Title: A comparative study of statistical methods for characterisation of materials surfaces by means of texture analysis

Authors: Sidnei Alves De Araújo; Wonder Alexandre Luz Alves; André Felipe Henriques Librantz; Peterson Adriano Belan

Addresses: Industrial Engineering Post Graduation Program, Universidade Nove de Julho (UNINOVE), Av. Francisco Matarazzo, 612 – Água Branca, Zip Code: 05001-100, São Paulo, SP, Brazil ' Department of Informatics, Universidade Nove de Julho (UNINOVE), Av. Doutor Adolfo Pinto, 109 – Barra Funda, São Paulo, Zip Code: 01156-050, São Paulo, SP, Brazil ' Industrial Engineering Post Graduation Program, Universidade Nove de Julho (UNINOVE), Av. Francisco Matarazzo, 612 – Água Branca, Zip Code: 05001-100, São Paulo, SP, Brazil ' Industrial Engineering Post Graduation Program, Universidade Nove de Julho (UNINOVE), Av. Francisco Matarazzo, 612 – Água Branca, Zip Code: 05001-100, São Paulo, SP, Brazil

Abstract: Texture is an important attribute to distinguish objects and materials. Thus, along the decades many texture analysis methods have been proposed and utilised in a variety of application domains. Due to the fact there is not a generic method to describe a large variety of textures, comparative studies among the related methods became necessary. This paper describes a comparative study of the main statistical methods applied to materials surface characterisation. In order to evaluate the performance of the compared methods, an unsupervised neural network was used to classify a set of 3,000 textures images, divided in five categories, with different levels of details. Inferences from this work could assist those ones that intend to perform some tasks involving automatic inspection of texture, mainly in materials science context.

Keywords: texture analysis; statistical descriptors; materials surfaces; automatic inspection; artificial neural networks; ANNs; moments of histogram; spatial grey level dependence; SGLD; grey level difference; sums and differences histograms; grey level run length matrices; GLRLM; texture images; image classification; materials science.

DOI: 10.1504/IJCAT.2013.053420

International Journal of Computer Applications in Technology, 2013 Vol.46 No.4, pp.297 - 306

Received: 08 May 2021
Accepted: 12 May 2021

Published online: 21 Apr 2013 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article