An efficient algorithm for attention-driven image interpretation from segments

被引:10
作者
Fu, Hong [1 ]
Chi, Zheru [1 ]
Feng, Dagan [1 ,2 ]
机构
[1] Hong Kong Polytech Univ, Elect & Informat Engn Dept, Ctr Multimedia Signal Proc, Kowloon, Hong Kong, Peoples R China
[2] Univ Sydney, Sch Informat Technol, Sydney, NSW 2006, Australia
关键词
Computer vision; Search optimization; Region combination; Visual attention model; Image understanding; Content-based image retrieval; SELECTIVE VISUAL-ATTENTION; MODEL; RECOGNITION; SENSITIVITY;
D O I
10.1016/j.patcog.2008.06.021
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In the attention-driven image interpretation process, an image is interpreted as containing several perceptually attended objects as well as the background. The process benefits greatly a content-based image retrieval task with attentively important objects identified and emphasized. An important issue to be addressed in an attention-driven image interpretation is to reconstruct several attentive objects iteratively from the segments of an image by maximizing a global attention function, The object reconstruction is a combinational optimization problem with a complexity of 2(N) which is computationally very expensive when the number of segments N is large. in this paper, we formulate the attention-driven image interpretation process by a matrix representation. An efficient algorithm based on the elementary transformation of matrix is proposed to reduce the Computational complexity to 3 omega N(N - 1)(2)/2, where omega is the number of runs. Experimental results oil both the synthetic and real data show a significantly improved processing speed with air acceptable degradation to the accuracy of object formulation. (C) 2008 Elsevier Ltd. All rights reserved.
引用
收藏
页码:126 / 140
页数:15
相关论文
共 37 条
[1]   Attention-based dynamic visual search using inner-scene similarity: Algorithms and bounds [J].
Avraham, T ;
Lindenbaum, M .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (02) :251-264
[2]   Data- and model-driven gaze control for an active-vision system [J].
Backer, G ;
Mertsching, B ;
Bollmann, M .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2001, 23 (12) :1415-1429
[3]  
DEMMEL J, 1999, GRAPH PARTITIONING 2
[4]   Unsupervised segmentation of color-texture regions in images and video [J].
Deng, YN ;
Manjunath, BS .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2001, 23 (08) :800-810
[5]  
Fan R. K, 1997, Spectral Graph Theory
[6]  
FU H, 2005, P 2005 AS PAC WORKSH, P128
[7]   Attention-driven image interpretation with application to image retrieval [J].
Fu, Hong ;
Chi, Zheru ;
Feng, Dagan .
PATTERN RECOGNITION, 2006, 39 (09) :1604-1621
[8]  
HAN J, 2003, INT C IM PROC 14 17, V2, P403
[9]   Focus-of-attention from local color symmetries [J].
Heidemann, G .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2004, 26 (07) :817-830
[10]   A minimum entropy approach to adaptive image polygonization [J].
Hermes, L ;
Buhmann, JM .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2003, 12 (10) :1243-1258