2012 | OriginalPaper | Buchkapitel
Improved Defect Classification of Printed Circuit Board Using SVM
verfasst von : Yuji Iwahori, Deepak Kumar, Takuya Nakagawa, M. K. Bhuyan
Erschienen in: Intelligent Decision Technologies
Verlag: Springer Berlin Heidelberg
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
This paper proposes an analytical approach to make correct recognition between the true defect and the pseudo defect with visual inspection of the electronic board. Some classification approaches have already been proposed for the limited kinds of defects but there have been incorrect recognitions for the defects which is difficult to handle with the visual inspection. This paper proposes the approach to reduce the incorrect recognition for the defects using Support Vector Machine. Real electronic board image data are tested and evaluated with the proposed approach. It is shown that the proposed approach gives efficient classification with some new features with a proper analysis on histogram of image according to the proposed evaluation criteria for the performance.