A texture-based method for classifying cracked concrete surfaces from digital images using neural networks

Using a dSLR camera with macro LED light, 11 samples containing light and moderately cracked concrete surfaces were imaged with perpendicular and angled illumination. Textural features from gray level co-occurrence matrix statistics were derived, from which 3-6 salient features were selected. Cross...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Chen, Z., Derakhshani, R. R., Halmen, C., Kevern, J. T.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Artificial neural networks Concrete Feature extraction Lighting Surface cracks Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!