面向互联网的大规模重复图像检索技术研究

doi:10.3969/j.issn.1000-436x.2014.12.023

Journal on Communications ›› 2014, Vol. 35 ›› Issue (12): 196-202.doi: 10.3969/j.issn.1000-436x.2014.12.023

• Correspondences • Previous Articles Next Articles

Large-scale duplicate image retrieval technical research for the internet

Shu-peng WANG¹,Ming CHEN²,Guang-jun WU¹

¹ Institute of Information Engineering,Chinese Academy of Sciences,Beijing 100093,China
² School of Software Engineering,Zhengzhou University of Light Industry,Zhengzhou 450000,China

Online:2014-12-25 Published:2017-06-17
Supported by:
The National Natural Science Foundation of China;The National Natural Science Foundation of China;The National High Technology Re-search and Development Program of China (863 Program);The National High Technology Re-search and Development Program of China (863 Program);The National High Technology Re-search and Development Program of China (863 Program);Beijing Municipal Science and Technology Project

Abstract

Abstract:

For the typical social media application on the internet,a large-scale distributed duplicate image retrieval ap-proach based on random projection and the block DCT coefficients was proposed.On the basis of Hadoop,this approach exploited image signatures generated by random projection mapping to retrieve HBase efficiently.And candidate images with high-recall were achieved.Then in order to improve the retrieval precision,the block DCT coefficients were used to further filter candidate images.For 12 million images,experimental results showed that with our approach the recall ratio reached 98%,the precision ratio reached 93.2%,and the average retrieval time was 6.7s when H=2 and T=150.

Key words: social media, random projection mapping, image signature, block DCT coefficients, Hadoop cluster

Shu-peng WANG,Ming CHEN,Guang-jun WU. Large-scale duplicate image retrieval technical research for the internet[J]. Journal on Communications, 2014, 35(12): 196-202.

Figures/Tables 9

References 13

[1]	[EB/OL]. 2013.
[2]	SANG J T . Collective search and recommendation in social media[A]. Proc of the 20th ACM International Conference on Multimedia[C]. 2012.1421-1424.
[3]	SANG J T , XU C S . Browse by chunks:topic mining and organizing on web-scale social media[J]. ACM Transactions on Multimedia Computing,Communications,and Applications, 2011,7s(1):30.
[4]	SANG J T , XU C S . Learn to personalized image search from the photo sharing Web sites[J]. IEEE Transactions on Multimedia, 2012,14(4):963-974.
[5]	[EB/OL]. 2013.
[6]	CHANGICK K . Content-based image copy detection[J]. Signal Proc-essing:Image Communication, 2003,18(3):169-184.
[7]	WANG B , LI Z W , LI M J . Large-scale duplicate detection for Web image search[A]. International Conference on Multimedia Computing and Systems/International Conference on Multimedia and Expo[C]. 2006.353-356.
[8]	THOMEE B , HUISKES M J , BAKKER E . Large scale image copy detection evaluation[A]. Proc of the 1st ACM International Conference on Multimedia information Retrieval[C]. 2008.59-66.
[9]	JOLY A , BUISSON O , FRELICOT C . Content-based copy retrieval using distortion-based probabilistic similarity search[J]. IEEE Trans-actions on Multimedia, 2007,9(2):293-306.
[10]	CHARIKAR M S . Similarity estimation techniques from rounding algorithms[A]. Proc of the 34th Annual ACM Symposium on Theory of Computing[C]. Montréal,Canada, 2002.380-388.
[11]	YUAN P S , SHA C F , WANG X L ,et al. C-approximate nearest neighbor query algorithm based on learning for high-dimensional data[J]. Journal of Software, 2012,23(8):2018-2031.
[12]	XIE K , WEN J G , ZHANG D F ,et al. Bloom filter query algorithm[J]. Journal of Software, 2009,20(1):96-108.
[13]	LING H F , XU Z H , ZOU F H ,et al. A robust image copy detection scheme using ordinal measure of full DCT coefficients[J]. Journal of Computer Research and Development, 2010,47(10):1812-1822.

Metrics

Recommended 0

No Suggested Reading articles found!

字段	值
主键	区域_图像签名_计数
C1：图像ID	图像名
C2：图像特征	图像的整体DCT信息，以字符串的形式存放
C3：图像缩略图	源图像的缩略图，以文件形式存放
C4：图像源文件地址	源图像在系统中的存放位置，以字符串形式存放

Large-scale duplicate image retrieval technical research for the internet

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 13

Related Articles 2

Metrics

Recommended 0

[1]	Yaqiong QIAO, Xiangyang LUO, Jiangtao MA, Chenliang LI, Meng ZHANG, Ruixiang LI. Social media user geolocalization based on multiple mention relationships [J]. Journal on Communications, 2020, 41(12): 72-81.
[2]	. Large-scale duplicate image retrieval technical research for the internet [J]. Journal on Communications, 2014, 35(12): 23-202.