Semantic hierarchies for image annotation: A survey

被引:106
作者
Tousch, Anne-Marie [1 ,2 ]
Herbin, Stephane [1 ]
Audibert, Jean-Yves [2 ,3 ]
机构
[1] Off Natl Etud & Rech Aerosp, French Aerosp Lab, Palaiseau, France
[2] Univ Paris Est, Ecole Ponts ParisTech, IMAGINE, Marne La Vallee, France
[3] SIERRA, ENS, INRIA, Paris, France
关键词
Image annotation; Semantic description; Structured vocabulary; Image retrieval; OBJECT; RETRIEVAL; ONTOLOGY; CLASSIFICATION; MULTICLASS; TAXONOMIES; THESAURI;
D O I
10.1016/j.patcog.2011.05.017
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this survey, we argue that using structured vocabularies is capital to the success of image annotation. We analyze literature on image annotation uses and user needs, and we stress the need for automatic annotation. We briefly expose the difficulties posed to machines for this task and how it relates to controlled vocabularies. We survey contributions in the field showing how structures are introduced. First we present studies that use unstructured vocabulary, focusing on those introducing links between categories or between features. Then we review work using structured vocabularies as an input and analyze how the structure is exploited. (C) 2011 Elsevier Ltd. All rights reserved.
引用
收藏
页码:333 / 345
页数:13
相关论文
共 105 条
[1]  
Ahuja N., 2007, P IEEE INT C COMPUTE, P1
[2]   Learning Bayesian classifiers for scene classification with a visual grammar [J].
Aksoy, S ;
Koperski, K ;
Tusk, C ;
Marchisio, G ;
Tilton, JC .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2005, 43 (03) :581-589
[3]  
Amit Y., 2007, P 24 INT C MACH LEAR, P17, DOI 10.1145/1273496.1273499
[4]  
[Anonymous], ACCV 09
[5]  
[Anonymous], KCAP 03
[6]  
[Anonymous], IEEE C COMP VIS PATT
[7]  
[Anonymous], 2007, 2007 IEEE C COMPUTER, DOI [10.1109/CVPR.2007.383086, DOI 10.1109/CVPR.2007.383086]
[8]  
[Anonymous], 2007, 2007 IEEE 11 INT C C
[9]  
[Anonymous], LECT NOTES COMPUT SC
[10]  
[Anonymous], P 2008 IEEE C COMP V