A Novel Fast Affinity Propagation Based Visual Word Clustering Algorithm

被引:0
作者
Jian, Zhao [1 ]
Jian, Jia [1 ]
Duan, Xie [2 ]
Ning, Feng [1 ]
Yu, Xie [1 ]
机构
[1] NW Univ Xian, Sch Informat Sci & Technol, Xian 710069, Peoples R China
[2] Xian Univ Posts & Telecommun, Sch Elect Engn, Xian 710121, Peoples R China
基金
中国国家自然科学基金;
关键词
Indexing Structure; Vocabulary Tree; Visual Word; Affinity Propagation Clustering;
D O I
10.1166/jctn.2014.3634
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
The weaknesses of k-means clustering would result in deviation of the vocabulary tree structure. In this paper, we developed an improved affinity propagation clustering algorithm based vocabulary tree structure. Three datasets were used to test the tasks: the Corel dataset, the LabelMe dataset and the Caltech-101 dataset. The experimental result shows that this new build method for vocabulary tree offers not only compute vocabulary tree set faster, but also improve the retrieval accuracy.
引用
收藏
页码:2258 / 2262
页数:5
相关论文
共 16 条
  • [1] [Anonymous], 2006, 2006 IEEE COMP SOC C
  • [2] [Anonymous], 2012, QUANTUM MATTER, DOI DOI 10.1166/QM.2012.1012
  • [3] Bose P.K., 2012, Quant Matter, V1, P89, DOI 10.1166/qm.2012.1009
  • [4] Chen D., 2009, P SOC PHOTO-OPT INS, V7257, P360
  • [5] Chiu HH, 2006, J COMPUT THEOR NANOS, V3, P88
  • [6] Optimal clustering in the context of overlapping cluster analysis
    De Mulder, Wim
    [J]. INFORMATION SCIENCES, 2013, 223 : 56 - 74
  • [7] Clustering by passing messages between data points
    Frey, Brendan J.
    Dueck, Delbert
    [J]. SCIENCE, 2007, 315 (5814) : 972 - 976
  • [8] Node Based Clustering Method on Protein-Protein Interaction Network
    Liu, Hao
    Liao, Bo
    Cao, Zhi
    Zhu, Wen
    Li, Renfa
    [J]. JOURNAL OF COMPUTATIONAL AND THEORETICAL NANOSCIENCE, 2009, 6 (10) : 2198 - 2202
  • [9] Narayanan M., 2012, QUANTUM MATTER, V1, P53, DOI DOI 10.1166/QM.2012.1005
  • [10] Evolutionary fuzzy clustering algorithm with knowledge-based evaluation and applications for gene expression profiling
    Park, HS
    Yoo, SH
    Cho, SB
    [J]. JOURNAL OF COMPUTATIONAL AND THEORETICAL NANOSCIENCE, 2005, 2 (04) : 524 - 533