Image object classification using saccadic search, spatio-temporal pattern encoding and self-organisation

被引:6
作者
Becanovic, V [1 ]
机构
[1] George Mason Univ, Inst Biosci Bioinformat & Biotechnol, Fairfax, VA 22030 USA
关键词
saccadic eye movement; foveation; segmentation; PCNN time-series; signatures; hierarchical SOM;
D O I
10.1016/S0167-8655(99)00154-3
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A method for extracting features from photographic images is investigated. The input image is through a saccadic search algorithm divided into a set of sub-images, segmented and coded by a spatio-temporal encoding engine. The input image is thus represented by a set of characteristic pattern signatures, well suited for classification by an unsupervised neural network. A strategy using multiple self-organising feature maps (SOM) in a hierarchical manner is used. With this approach, using a certain degree of user selection, a database of sub-images is grouped according to similarities in signature space. (C) 2000 Elsevier Science B.V. All rights reserved.
引用
收藏
页码:253 / 263
页数:11
相关论文
共 22 条
[1]  
[Anonymous], 1998, IMAGE PROCESSING USI
[2]  
BECANOVIC V, 1998, VIDYNN 98
[3]   Competitive neural trees for pattern classification [J].
Behnke, S ;
Karayiannis, NB .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (06) :1352-1369
[4]  
ECKHORN R, 1999, IEEE T NEURAL NETWOR
[5]  
Gonzales R.C., 1992, DIGITAL IMAGE PROCES
[6]  
Haykin S., 1994, NEURAL NETWORKS COMP
[7]   The effects of semantic consistency on eye movements during complex scene viewing [J].
Henderson, JM ;
Weeks, PA ;
Hollingworth, A .
JOURNAL OF EXPERIMENTAL PSYCHOLOGY-HUMAN PERCEPTION AND PERFORMANCE, 1999, 25 (01) :210-228
[8]  
HORN D, 1997, NEURAL COMPUTATION, V9
[9]   PULSE-COUPLED NEURAL NETS - TRANSLATION, ROTATION, SCALE, DISTORTION, AND INTENSITY SIGNAL INVARIANCE FOR IMAGES [J].
JOHNSON, JL .
APPLIED OPTICS, 1994, 33 (26) :6239-6253
[10]  
KATELAERE BD, 1997, P C WSOM 97