Fast automatic microstructural segmentation of ferrous alloy samples using opti...

• Autor(es): João Paulo Papa ; Victor Hugo C. de Albuquerque ; Alexandre Xavier Falcão ; João Manuel Ribeiro da Silva Tavares
• Data: 2010
• Identificador Persistente: http://hdl.handle.net/10216/43303
• Origem: Repositório Aberto da Universidade do Porto
• Assunto(s): Ciências tecnológicas; Tecnologia; Tecnologia de computadores; Processamento de imagem
• Tipo de Documento: Parte ou capítulo de livro
• Idioma: Inglês

Descrição

In this work we propose a novel automatic cast iron segmentation approach based on the Optimum-Path Forest classifier (OPF). Microscopic images from nodular, gray and malleable cast irons are segmented using OPF, and Support Vector Machines (SVM) with Radial Basis Function and SVM without kernel mapping. Results show accurate and fast segmented images, in which OPF outperformed SVMs. Our work is the first into applying OPF for automatic cast iron segmentation.