A new approach to image segmentation based on simplified region growing PCNN

被引:48
作者
Lu, Yunfeng [1 ]
Miao, Jun [2 ]
Duan, Lijuan [1 ]
Qiao, Yuanhua [3 ]
Jia, Ruixin [1 ]
机构
[1] Beijing Univ Technol, Coll Comp Sci & Technol, Beijing 100022, Peoples R China
[2] Chinese Acad Sci, Inst Comp Technol, Beijing 100080, Peoples R China
[3] Beijing Univ Technol, Coll Appl Sci, Beijing 100022, Peoples R China
基金
中国国家自然科学基金;
关键词
Image segmentation; Pulse coupled neural network (PCNN); Region growing; Simplified region growing PCNN (SRG-PCNN);
D O I
10.1016/j.amc.2008.05.029
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
The region growing pulse coupled neural network (PCNN) algorithm is an efficient method for multi-value image segmentation. However, as a kind of PCNN models, choosing appropriate parameters are usually difficult. This paper brings forward a new approach which improves the region growing PCNN model by modifying the linking channel function and decreases the complexity of adjusting parameters. The region growing PCNN is not effective when processing the edge pixels between different regions because the edge pixels and central pixels are dealt with unfairly. In order to overcome this disadvantage, the proposed method processes the edge pixels by setting the edge pixels and central pixels to receive same linking input if they are in similar condition. Computer simulations prove it can process the edge pixels efficiently and obtain clear boundaries between different regions. (C) 2008 Elsevier Inc. All rights reserved.
引用
收藏
页码:807 / 814
页数:8
相关论文
共 7 条
[1]   Feature Linking via Synchronization among Distributed Assemblies: Simulations of Results from Cat Visual Cortex [J].
Eckhorn, R. ;
Reitboeck, H. J. ;
Arndt, M. ;
Dicke, P. .
NEURAL COMPUTATION, 1990, 2 (03) :293-307
[2]  
Gu XD, 2002, 2002 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-4, PROCEEDINGS, P175, DOI 10.1109/ICMLC.2002.1176733
[3]   IMAGE SEGMENTATION TECHNIQUES [J].
HARALICK, RM ;
SHAPIRO, LG .
COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1985, 29 (01) :100-132
[4]   PCNN models and applications [J].
Johnson, JL ;
Padgett, ML .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (03) :480-498
[5]   Perfect image segmentation using pulse coupled neural networks [J].
Kuntimad, G ;
Ranganath, HS .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (03) :591-598
[6]  
MA Y, 2006, PRINCIPLES APPL PCNN, P69
[7]   Region growing with pulse-coupled neural networks: An alternative to seeded region growing [J].
Stewart, RD ;
Fermin, I ;
Opper, M .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002, 13 (06) :1557-1562