏编码的频域视觉显著性检测算法

doi:10.3969/j.issn.0372-2112.2012.06.018

电子学报 ›› 2013, Vol. 41 ›› Issue (6): 1159-1165.DOI: 10.3969/j.issn.0372-2112.2012.06.018

一种基于加权稀疏编码的频域视觉显著性检测算法

钱晓亮, 郭雷, 韩军伟, 程塨, 姚西文

西北工业大学自动化学院, 陕西西安 710129

收稿日期:2012-07-20 修回日期:2012-09-29 出版日期:2013-06-25
- 通讯作者:
- 韩军伟男,1977年生,陕西西安人.西北工业大学自动化学院教授,博士生导师.研究方向:计算机视觉、多媒体信息处理. E-mail:jhan@nwpu.edu.cn
- 作者简介:
- 钱晓亮男,1982年生,河南孟州人.西北工业大学自动化学院博士研究生.研究方向为:计算机视觉,模式识别与智能系统. E-mail:qxlzengli@gmail.com 郭雷男,1956年生,山东海阳人.西北工业大学自动化学院教授,博士生导师.研究方向:计算机视觉、模式识别. E-mail:lguo@nwpu.edu.cn
- 基金资助:
- 国家自然科学基金 (No.61005018,No.91120005); 教育部新世纪优秀人才支持计划 (No.NCET-10-0079); 西北工业大学基础研究基金 (No.JC20120237)

A Spectral Algorithm Based on Weighted Sparse Coding for Visual Saliency Detection

QIAN Xiao-liang, GUO Lei, HAN Jun-wei, CHENG Gong, YAO Xi-wen

School of Automation, Northwestern Polytechnical University, Xi'an, Shaanxi 710129, China

Received:2012-07-20 Revised:2012-09-29 Online:2013-06-25 Published:2013-06-25
- Supported by:
- National Natural Science Foundation of China (No.61005018, No.91120005); Program for New Century Excellent Talents in University of Ministry of Education of China (No.NCET-10-0079); Basic Research Fund of Northwestern Polytechnical University (No.JC20120237)

摘要/Abstract

摘要： 针对现有的基于频域的视觉显著性检测算法检测准确度不高的弱点,本文提出了一种基于加权稀疏编码的频域算法,旨在提高检测准确度的同时保持频域算法运算速度快的优势.在传统的稀疏编码算法基础上,本文根据各子码的增量编码长度来设置它们的权重,实现对图像的加权稀疏编码而不是直接对原始图像进行处理.最后,为了处理多维的稀疏编码信号,本文利用信息论的思想对最新发表的图像签名算法进行了多通道改进,以香农自信息的形式输出图像的显著性检测结果.在公开的人眼跟踪数据库上同9种流行算法的实验对比和对算法复杂度的分析证明了本文算法的有效性和快速性.

关键词: 显著性检测, 加权稀疏编码, 频域算法, 信息论

Abstract: A spectral algorithm using weighted sparse coding is proposed for visual saliency detection in this paper.This algorithm is able to improve the accuracy of the traditional spectral saliency detection approaches while preserving their advantage of fast processing speed.Based on the traditional sparse coding algorithm,the sub-codes are weighted according to their incremental coding length.Then,the image is encoded by weighted sparse coding instead of directly transforming the raw images into frequency domain.Finally,we improve the multi-channel method developed in a recently published algorithm called image signature through information theory.Our method yields the saliency map with the form of the Shannon self-information.The experimental comparisons between the proposed and 9 state-of-the-art approaches and the analysis of complexity of our algorithm demonstrate the effectiveness and efficiency of our method.

Key words: saliency detection, weighted sparse coding, spectral algorithm, information theory

中图分类号:

TP391.4

钱晓亮, 郭雷, 韩军伟, 等. 一种基于加权稀疏编码的频域视觉显著性检测算法[J]. 电子学报, 2013, 41(6): 1159-1165.

