Rotation invariant texture descriptors based on Gaussian Markov random fields for classification
Rotation invariant texture descriptors based on Gaussian Markov random fields for classification
Local Parameter Histograms (LPH) based on Gaussian–Markov random fields (GMRFs) have been successfully used in effective texture discrimination. LPH features represent the normalized histograms of locally estimated GMRF parameters via local linear regression. However, these features are not rotation invariant. In this paper two techniques to design rotation invariant LPH texture descriptors are discussed namely, Rotation Invariant LPH (RI-LPH) and the Isotropic LPH (I-LPH) descriptors. Extensive texture classification experiments using traditional GMRF features, LPH features, RI-LPH and I-LPH features are performed. Furthermore comparisons to the current state-of-the-art texture features are made. Classification results demonstrate that LPH, RI-LPH and I-LPH features achieve significantly better accuracies compared to the traditional GMRF features. RI-LPH descriptors give the highest classification rates and offer the best texture discriminative competency. RI-LPH and I-LPH features maintain higher accuracies in rotation invariant texture classification providing successful rotational invariance.
gaussian–markov random field, texture features, rotational invariance, texture classification
15-21
Dharmagunaw, C.
a2b31066-115f-43d2-9668-5a556504c852
Mahmoodi, S.
91ca8da4-95dc-4c1e-ac0e-f2c08d6ac7cf
Bennett, M.
e42f5213-4410-4284-9e96-74e359df6b19
Niranjan, M.
5cbaeea8-7288-4b55-a89c-c43d212ddd4f
22 October 2016
Dharmagunaw, C.
a2b31066-115f-43d2-9668-5a556504c852
Mahmoodi, S.
91ca8da4-95dc-4c1e-ac0e-f2c08d6ac7cf
Bennett, M.
e42f5213-4410-4284-9e96-74e359df6b19
Niranjan, M.
5cbaeea8-7288-4b55-a89c-c43d212ddd4f
Dharmagunaw, C., Mahmoodi, S., Bennett, M. and Niranjan, M.
(2016)
Rotation invariant texture descriptors based on Gaussian Markov random fields for classification.
Pattern Recognition Letters, 69, .
(doi:10.1016/j.patrec.2015.10.006).
Abstract
Local Parameter Histograms (LPH) based on Gaussian–Markov random fields (GMRFs) have been successfully used in effective texture discrimination. LPH features represent the normalized histograms of locally estimated GMRF parameters via local linear regression. However, these features are not rotation invariant. In this paper two techniques to design rotation invariant LPH texture descriptors are discussed namely, Rotation Invariant LPH (RI-LPH) and the Isotropic LPH (I-LPH) descriptors. Extensive texture classification experiments using traditional GMRF features, LPH features, RI-LPH and I-LPH features are performed. Furthermore comparisons to the current state-of-the-art texture features are made. Classification results demonstrate that LPH, RI-LPH and I-LPH features achieve significantly better accuracies compared to the traditional GMRF features. RI-LPH descriptors give the highest classification rates and offer the best texture discriminative competency. RI-LPH and I-LPH features maintain higher accuracies in rotation invariant texture classification providing successful rotational invariance.
Text
Manuscript_PRL.pdf
- Other
Restricted to Repository staff only
Request a copy
Text
Dharmagunawardhana_Rotation.pdf
- Accepted Manuscript
More information
Accepted/In Press date: 5 October 2015
Published date: 22 October 2016
Keywords:
gaussian–markov random field, texture features, rotational invariance, texture classification
Identifiers
Local EPrints ID: 382641
URI: http://eprints.soton.ac.uk/id/eprint/382641
PURE UUID: 38175b2d-21db-40c7-8d2e-f206fb40d844
Catalogue record
Date deposited: 08 Oct 2015 10:50
Last modified: 15 Mar 2024 03:29
Export record
Altmetrics
Contributors
Author:
C. Dharmagunaw
Author:
S. Mahmoodi
Author:
M. Bennett
Author:
M. Niranjan
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics