Title: Quantification of the microstructures of hypoeutectic white cast iron using mathematical morphology and an artificial neural network

Authors: Victor Hugo C. De Albuquerque, Joao Manuel R.S. Tavares, Paulo Cesar Cortez

Addresses: Centro de Ciencias Tecnologicas (CCT), Nucleo de Pesquisas Tecnologicas (NPT), Universidade de Fortaleza, Av. Washington Soares, 1321, Edson Queiroz, Sala NPT/CCT, CEP, 60811-905, Fortaleza, Ceara, Brasil. ' Instituto de Engenharia Mecanica e Gestao Industrial (INEGI)/ Departamento de Engenharia Mecanica (DEMec), Faculdade de Engenharia da Universidade do Porto (FEUP), Rua Dr. Roberto Frias, s/n, 4200-465 Porto, Portugal. ' Centro de Tecnologia (CT), Departamento de Engenharia de Teleinformatica (DETI), Universidade Federal do Ceara (UFC), Av. Humberto Monte, s/n, Campus do PICI S/N, Bloco 723, CEP, 60455-970, Fortaleza, Ceara, Brasil

Abstract: This paper describes an automatic system for segmentation and quantification of the microstructures of white cast iron. Mathematical morphology algorithms are used to segment the microstructures in the input images, which are later identified and quantified by an artificial neuronal network (ANN). A new computational system was developed because ordinary software could not segment the microstructures of this cast iron correctly, which is composed of cementite, pearlite and ledeburite. For validation purpose, 30 samples were analysed. The microstructures of the material in analysis were adequately segmented and quantified, which did not happen when we used ordinary commercial software. Therefore, the proposed system offers researchers, engineers, specialists and others, a valuable and competent tool for automatic and efficient microstructural analysis from images.

Keywords: image processing; image analysis; image segmentation; image quantification; microstructure; hypoeutectic white cast iron; mathematical morphology; artificial neural networks; ANNs.

DOI: 10.1504/IJMMP.2010.032501

International Journal of Microstructure and Materials Properties, 2010 Vol.5 No.1, pp.52 - 64

Published online: 04 Apr 2010 *

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