Evaluation of multilayer perceptron and self-organizing map neural network topologies applied on microstructure segmentation from metallographic images

• Tipo: Artigo em Revista Científica Internacional
• Data: 2009

Autores

Victor Hugo C. de Albuquerque (Autor) Outra; Auzuir Ripardo de Alexandria (Autor) Outra; Paulo César Cortez (Autor) Outra; João Manuel R. S. Tavares (Autor) FEUP

Revista

Título: NDT & E International

Vol. 42 Nº 7

Páginas: 644-651

ISSN: 0963-8695

Editora: Elsevier

Indexação

ISI Web of Knowledge - 37 Citações

ISI Web of Science

Scopus - 79 Citações

INSPEC

COMPENDEX

Classificação Científica

FOS: Ciências da engenharia e tecnologias > Outras ciências da engenharia e tecnologias

CORDIS: Ciências Tecnológicas > Tecnologia > Tecnologia de computadores > Processamento de imagem ; Ciências Físicas > Ciência de computadores > Design de sistemas > Redes neuronais

Outras Informações

ID Authenticus: P-003-FJ0

DOI: 10.1016/j.ndteint.2009.05.002

Abstract (EN): Artificial neuronal networks have been used intensively in many domains to accomplish different computational tasks. One of these tasks is the segmentation of objects in images, like to segment microstructures from metallographic images, and for that goal several network topologies were proposed. This paper presents a comparative analysis between multilayer perceptron and selforganizing map topologies applied to segment microstructures from metallographic images. The multilayer perceptron neural network training was based on the backpropagation algorithm, that is a supervised training algorithm, and the self-organizing map neural network was based on the Kohonen algorithm, being thus an unsupervised network. Sixty samples of cast irons were considered for experimental comparison and the results obtained by multilayer perceptron neural network were very similar to the ones resultant by visual human inspection. However, the results obtained by selforganizing map neural network were not so good. Indeed, multilayer perceptron neural network always segmented efficiently the microstructures of samples in analysis, what did not occur when selforganizing map neural network was considered. From the experiments done, we can conclude that multilayer perceptron network is an adequate tool to be used in Material Science fields to accomplish microstructural analysis from metallographic images in a fully automatic and accurate manner.

Idioma: Inglês

Tipo (Avaliação Docente): Científica