Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/30888
Title: Feature-based image patch approximation for lung tissue classification
Authors: Song, Y
Cai, W
Zhou, Y
Feng, DD
Issue Date: 2013
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on medical imaging, 2013, v. 32, no. 4, p. 797-808 How to cite?
Journal: IEEE transactions on medical imaging 
Abstract: In this paper, we propose a new classification method for five categories of lung tissues in high-resolution computed tomography (HRCT) images, with feature-based image patch approximation. We design two new feature descriptors for higher feature descriptiveness, namely the rotation-invariant Gabor-local binary patterns (RGLBP) texture descriptor and multi-coordinate histogram of oriented gradients (MCHOG) gradient descriptor. Together with intensity features, each image patch is then labeled based on its feature approximation from reference image patches. And a new patch-adaptive sparse approximation (PASA) method is designed with the following main components: minimum discrepancy criteria for sparse-based classification, patch-specific adaptation for discriminative approximation, and feature-space weighting for distance computation. The patch-wise labelings are then accumulated as probabilistic estimations for region-level classification. The proposed method is evaluated on a publicly available ILD database, showing encouraging performance improvements over the state-of-the-arts.
URI: http://hdl.handle.net/10397/30888
ISSN: 0278-0062 (print)
1558-254X (online)
DOI: 10.1109/TMI.2013.2241448
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

70
Last Week
1
Last month
Citations as of Aug 16, 2018

WEB OF SCIENCETM
Citations

53
Last Week
0
Last month
0
Citations as of Aug 18, 2018

Page view(s)

192
Last Week
0
Last month
Citations as of Aug 13, 2018

Google ScholarTM

Check

Altmetric


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