Morphological segmentation of binary patterns

Pierre Soille

doi:10.1016/j.patrec.2008.10.015

Morphological segmentation of binary patterns

2009-03-01

555

PRE

AI

DOI：10.1016/j.patrec.2008.10.015

Original

Original request for help

Save

Abstract

En 中文

This paper presents a method for segmenting binary patterns into seven mutually exclusive categories: core, islet, loop, bridge, perforation, edge, and branch. This is achieved by applying a series of morphological transformations such as erosions, geodesic dilations, reconstruction by dilation, anchored skeletonisation, etc. The proposed method depends on a single parameter only and can be used for characterising binary patterns with emphasis on connections between their parts as measured at varying analysis scales. This is illustrated on two examples related to land cover maps and circuit board defect detection. (c) 2008 Elsevier B.V. All rights reserved.

Keywords:

Morphological image analysis

Pattern segmentation

Connectivity

Morphological segmentation of binary patterns

Abstract

Journal

Organization