A study of image segmentation based on a robust data clustering method

Abstract

AbstractThis paper considers intelligent image clustering and proposes a clustering method based on the self‐organizing mechanism, which is an adaptive and autonomous algorithm. The proposed method solves the problem of initial value setting, which has been a difficulty in the conventional clustering method, and has the feature that the effective clusters are always self‐organized. A method is realized which is robust and does not require empirical setting of the initial value. Thus, the effective initial cluster can always be selected for various kinds of data sets, and an excellent clustering is obtained. A method is proposed in which these features are utilized in image segmentation. © 2004 Wiley Periodicals, Inc. Electron Comm Jpn Pt 3, 87(7): 27–35, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecjc.10154