Precipitates Segmentation from Scanning Electron Microscope Images through Machine Learning Techniques

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2011

Autores

Papa, JP (Autor) Outra; Pereira, CR (Autor) Outra; de Albuquerque, VHC (Autor) Outra; Silva, CC (Autor) Outra; Falcao, AX (Autor) Outra; João Manuel R. S. Tavares (Autor) FEUP

Ata de Conferência Internacional

Título: COMBINATORIAL IMAGE ANALYSIS

Páginas: 456-468

14th International Workshop on Combinatorial Image Analysis (IWCIA)

Madrid, SPAIN, MAY 23-25, 2011

Indexação

ISI Web of Knowledge - 3 Citações

Scopus - 8 Citações

Outras Informações

ID Authenticus: P-007-YHP

DOI: 10.1007/978-3-642-21073-0_40

Abstract (EN): The presence of precipitates in metallic materials affects its durability, resistance and mechanical properties. Hence, its automatic identification by image processing and machine learning techniques may lead to reliable and efficient assessments on the materials. In this paper, we introduce four widely used supervised pattern recognition techniques to accomplish metallic precipitates segmentation in scanning electron microscope images from dissimilar welding on a Hastelloy C-276 alloy: Support Vector Machines, Optimum-Path Forest, Self Organizing Maps and a Bayesian classifier. Experimental results demonstrated that all classifiers achieved similar recognition rates with good results validated by an expert in metallographic image analysis.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 13