QIAN Xiao-liang, GUO Lei, HAN Jun-wei, et al. A Spectral Algorithm Based on Weighted Sparse Coding for Visual Saliency Detection[J]. Acta Electronica Sinica, 2013, 41(6): 1159-1165.

参考文献

[1] Rutishauser U,Walther D,Koch C,et al.Is bottom-up attention useful for object recognition?[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Washington:IEEE Press,2004.37-44.

[2] Han J W,Ngan K N,Li M J,et al.Unsupervised extraction of visual attention objects in color images[J].IEEE Transactions on Circuits and Systems for Video Technology,2006,16(1):141-145.

[3] Wang Z,Lu L G,Bovik A C.Foveation scalable video coding with automatic fixation selection[J].IEEE Transactions on Image Processing,2003,12(2):243-254.

[4] Chen T,Cheng M M,Tan P,et al.Sketch2Photo:internet image montage[J].ACM Transactions on Graphics,2009,28(5):1-10.

[5] Koch C,Ullman S.Shifts in selective visual attention:towards the underlying neural circuitry[J].Human Neurobiology,1985,4(4):219-227.

[6] Itti L,Koch C,Niebur E.A model of saliency-based visual attention for rapid scene analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(11):1254-1259.

[7] Treisman A M,Gelade G.A feature-integration theory of attention[J].Cognitive Psychology,1980,12(1):97-136.

[8] 张孝临,赵宏伟,王慧,等.基于对比敏感度和马尔可夫链的注意信息提取算法[J].电子学报,2010,38(2A):213-217. ZHANG Xiao-lin,ZHAO Hong-wei,WANG Hui,et al.Extracting attention information algorithm based on contrast sensitivity and Markov chain[J].Acta Electronica Sinica,2010,38(2A):213-217.(in Chinese)

[9] Bruce N D B,Tsotsos J K.Saliency,attention,and visual search:An information theoretic approach[J].Journal of Vision,2009,9(3):1-24.

[10] Zhang L Y,Tong M H,Marks T K,et al.SUN:A Bayesian framework for saliency using natural statistics[J].Journal of Vision,2008,8(7):1-20.

[11] Harel J,Koch C,Perona P.Graph-based visual saliency[A].Advances in Neural Information Processing Systems[C].Vancouver:MIT Press,2007.545-552.

[12] Judd T,Ehinger K,Durand F,et al.Learning to predict where humans look[A].IEEE International Conference on Computer Vision[C].Kyoto:IEEE Press,2009.2106-2113.

[13] Liu T,Yuan Z,Sun J,et al.Learning to detect a salient object[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(2):353-367.

[14] Hou X,Zhang L.Saliency detection:A spectral residual approach[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Minnesota:IEEE Press,2007.1-8.

[15] Guo C,Ma Q,Zhang L.Spatio-temporal saliency detection using phase spectrum of quaternion Fourier transform[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Alaska:IEEE Press,2008.1-8.

[16] 马奇,张立明.快速注意力选择计算及其在图像质量评价中的应用[J].计算机辅助设计与图形学学报,2009,21(7):973-983. MA Qi,ZHANG Li-ming.A fast computation of attention selection map and its application in image quality assessment[J].Journal of Computer-Aided Design & Computer Graphics,2009,21(7):973-983.(in Chinese)

[17] Achanta R,Hemami S,Estrada F,et al.Frequency-tuned salient region detection[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Miami:IEEE Press,2009.1597-1604.

[18] Li J,Levine M D,An X,et al.Saliency detection based on frequency and spatial domain analysis[A].British Machine Vision Conference[C].Dundee:BMVA Press,2011.1-11.

[19] Hou X D,Harel J,Koch C.Image signature:highlighting sparse salient regions[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(1):194-201.

[20] Olshausen B A,Field D J.Emergence of simple-cell receptive field properties by learning a sparse code for natural images[J].Nature,1996,381(6583):607-609.

