Title :
Steel defect classification with Max-Pooling Convolutional Neural Networks
Author :
Masci, Jonathan ; Meier, Ueli ; Ciresan, Dan ; Schmidhuber, Jürgen ; Fricout, Gabriel
Author_Institution :
IDSIA, USI, Manno-Lugano, Switzerland
Abstract :
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.
Keywords :
automatic optical inspection; image classification; image segmentation; neural nets; production engineering computing; steel; detected steel defects; error rate; maxpooling convolutional neural networks; production line; raw pixel intensities; segmented steel defects; supervised steel defect classification; Error analysis; Feature extraction; Histograms; Neural networks; Standards; Steel; Training;
Conference_Titel :
Neural Networks (IJCNN), The 2012 International Joint Conference on
Conference_Location :
Brisbane, QLD
Print_ISBN :
978-1-4673-1488-6
Electronic_ISBN :
2161-4393
DOI :
10.1109/IJCNN.2012.6252468