基于视觉注意和模糊区域生长的图像检索*

南京大学学报(自然科学版) ›› 2013, Vol. 49 ›› Issue (1): 101–108.

基于视觉注意和模糊区域生长的图像检索*

吴梦麟1**，孙权森2

出版日期:2015-09-23 发布日期:2015-09-23
作者简介: (1.南京工业大学电子与信息工程学院，南京，211816:2.南京理工大学计算机科学与技术学院，南京，210094)
基金资助:
国家自然科学基金(61273251)，江苏省自然科学基金(BK2008411)

Image retrieval based on visual attention and fuzzy regions growing

Wu Meng一Lin1，Sun Quan-Sen2

Online:2015-09-23 Published:2015-09-23
About author:(1 .College of Electronics and information Enginerring,Nanjing University of Technology, Nanj ing, 21 181 6 , China;
2. College of Computer Science and Technology,Nanjing University of Science and Technology,Nanjing,210094,China)

摘要/Abstract

摘要： 视觉注意能够反映用户对图像场景中主要目标的理解，在此基础上提出一种基于视觉注意和
模糊区域生长的图像检索算法.首先，由改进的视’觉注意模型得到显著图;然后，根据分割的结果，提出一种根据显著区域隶属度进行模糊区域生长的算法，合并相似区域以获得查询目标，并提取颜色和纹理特征;最后设计结合隶属度和区域邻接图的相似性度量准则.实验结果表明，该算法能够有效表达用户查询的语义，具有较好的检索性能.

Abstract: Visual attention reflects custom understanding of focused object in image scene. Because of this mecha-
nism,an image retrieval algorithm based on visual attention regions is proposed. Firstly,a saliency map is computed
by improved visual attention model.Then,according to the segmentation result,a saliency region fuzzy growing algo-
rithm based on degree of membership is proposed to obtain object region by merging similar regions,so as to extract
color and texture features. Finally,a combination of degree of membership and region adjacency graphs(RAG)strate-
gy is designed to similarity measure. Experimental results show that proposed algorithm represent custom’s query
semantic effectivcly,and achieve satisfying retrieval performance.

吴梦麟1**，孙权森2
. 基于视觉注意和模糊区域生长的图像检索*[J]. 南京大学学报(自然科学版), 2013, 49(1): 101–108.

Wu Meng一Lin1，Sun Quan-Sen2
. Image retrieval based on visual attention and fuzzy regions growing[J]. Journal of Nanjing University(Natural Sciences), 2013, 49(1): 101–108.

参考文献

[1]Wu J，Lin Z K，Lu M Y，et al. Enhancing relevance feedback in image retrieval using asym- metric Baycsian learning. Journal of Nanjing Uni- versity( Natural Sciences)，2009，45(9):604一612.(邬俊，林正奎，鲁明羽等.基于不对称贝叶斯学习的图像检索相关反馈算法研究.南京大学学报(自然科学),2009,45(9):604-612).
[2]Zhang Q, Shen L S, David D F. A survey of image retrieval based on visual perception. Acta Electronica
Sinica, 2008 , 36 ( 3 ) : 494- 499.(张菩，沈兰荪，David D F.基于视觉感知的图像检索的研究.电子学报，2008,36(3):494-499).
[3]Olshausen B A, Anderson C H，Van Essen D C. A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information.The Journal of Neuroscience, 1993，13(11):4700一4719.
[4]Oge M,Liam M M,Gustavo B B,et al. An attention- driven model for grouping similar images with image
retrieval applications. Eurasip Journal on Advances in Signal Processing,2007,2007:1一17.
[5]Feng S H，Xu D, Yang X. Attentiorrdrvien salient edge(s) and regions) extraction with application to
CBIR. Signal Processing, 2010 , 90( 1):1一15.
[6]Fu H，Chi Z R, Feng D G. Attention-driven image interpretation with application to image retrieval.
Pattern Recognition,2006，39(9):1604一1621.
[7]Huang C B,Jin Z. Image retrieval based on combina- tion of visual perception and local binary pattern his-
togram fouricr. Journal of Computer-Aided Design and Computer Graphics,2011,23(3):406一412.(黄
传波，金忠.结合视觉感知与LBP傅里叶直方图的图像检索.计算机辅助设计与图形学学报，2011,23(3):406~412).
[8]Itti L,Koch C, Nicbur E. A model of saliency-based visual attention for rapid scene analysis, IEEE Trans-
actions on Pattern Analysis and Machine Intelligence, 1998 , 20 (11):1254一1259.
[9]Sun Y R,Fisher R. Object- based visual attention for computer vision. Artificial intelligence, 2003，146 (1):77一123.
[10]Deng Y,Manjunath B S. Unsupervised segmentation of color texture regions in images and video. IEEE
Transactions on Pattern Recognition and Machine Intelligence, 2001 , 23 (8) :800一810.
[11]Sahoo P K,Slaaf D W,Albert T A.Threshold selec- tion using a minimal histogram entropy difference.
Optical Engineering,36(7):1976一1981.
[12]Liu Y,Zhang D S,Liu G. Regiorrbased image retrieval with perceptual colors. Proceedings of the Pacific-Rim
Multimedia Conference,2004:931一938.
[13]Ojala T, Pictikainen M, Macnpaa T. Multiresolution gray-scale and rotation invariant texture classification
with local binary patterns. IEEE Zi-ansactions on Pattern Analysis and Machine intelligence, 2002，24 (7):971一987.
[14]Cheng R,Cheng Y,Jiang X. Thresholding using two- dimensional histogram and fuzzy entropy principle.
IEEE Transactions on image Processing, 2000，9 (4):732一735.
[15]James Z. Wang, J L, Gio W. SIMPLIcity; Scmantics- sensitive integrated matching for picture libraries.
IEEE Zi-ansactions on Pattern Analysis and Machine intelligence, 2001 , 23 ( 9) ; 947一963.
[16]Md Mahmudur R,Prabir B,Bipin C D. A unified im- age retrieval framework on local visual and semantic
concept based feature spaces. Visual Communication and image Representation,2009,20(7);450一462.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed