Fuzzy segmentation for object-based image classification

Authors: Lizarazo, I.¹; Elsner, P.²

Source: International Journal of Remote Sensing, Volume 30, Number 6, 2009 , pp. 1643-1649(7)

Buy & download fulltext article:

Price: $55.77 plus tax (Refund Policy)

Abstract:

This Letter proposes an object-based image classification procedure which is based on fuzzy image-regions instead of crisp image-objects. The approach has three stages: (a) fuzzification in which fuzzy image-regions are developed, resulting in a set of images whose digital values express the degree of membership of each pixel to target land-cover classes; (b) feature analysis in which contextual properties of fuzzy image-regions are quantified; and (c) defuzzification in which fuzzy image-regions are allocated to target land-cover classes. The proposed procedure is implemented using automated statistical techniques that require very little user interaction. The results indicate that fuzzy segmentation-based methods produce acceptable thematic accuracy and could represent a viable alternative to current crisp image segmentation approaches.

Document Type: Research article

DOI: http://dx.doi.org/10.1080/01431160802460062

Affiliations: 1: Cadastral Engineering and Geodesy Department, Universidad Distrital Francisco Jose de Caldas, Bogota, Colombia 2: Birkbeck College, University of London, London, United Kingdom

Publication date: 2009-01-01

More about this publication?