National Taiwan Ocean University Institutional Repository:Item 987654321/28602
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 26994/38795
造访人次 : 2390336      在线人数 : 143
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 进阶搜寻


题名: Self-organizing Fusion Neural Networks
作者: Jung-Hua Wang;Chun-Shun Tseng;Sih-Yin Shen;Ya-Yun Jheng
贡献者: NTOU:Department of Electrical Engineering
关键词: neural networks;image segmentation;clustering;counteracting learning;watershed
日期: 2007
上传时间: 2011-10-21T02:38:25Z
出版者: Journal of Advanced Computational Intelligence and Intelligent Informatics
摘要: Abstract:This paper presents a self-organizing fusion neural network (SOFNN) effective in performing fast clustering and segmentation. Based on a counteracting learning scheme, SOFNN employs two parameters that together control the training in a counteracting manner to obviate problems of over-segmentation and under-segmentation. In particular, a simultaneous region-based updating strategy is adopted to facilitate an interesting fusion effect useful for identifying regions comprising an object in a self-organizing way. To achieve reliable merging, a dynamic merging criterion based on both intra-regional and inter-regional local statistics is used. Such extension in adjacency not only helps achieve more accurate segmentation results, but also improves input noise tolerance. Through iterating the three phases of simultaneous updating, self-organizing fusion, and extended merging, the training process converges without manual intervention, thereby conveniently obviating the need of pre-specifying the terminating number of objects. Unlike existing methods that sequentially merge regions, all regions in SOFNN can be processed in parallel fashion, thus providing great potentiality for a fully parallel hardware implementation.
關聯: 11(6), PP.610-619
显示于类别:[電機工程學系] 期刊論文


档案 描述 大小格式浏览次数



著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