[1] Wang Xiaoling, Xie Kanglin,. Auto-expanded multi query examples technologyin content-based image retrieval [J]. Journal of Southeast University (English Edition), 2005, 21 (3): 287-292. [doi:10.3969/j.issn.1003-7985.2005.03.009]

Copy

Auto-expanded multi query examples technologyin content-based image retrieval()

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

21

Issue:

2005 3

Page:

287-292

Research Field:

Information and Communication Engineering

Publishing date:

2005-09-30

Info

Title:

Auto-expanded multi query examples technologyin content-based image retrieval

Author(s):

Wang Xiaoling¹;  2;  Xie Kanglin¹

¹Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai 200030, China
²Institute of Information Management, Shanxi Financial University, Taiyuan 030016, China

Keywords:

content-based image retrieval;  semantic;  multi query examples;  K-means clustering

PACS:

TN911.73

DOI:

10.3969/j.issn.1003-7985.2005.03.009

Abstract:

In order to narrow the semantic gap existing in content-based image retrieval(CBIR), a novel retrieval technology called auto-extended multi query examples(AMQE)is proposed.It expands the single one query image used in traditional image retrieval into multi query examples so as to include more image features related with semantics.Retrieving images for each of the multi query examples and integrating the retrieval results, more relevant images can be obtained.The property of the recall-precision curve of a general retrieval algorithm and the K-means clustering method are used to realize the expansion according to the distance of image features of the initially retrieved images.The experimental results demonstrate that the AMQE technology can greatly improve the recall and precision of the original algorithms.

References:

[1] Smeulders A W M, Worring M, Santini S, et al.Content-based image retrieval at the end of the early years [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(12):1349-1380.
[2] Yoon Janghyun, Jayant Nikil.Relevance feedback for semantics based image retrieval [A].In:Proc of the IEEE International Conference on Image Processing [C].Thessaloniki, Greece, 2001.42-45.
[3] Smith John R, Li Chung-Sheng.Image classification and querying using composite region templates [J].Computer Vision and Image Understanding, 1999, 75(1, 2):165-174.
[4] Zhuang Y, Liu X, Pan Y.Apply semantic template to support content-based image retrieval [A].In:Proc of the SPIE Storage and Retrieval for Multimedia Database [C].San Jose, CA, USA, 2000.442-449.
[5] Natsev Apostol, Smith John R.Active selection for multi-example querying by content [A].In:Proc of the IEEE International Conference on Multimedia and Expo [C].Baltimore, MD, USA, 2003.445-448.
[6] Nastar C, Mitschke M, Meilhac C, et al.Surfimage:a flexible content-based image retrieval system [A].In:Proc of the ACM Multimedia [C].Bristol, England, 1998.339-344.
[7] Han Jiawei, Kamber Micheline.Data mining concepts and techniques [M].Translated by Fan Ming, Meng Xiaofeng.Beijing:China Machine Press, 2001.232-235.(in Chinese)
[8] Shim Jae-Chang, Dorai Chitra.A generalized region labeling algorithm for image coding, restoration, and segmentation [A].In:Proc of the IEEE International Conference on Image Processing [C].Los Alamitos, CA, USA, 1999.46-50.
[9] Hampapur Arun, Bolle Ruud M.Feature based indexing for media tracking [A].In:Proc of the IEEE International Conference on Multimedia and Expo (Ⅲ)[C].New York, NY, USA, 2000.1709-1712.
[10] Zhou X S, Huang T S.Relevance feedback for image retrieval:a comprehensive review [J].Multimedia System, 2003, 8(6):536-544.

Memo

Memo:

Biographies: Wang Xiaoling(1975—), female, graduate;Xie Kanglin(corresponding author), male, professor, xie-kl@mail.cs.sjtu.edu.cn.

Common functions