Please use this identifier to cite or link to this item:
Scopus Web of ScienceĀ® Altmetric
Type: Conference paper
Title: Man-made structure segmentation using gaussian procesess and wavelet features.
Author: Zhou, H.
Suter, D.
Citation: Proceedings of the 14th IEEE International Conference on Image Processing, San Antonio, Texas, USA., 2007: pp.IV-349-IV-352
Publisher: IEEE
Publisher Place: Online
Issue Date: 2007
ISBN: 1424414377
ISSN: 1522-4880
Conference Name: IEEE International Conference on Image Processing (14th : 2007 : San Antonio, Texas)
Statement of
Hang Zhou and David Suter
Abstract: We apply Gaussian process classification (GPC) to man-made structure segmentation, treated as a two class problem. GPC is a discriminative approach, and thus focuses on modelling the posterior directly. It relaxes the strong assumption of conditional independence of the observed data (generally used in a generative model). In addition, wavelet transform features, which are effective in describing directional textures, are incorporated in the feature vector. Satisfactory results have been obtained which show the effectiveness of our approach.
Keywords: Man-made structure segmentation
Gaussianprocess (GP)
Gaussian process classification (GPC)
Expectation Propagation (EP)
wavelet transform.
DOI: 10.1109/ICIP.2007.4380026
Description (link):
Published version:
Appears in Collections:Aurora harvest 5
Computer Science publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.