Browsing by Author "Rebello, Joao M. A."

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Detection and classification of weld discontinuities in radiographic images (Part I: Supervised learning)
    (AMER SOC NONDESTRUCTIVE TEST, 2007) de Padua, Germano X.; da Silva, Romeu R.; Mery, Domingo; Siqueira, Marcio H. S.; Rebello, Joao M. A.; Caloba, Luiz P.
    Radiographic testing of weld joints is of great importance for verifying and maintaining weld quality. This work presents a new technique for the development Of an automatic or semiautomatic system for radiographic weld analysis. This technique uses gray level profiles transversal to weld beads in radiographic patterns. These profiles were processed to aid in the setup of nonlinear pattern classifiers developed by neural networks with algorithms by backpropagation of error. The classification accuracy was estimated via the average correctness of 10 randomly chosen test sets. The results presented a general accuracy of classification correctness of around 95% for the class patterns in the profiles that were used.
  • No Thumbnail Available
    Item
    Detection and classification of weld discontinuities in radiographic images (Part II: Unsupervised learning)
    (2007) de Padua, Germano X.; da Silva, Romeu R.; Mery Quiroz, Domingo Arturo; Rebello, Joao M. A.; Caloba, Luiz P.
  • Thumbnail Image
    Item
    Detection and Classification of Weld Discontinuities in Radiographic Images (Part III: Unsupervised Learning - Phenomenological Analysis)
    (AMER SOC NONDESTRUCTIVE TEST, 2008) de Padua, Germano X.; da Silva, Romeu R.; Mery, Domingo; Rebello, Joao M. A.; Caloba, Luiz P.
    This is the third and final installment of a three-part article on detection and classification of discontinuities appearing in radiographic images of welds. The present installment is the continuation of the section on unsupervised pattern recognition. In this work, the authors present the phenomenological analysis of the pattern profiles of weld discontinuities that resulted from the adaptive resonance theory (ART) networks that were carried out. It is recommended that the previous parts of this article (de Padua et al., 2007a; 2007b) be read before the present installment.