Classification of ordered texture images using regression modelling and granulometric features

Mahmuda Khatun, Alison Gray, Stephen Marshall

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

Structural information available from the granulometry of an image has been used widely in image texture analysis and classification. In this paper we present a method for classifying texture images which follow an intrinsic ordering
of textures, using polynomial regression to express granulometric moments as a function of class label. Separate models are built for each individual moment and combined for back-prediction of the class label of a new image. The methodology was developed on synthetic images of evolving textures and tested using real images of 8 different grades of cut-tear-curl black tea leaves.
For comparison, grey level co-occurrence (GLCM) based features were also computed, and both feature types were used in a range of classifiers including the regression approach. Experimental results demonstrate the superiority of the granulometric moments over GLCM-based features for classifying these tea images.
LanguageEnglish
Pages70-75
Number of pages6
Publication statusPublished - 9 Sep 2011
EventIrish Machine Vision and Image Processing Conference - Dublin, Ireland
Duration: 8 Sep 20119 Sep 2011

Conference

ConferenceIrish Machine Vision and Image Processing Conference
CountryIreland
CityDublin
Period8/09/119/09/11

Fingerprint

Textures
Labels
Image texture
Classifiers
Polynomials
Tea

Keywords

  • granulometry
  • structuring
  • pattern spectrum

Cite this

Khatun, M., Gray, A., & Marshall, S. (2011). Classification of ordered texture images using regression modelling and granulometric features. 70-75. Paper presented at Irish Machine Vision and Image Processing Conference , Dublin, Ireland.
Khatun, Mahmuda ; Gray, Alison ; Marshall, Stephen. / Classification of ordered texture images using regression modelling and granulometric features. Paper presented at Irish Machine Vision and Image Processing Conference , Dublin, Ireland.6 p.
@conference{7e6b2f76054b49acba1ca620f82b9df3,
title = "Classification of ordered texture images using regression modelling and granulometric features",
abstract = "Structural information available from the granulometry of an image has been used widely in image texture analysis and classification. In this paper we present a method for classifying texture images which follow an intrinsic orderingof textures, using polynomial regression to express granulometric moments as a function of class label. Separate models are built for each individual moment and combined for back-prediction of the class label of a new image. The methodology was developed on synthetic images of evolving textures and tested using real images of 8 different grades of cut-tear-curl black tea leaves.For comparison, grey level co-occurrence (GLCM) based features were also computed, and both feature types were used in a range of classifiers including the regression approach. Experimental results demonstrate the superiority of the granulometric moments over GLCM-based features for classifying these tea images.",
keywords = "granulometry, structuring, pattern spectrum",
author = "Mahmuda Khatun and Alison Gray and Stephen Marshall",
year = "2011",
month = "9",
day = "9",
language = "English",
pages = "70--75",
note = "Irish Machine Vision and Image Processing Conference ; Conference date: 08-09-2011 Through 09-09-2011",

}

Khatun, M, Gray, A & Marshall, S 2011, 'Classification of ordered texture images using regression modelling and granulometric features' Paper presented at Irish Machine Vision and Image Processing Conference , Dublin, Ireland, 8/09/11 - 9/09/11, pp. 70-75.

Classification of ordered texture images using regression modelling and granulometric features. / Khatun, Mahmuda; Gray, Alison; Marshall, Stephen.

2011. 70-75 Paper presented at Irish Machine Vision and Image Processing Conference , Dublin, Ireland.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Classification of ordered texture images using regression modelling and granulometric features

AU - Khatun, Mahmuda

AU - Gray, Alison

AU - Marshall, Stephen

PY - 2011/9/9

Y1 - 2011/9/9

N2 - Structural information available from the granulometry of an image has been used widely in image texture analysis and classification. In this paper we present a method for classifying texture images which follow an intrinsic orderingof textures, using polynomial regression to express granulometric moments as a function of class label. Separate models are built for each individual moment and combined for back-prediction of the class label of a new image. The methodology was developed on synthetic images of evolving textures and tested using real images of 8 different grades of cut-tear-curl black tea leaves.For comparison, grey level co-occurrence (GLCM) based features were also computed, and both feature types were used in a range of classifiers including the regression approach. Experimental results demonstrate the superiority of the granulometric moments over GLCM-based features for classifying these tea images.

AB - Structural information available from the granulometry of an image has been used widely in image texture analysis and classification. In this paper we present a method for classifying texture images which follow an intrinsic orderingof textures, using polynomial regression to express granulometric moments as a function of class label. Separate models are built for each individual moment and combined for back-prediction of the class label of a new image. The methodology was developed on synthetic images of evolving textures and tested using real images of 8 different grades of cut-tear-curl black tea leaves.For comparison, grey level co-occurrence (GLCM) based features were also computed, and both feature types were used in a range of classifiers including the regression approach. Experimental results demonstrate the superiority of the granulometric moments over GLCM-based features for classifying these tea images.

KW - granulometry

KW - structuring

KW - pattern spectrum

UR - http://sites.google.com/site/imvip2011/

M3 - Paper

SP - 70

EP - 75

ER -

Khatun M, Gray A, Marshall S. Classification of ordered texture images using regression modelling and granulometric features. 2011. Paper presented at Irish Machine Vision and Image Processing Conference , Dublin, Ireland.