[21] Hou X D,Zhang L.Dynamic visual attention:Searching for coding length increments[A].Advances in Neural Information Processing Systems[C].Vancouver:MIT Press,2008.681-688.

[22] Tibshirani R.Regression shrinkage and selection via the lasso[J].Journal of the Royal Statistical Society,1996,58(1):267-288.

[23] Efron B,Hastie T,Johnstone I,et al.Least angle regression[J].The Annals of Statistics,2004,32(2):407-499.

[24] He S,Han J W,Hu X T,et al.A biologically inspired computational model for image saliency detection[A].ACM International Conference on Multimedia[C].Arizona:ACM Press,2011.1465-1468.

[25] Mairal J,Bach F,Ponce J,et al.Online learning for matrix factorization and sparse coding[J].Journal of Machine Learning Research,2010,11:19-60.

[26] Bruce N,Tsotsos J.Saliency based on information maximization[A].Advances in Neural Information Processing Systems[C].Vancouver:MIT Press,2005.155-162.

一种基于加权稀疏编码的频域视觉显著性检测算法

A Spectral Algorithm Based on Weighted Sparse Coding for Visual Saliency Detection

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	陈星宇, 叶锋, 黄添强, 翁彬, 陈家祯, 林文忠. 融合小型深度生成模型的显著性检测[J]. 电子学报, 2021, 49(4): 768-774.
[2]	丁颖, 刘延伟, 刘金霞, 刘科栋, 王利明, 徐震. 虚拟现实全景图像显著性检测研究进展综述[J]. 电子学报, 2019, 47(7): 1575-1583.
[3]	李庆武, 马云鹏, 周亚琴, 邢俊. 基于无监督栈式降噪自编码网络的显著性检测算法[J]. 电子学报, 2019, 47(4): 871-879.
[4]	杨小冈, 李维鹏, 马玛双. 概率框架下多特征显著性检测算法[J]. 电子学报, 2019, 47(11): 2378-2385.
[5]	张峰, 钟宝江. 基于兴趣目标的图像检索[J]. 电子学报, 2018, 46(8): 1915-1923.
[6]	李梦, 刘星, 任泽民. 联合Sobolev梯度的相场变分模型应用于图像显著性检测[J]. 电子学报, 2018, 46(7): 1683-1690.
[7]	杨兴明, 王雨廷, 谢昭, 吴克伟. 基于“轮廓-区域”多层互补特性的显著性检测[J]. 电子学报, 2018, 46(11): 2688-2695.
[8]	李鑫, 李兴华, 杨丹, 马建峰. 基于矢量量化的高效随机物理层密钥提取方案[J]. 电子学报, 2016, 44(2): 275-281.
[9]	陈杰;朱晶;周荫清;李春升. 复杂目标场景合成孔径雷达图像异质性分析与测量方法研究[J]. 电子学报, 2008, 36(9): 1687-1692.
[10]	蒋挺;赵成林;周正. 准最佳屏蔽二进阵列偶理论研究[J]. 电子学报, 2007, 35(1): 78-83.
[11]	张杰, 廖桂生, 王珏. 空间相关色噪声下基于酉变换的信号源数目估计[J]. 电子学报, 2005, 33(9): 1581-1585.
[12]	王超, 李治安, 吴德伟, 王永良. 两种典型的MIMO系统信道容量分析与仿真[J]. 电子学报, 2004, 32(12): 2001-2004.
[13]	蒋挺;赵晓群;李琦;贾志成;候蓝田. 准最佳二进阵列偶[J]. 电子学报, 2003, 31(5): 751-755.
[14]	刘先省;申石磊;潘泉. 传感器管理及方法综述[J]. 电子学报, 2002, 30(3): 394-398.
[15]	张彤;杨波;王育民;李真富. 两类信息隐匿技术安全性的信息论分析方法[J]. 电子学报, 2001, 29(10): 1346-1348.