A comparative study of statistical methods for characterisation of materials surfaces by means of texture analysis. (1st January 2013)

• Record Type: Journal Article
• Authors: de Araújo, Sidnei Alves; Alves, Wonder Alexandre Luz; Librantz, André Felipe Henriques; Belan, Peterson Adriano
• Is Part Of: International journal of computer applications technology. Volume 46:Number 4(2013)
• Page Start: 297
• Page End: 306
• Publication Date: 2013-01-01
• Subjects: texture -- statistical descriptors -- materials surface -- automatic inspection -- artificial neural network -- ANN -- moments of histogram -- MH -- spatial grey level dependence -- SGLD -- grey level difference -- sums and differences histograms -- grey level run length matrices -- GLRLM; Technology -- Data processing -- Periodicals; 620.00285
• Languages: English
• ISSNs: 0952-8091

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.