Classification of ordered texture images using regression modelling and granulometric features

Khatun, Mahmuda and Gray, Alison and Marshall, Stephen (2011) Classification of ordered texture images using regression modelling and granulometric features. In: Irish Machine Vision and Image Processing Conference, 2011-09-08 - 2011-09-09.

[img]
Preview
 PDF
imvip_ieee_5.pdf
Final Published Version
Download (205kB)| Preview

    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.

    Creators(s): Khatun, Mahmuda, Gray, Alison ORCID logoORCID: https://orcid.org/0000-0002-6273-0637 and Marshall, Stephen ORCID logoORCID: https://orcid.org/0000-0001-7079-5628;
    Item type:Conference or Workshop Item(Paper)
    ID code:33186
    Keywords:granulometry, structuring, pattern spectrum, Mathematics, Probabilities. Mathematical statistics, Electrical engineering. Electronics Nuclear engineering
    Subjects:Science > Mathematics
    Science > Mathematics > Probabilities. Mathematical statistics
    Technology > Electrical engineering. Electronics Nuclear engineering
    Department:Faculty of Science > Mathematics and Statistics
    Faculty of Engineering > Electronic and Electrical Engineering
    Technology and Innovation Centre > Sensors and Asset Management
    Depositing user: Pure Administrator
    Date deposited:13 Sep 2011 14:11
    Last modified:01 Jan 2021 07:37
    Related URLs:
    URI:https://strathprints.strath.ac.uk/id/eprint/33186
    Export data:
    CORE (COnnecting REpositories)