• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Sistema de visÃo computacional para a caracterizaÃÃo da grafita usando microfotografias / System of computational vision for the characterization of the graphite using microphotographies

Victor Hugo Costa de Albuquerque 06 October 2007 (has links)
CoordenaÃÃo de AperfeiÃoamento de Pessoal de NÃvel Superior / A Ãrea de CiÃncia dos Materiais utiliza sistemas de VisÃo Computacional para determinar tamanho e/ou quantidade de grÃos, controle de soldagem, modelamento de elementos de ligas, entre outras. O presente trabalho tem como principal objetivo desenvolver e validar o programa SVRNA (SegmentaÃÃo de Microestruturas por VisÃo Computacional Baseada em Rede Neural Artificial), que, combinado com Rede Neural Artificial, utiliza tÃcnicas de morfologia matemÃtica para realizar a segmentaÃÃo dos constituintes do ferro fundido branco de forma semi-automÃtica e a classificaÃÃo automÃtica da grafita nos ferros fundidos nodular, maleÃvel e cinzento. Os resultados da segmentaÃÃo e quantificaÃÃo destes materiais sÃo comparados entre o SVRNA e um programa comercial bastante utilizado neste domÃnio. A anÃlise comparativa entre estes mÃtodos mostra que o SVRNA apresenta melhores resultados. Conclui-se, portanto, que o sistema proposto pode ser utilizado em aplicaÃÃes na Ãrea da CiÃncia dos Materiais para a segmentaÃÃo e quantificaÃÃo de constituintes em materiais metÃlicos, reduzindo o tempo de anÃlise e obtendo resultados precisos. / CATERIALS Sciences field uses Computational Vision systems to determine size and/or amount of grains, welding control, modeling of alloy elements, among other. The present paper has as main objective to develop and validate the SVRNA system (Microstructure Segmentation for Computational Vision based on Artificial Neural Networks), which, combined with ArtiÂcial Neural Network, uses mathematical morphology technics to accomplish the constituent segmentations from white cast iron of semi-automatic form, and graphite automatic classiÂcation from nodular, malleable and gray cast iron. Segmentation and quantiÂcation results of this materials are compared between SVRNA and a commercial program more used in this domain. Comparative analysis between this methods showed that SVRNA present best results. It has concluded, therefore, which the proposed system can be used in applications in Material Sciences field for microstructure segmentation and quantification in metallic materials, reducing the analyze time, and obtained accurate results.

Page generated in 0.1206 seconds