Classification of the Surface Technological Defects in Rolled Metal Products with the Help of a Deep Neural Network

We develop and study an automated method for the detection and classification of three types of technological defects in rolled metal products. The method is based on the ResNet50 neural network classifier, which makes it possible to recognize three classes of defects in the images of flat surfaces...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Materials science (New York, N.Y.) N.Y.), 2021-05, Vol.56 (6), p.779-788
Hauptverfasser:	Konovalenko, I. V., Maruschak, P. O.
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Characterization and Evaluation of Materials Chemistry and Materials Science Classification Classifiers Defects Flat surfaces Materials Science Metal products Neural networks Nondestructive testing Solid Mechanics Structural Materials
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!