2015 | OriginalPaper | Buchkapitel
Bayesian Networks-Based Defects Classes Discrimination in Weld Radiographic Images
verfasst von : Aicha Baya Goumeidane, Abdessalem Bouzaieni, Nafaa Nacereddine, Salvatore Tabbone
Erschienen in: Computer Analysis of Images and Patterns
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Bayesian (also called Belief) Networks (BN) is a powerful knowledge representation and reasoning mechanism. Based on probability theory involving a graphical structure and random variables, BN is widely used for classification tasks and in this paper, BN is used as a class discrimination tool for a set of weld defects radiographic images using suitable attributes based on invariant geometric descriptors. Tests are performed on a database of few hundred elements where the results are outstanding and very promising, since they outperform those given by powerful SVM classifiers.