Fast Search with Data-Oriented Multi-Index Hashing for Multimedia Data

doi:10.3837/tiis.2015.07.015

	Fast Search with Data-Oriented Multi-Index Hashing for Multimedia Data
	Ma, Yanping 1,2; Zou, Hailin 1; Xie, Hongtao 3; Su, Qingtang 1
	2015-07-31
发表期刊	KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS
ISSN	1976-7277
卷号	9 期号:7 页码:2599-2613
摘要	Multi-index hashing (MIH) is the state-of-the-art method for indexing binary codes, as it divides long codes into substrings and builds multiple hash tables. However, MIH is based on the dataset codes uniform distribution assumption, and will lose efficiency in dealing with non-uniformly distributed codes. Besides, there are lots of results sharing the same Hamming distance to a query, which makes the distance measure ambiguous. In this paper, we propose a data-oriented multi-index hashing method (DOMIH). We first compute the covariance matrix of bits and learn adaptive projection vector for each binary substring. Instead of using substrings as direct indices into hash tables, we project them with corresponding projection vectors to generate new indices. With adaptive projection, the indices in each hash table are near uniformly distributed. Then with covariance matrix, we propose a ranking method for the binary codes. By assigning different bit-level weights to different bits, the returned binary codes are ranked at a finer-grained binary code level. Experiments conducted on reference large scale datasets show that compared to MIH the time performance of DOMIH can be improved by 36.9%-87.4%, and the search accuracy can be improved by 22.2%. To pinpoint the potential of DOMIH, we further use near-duplicate image retrieval as examples to show the applications and the good performance of our method.
关键词	Nearest Neighbor Search Binary Codes Indexing
DOI	10.3837/tiis.2015.07.015
收录类别	SCI
语种	英语
资助项目	Strategic Priority Research Program of the Chinese Academy of Sciences[XDA06030602] ; National High Technology Research and Development Program[2011AA010705] ; National Nature Science Foundation of China[61170161] ; National Nature Science Foundation of China[61303171] ; National Nature Science Foundation of China[61271406] ; Natural Science Foundation of Shandong Province[ZR2014FM005]
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Telecommunications
WOS记录号	WOS:000358997000015
出版者	KSII-KOR SOC INTERNET INFORMATION
引用统计	被引频次：4[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/9538
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Ma, Yanping
作者单位	1.Ludong Univ, Scholol Informat & Elect Engn, Yantai, Peoples R China 2.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Informat Engn, Natl Engn Lab Informat Secur Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Ma, Yanping,Zou, Hailin,Xie, Hongtao,et al. Fast Search with Data-Oriented Multi-Index Hashing for Multimedia Data[J]. KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS,2015,9(7):2599-2613.
APA	Ma, Yanping,Zou, Hailin,Xie, Hongtao,&Su, Qingtang.(2015).Fast Search with Data-Oriented Multi-Index Hashing for Multimedia Data.KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS,9(7),2599-2613.
MLA	Ma, Yanping,et al."Fast Search with Data-Oriented Multi-Index Hashing for Multimedia Data".KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS 9.7(2015):2599-2613.