SOM ensemble-based image segmentation

被引:72
作者
Jiang, Y [1 ]
Zhou, ZH [1 ]
机构
[1] Nanjing Univ, Natl Lab Novel Software Technol, Nanjing 210093, Peoples R China
关键词
image segmentation; SOM; neural networks; neural network ensemble; ensemble learning; unsupervised learning;
D O I
10.1007/s11063-004-2022-8
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Image segmentation plays an important role in image analysis and image understanding. In this paper, an image segmentation method based on ensemble of SOM neural networks is proposed, which clusters the pixels in an image according to color and spatial features with many SOM neural networks, and then combines the clustering results to give the final segmentation. Experimental results show that the proposed method performs better than some existing clustering-based image segmentation methods.
引用
收藏
页码:171 / 178
页数:8
相关论文
共 17 条
[1]  
[Anonymous], SELF ORGANIZING MAPS
[2]  
Asano T, 1996, PROCEEDINGS OF THE SEVENTH ANNUAL ACM-SIAM SYMPOSIUM ON DISCRETE ALGORITHMS, P104
[3]   Quantitative evaluation of color image segmentation results [J].
Borsotti, M ;
Campadelli, P ;
Schettini, R .
PATTERN RECOGNITION LETTERS, 1998, 19 (08) :741-747
[4]   Bagging predictors [J].
Breiman, L .
MACHINE LEARNING, 1996, 24 (02) :123-140
[5]   Color image segmentation: advances and prospects [J].
Cheng, HD ;
Jiang, XH ;
Sun, Y ;
Wang, JL .
PATTERN RECOGNITION, 2001, 34 (12) :2259-2281
[6]  
Dietterich T.G., 2002, The Handbook of Brain Theory and Neural Networks, V2nd ed.
[7]  
ESTIVILLCASTRO V, 2002, SIGKDD EXPLORATIONS, V4, P65, DOI DOI 10.1145/568574.568575
[8]   A decision-theoretic generalization of on-line learning and an application to boosting [J].
Freund, Y ;
Schapire, RE .
JOURNAL OF COMPUTER AND SYSTEM SCIENCES, 1997, 55 (01) :119-139
[9]  
Jiang Y, 2003, LECT NOTES ARTIF INT, V2639, P640
[10]   SELF-ORGANIZED FORMATION OF TOPOLOGICALLY CORRECT FEATURE MAPS [J].
KOHONEN, T .
BIOLOGICAL CYBERNETICS, 1982, 43 (01) :59-69