Morphological granulometry for classification of evolving and ordered texture images.

Mahmuda Khatun, Alison Gray, Stephen Marshall

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

In this work we investigate the use of morphological granulometric moments as texture descriptors to predict time or class of texture images which evolve over time or follow an intrinsic ordering of textures. A cubic polynomial regression was used to model each of several granulometric moments as a function of time or class. These models are then combined and used to predict time or class. The methodology was developed on synthetic images of evolving textures and then successfully applied to classify a sequence of corrosion images to a point on an evolution time scale. Classification performance of the new regression approach is compared to that of linear discriminant analysis, neural networks and support vector machines. We also apply our method to images of black tea leaves, which are ordered according to granule size, and very high classification accuracy was attained compared to existing published results for these images. It was also found that granulometric moments provide much improved classification compared to grey level co-occurrence features for shape-based texture images.
LanguageEnglish
Pages759-763
Number of pages5
Publication statusPublished - Aug 2011
Event 19th European Signal Processing Conference -EUSIPCO 2011 - Barcelona, Spain
Duration: 29 Aug 20112 Sep 2011

Conference

Conference 19th European Signal Processing Conference -EUSIPCO 2011
CountrySpain
CityBarcelona
Period29/08/112/09/11

Fingerprint

Textures
Discriminant analysis
Support vector machines
Polynomials
Corrosion
Neural networks

Keywords

  • morphological granulometric moments
  • cubic polynomial regression
  • evolution time scale
  • texture images

Cite this

Khatun, M., Gray, A., & Marshall, S. (2011). Morphological granulometry for classification of evolving and ordered texture images.. 759-763. Paper presented at 19th European Signal Processing Conference -EUSIPCO 2011, Barcelona, Spain.
Khatun, Mahmuda ; Gray, Alison ; Marshall, Stephen. / Morphological granulometry for classification of evolving and ordered texture images. Paper presented at 19th European Signal Processing Conference -EUSIPCO 2011, Barcelona, Spain.5 p.
@conference{8856970c4d614440aa40334a3f8b5677,
title = "Morphological granulometry for classification of evolving and ordered texture images.",
abstract = "In this work we investigate the use of morphological granulometric moments as texture descriptors to predict time or class of texture images which evolve over time or follow an intrinsic ordering of textures. A cubic polynomial regression was used to model each of several granulometric moments as a function of time or class. These models are then combined and used to predict time or class. The methodology was developed on synthetic images of evolving textures and then successfully applied to classify a sequence of corrosion images to a point on an evolution time scale. Classification performance of the new regression approach is compared to that of linear discriminant analysis, neural networks and support vector machines. We also apply our method to images of black tea leaves, which are ordered according to granule size, and very high classification accuracy was attained compared to existing published results for these images. It was also found that granulometric moments provide much improved classification compared to grey level co-occurrence features for shape-based texture images.",
keywords = "morphological granulometric moments, cubic polynomial regression, evolution time scale , texture images",
author = "Mahmuda Khatun and Alison Gray and Stephen Marshall",
year = "2011",
month = "8",
language = "English",
pages = "759--763",
note = "19th European Signal Processing Conference -EUSIPCO 2011 ; Conference date: 29-08-2011 Through 02-09-2011",

}

Khatun, M, Gray, A & Marshall, S 2011, 'Morphological granulometry for classification of evolving and ordered texture images.' Paper presented at 19th European Signal Processing Conference -EUSIPCO 2011, Barcelona, Spain, 29/08/11 - 2/09/11, pp. 759-763.

Morphological granulometry for classification of evolving and ordered texture images. / Khatun, Mahmuda; Gray, Alison; Marshall, Stephen.

2011. 759-763 Paper presented at 19th European Signal Processing Conference -EUSIPCO 2011, Barcelona, Spain.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Morphological granulometry for classification of evolving and ordered texture images.

AU - Khatun, Mahmuda

AU - Gray, Alison

AU - Marshall, Stephen

PY - 2011/8

Y1 - 2011/8

N2 - In this work we investigate the use of morphological granulometric moments as texture descriptors to predict time or class of texture images which evolve over time or follow an intrinsic ordering of textures. A cubic polynomial regression was used to model each of several granulometric moments as a function of time or class. These models are then combined and used to predict time or class. The methodology was developed on synthetic images of evolving textures and then successfully applied to classify a sequence of corrosion images to a point on an evolution time scale. Classification performance of the new regression approach is compared to that of linear discriminant analysis, neural networks and support vector machines. We also apply our method to images of black tea leaves, which are ordered according to granule size, and very high classification accuracy was attained compared to existing published results for these images. It was also found that granulometric moments provide much improved classification compared to grey level co-occurrence features for shape-based texture images.

AB - In this work we investigate the use of morphological granulometric moments as texture descriptors to predict time or class of texture images which evolve over time or follow an intrinsic ordering of textures. A cubic polynomial regression was used to model each of several granulometric moments as a function of time or class. These models are then combined and used to predict time or class. The methodology was developed on synthetic images of evolving textures and then successfully applied to classify a sequence of corrosion images to a point on an evolution time scale. Classification performance of the new regression approach is compared to that of linear discriminant analysis, neural networks and support vector machines. We also apply our method to images of black tea leaves, which are ordered according to granule size, and very high classification accuracy was attained compared to existing published results for these images. It was also found that granulometric moments provide much improved classification compared to grey level co-occurrence features for shape-based texture images.

KW - morphological granulometric moments

KW - cubic polynomial regression

KW - evolution time scale

KW - texture images

M3 - Paper

SP - 759

EP - 763

ER -

Khatun M, Gray A, Marshall S. Morphological granulometry for classification of evolving and ordered texture images.. 2011. Paper presented at 19th European Signal Processing Conference -EUSIPCO 2011, Barcelona, Spain.