An interactive Image retrieval method

被引：0

作者：

Jiang, Ye ^{[1
]}

Jiang, Min ^{[1
]}

Luo, Jian ^{[1
]}

Gan, Zhaohui ^{[2
]}

Tang, Jinshan ^{[1
,3
]}

机构：

[1] Wuhan Univ Sci & Technol, Coll Comp Sci & Technol, Wuhan, Hubei, Peoples R China

[2] Wuhan Univ Sci & Technol, Coll Informat Sci & Technol, Wuhan, Hubei, Peoples R China

[3] Michigan Technol Univ, Sch Technol, Houghton, MI 49931 USA

来源：

2016 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) | 2016年

基金：

中国国家自然科学基金;

关键词：

interactive; image retrieval; image segmentation; relevance feedback;

D O I：

暂无

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, we propose an interactive image retrieval method based on interactive image segmentation and relevance feedback. For testing the performance of the algorithm, we built an image database by web crawlers, and added a background label to each image by histogram analysis. For image retrieval, an interactive image segmentation scheme based on GrabCut has been applied to get the region of interest (ROI), and then we use an automatic labeling method to get the training samples of relevance feedback, and then incorporate the background labels into the similarity measurement to decrease the influence of clutters. The experimental results show that this method can reduce the influence of image background on image retrieval, and optimize the search results by the feedback of users.

引用

页码：3429 / 3433

页数：5

共 15 条

[1]

Avula Sridhar R., 2006, MULTIMEDIA SYSTEMS J, V11

[2]

Belongie S., 2000, ADV NEURAL INFORM PR

[3] Image retrieval: Ideas, influences, and trends of the new age [J].

Datta, Ritendra ;

Joshi, Dhiraj ;

Li, Jia ;

Wang, James Z. .

ACM COMPUTING SURVEYS, 2008, 40 (02)

[4]

Kira K, 1992, P 9 INT WORKSH MACH, P249

[5]

Li Jing, 2013, Handbook on neural information processing, P433

[6] Texture features for browsing and retrieval of image data [J].

Manjunath, BS ;

Ma, WY .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1996, 18 (08) :837-842

[7] Gaze-Based Relevance Feedback for Realizing Region-Based Image Retrieval [J].

Papadopoulos, Georgios Th. ;

Apostolakis, Konstantinos C. ;

Daras, Petros .

IEEE TRANSACTIONS ON MULTIMEDIA, 2014, 16 (02) :440-454

[8]

Pass Greg, 1996, ACM INT C MULT

[9] GrabCut - Interactive foreground extraction using iterated graph cuts [J].

Rother, C ;

Kolmogorov, V ;

Blake, A .

ACM TRANSACTIONS ON GRAPHICS, 2004, 23 (03) :309-314

[10] An image retrieval algorithm using multiple query images [J].

Tang, J ;

Acton, S .

SEVENTH INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND ITS APPLICATIONS, VOL 1, PROCEEDINGS, 2003, :193-196

← 1 2 →