Title :
A texture-based method for classifying cracked concrete surfaces from digital images using neural networks
Author :
Chen, Z. ; Derakhshani, R.R. ; Halmen, C. ; Kevern, J.T.
Author_Institution :
Dept. of Civil & Mech. Eng., Univ. of Missouri-Kansas City, Kansas City, MO, USA
fDate :
July 31 2011-Aug. 5 2011
Abstract :
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 validation accuracies were as high as 94% using neural network classifiers, indicating the feasibility of rapid, automatic concrete cracking assessment using COTS digital imaging.
Keywords :
concrete; crack detection; image texture; matrix algebra; mechanical engineering computing; neural nets; statistical analysis; COTS digital imaging; angled illumination; cracked concrete surface; dSLR camera; digital image; gray level cooccurrence matrix statistics; macro LED light; neural network; perpendicular illumination; textural feature; texture-based method; Artificial neural networks; Concrete; Feature extraction; Lighting; Surface cracks; Training;
Conference_Titel :
Neural Networks (IJCNN), The 2011 International Joint Conference on
Conference_Location :
San Jose, CA
Print_ISBN :
978-1-4244-9635-8
DOI :
10.1109/IJCNN.2011.6033562