Finding compound structures in images using image segmentation and graph-based knowledge discovery

Date
2009-07
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2009
Print ISSN
Electronic ISSN
Publisher
IEEE
Volume
Issue
Pages
V252 - V255
Language
English
Type
Conference Paper
Journal Title
Journal ISSN
Volume Title
Series
Abstract

We present an unsupervised method for discovering compound image structures that are comprised of simpler primitive objects. An initial segmentation step produces image regions with homogeneous spectral content. Then, the segmentation is translated into a relational graph structure whose nodes correspond to the regions and the edges represent the relationships between these regions. We assume that the region objects that appear together frequently can be considered as strongly related. This relation is modeled using the transition frequencies between neighboring regions, and the significant relations are found as the modes of a probability distribution estimated using the features of these transitions. Experiments using an Ikonos image show that subgraphs found within the graph representing the whole image correspond to parts of different high-level compound structures. ©2009 IEEE.

Course
Other identifiers
Book Title
Keywords
Graph-based analysis, Image segmentation, Object detection, Compound images, Compound structures, Graph-based, Graph-based analysis, IKONOS images, Image regions, Initial segmentation, Knowledge Discovery, Object Detection, Relational graph, Spectral content, Subgraphs, Transition frequencies, Unsupervised method, Digital image storage, Geology, Image analysis, Probability distributions, Remote sensing
Citation
Published Version (Please cite this version)