TY - GEN
T1 - Steel defect classification with Max-Pooling Convolutional Neural Networks
AU - Masci, Jonathan
AU - Meier, Ueli
AU - Ciresan, Dan
AU - Schmidhuber, Jürgen
AU - Fricout, Gabriel
N1 - Generated from Scopus record by KAUST IRTS on 2022-09-14
PY - 2012/8/22
Y1 - 2012/8/22
N2 - We present a Max-Pooling Convolutional Neural Network approach for supervised steel defect classification. On a classification task with 7 defects, collected from a real production line, an error rate of 7% is obtained. Compared to SVM classifiers trained on commonly used feature descriptors our best net performs at least two times better. Not only we do obtain much better results, but the proposed method also works directly on raw pixel intensities of detected and segmented steel defects, avoiding further time consuming and hard to optimize ad-hoc preprocessing. © 2012 IEEE.
AB - We present a Max-Pooling Convolutional Neural Network approach for supervised steel defect classification. On a classification task with 7 defects, collected from a real production line, an error rate of 7% is obtained. Compared to SVM classifiers trained on commonly used feature descriptors our best net performs at least two times better. Not only we do obtain much better results, but the proposed method also works directly on raw pixel intensities of detected and segmented steel defects, avoiding further time consuming and hard to optimize ad-hoc preprocessing. © 2012 IEEE.
UR - http://ieeexplore.ieee.org/document/6252468/
UR - http://www.scopus.com/inward/record.url?scp=84865073494&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2012.6252468
DO - 10.1109/IJCNN.2012.6252468
M3 - Conference contribution
SN - 9781467314909
BT - Proceedings of the International Joint Conference on Neural Networks
ER -