An application of machine learning and statistics to defect detection

Authors:
R. Cucchiara;P. Mello;M. Piccardi;F. Riguzzi
Affiliations:
Dipartimento di Scienze dell'Ingegneria, Universit\'`a di Modena, Via Campi 213/b, 41100 Modena, Italy. E-mail: rita.cucchiara@unimo.it;D.E.I.S., Universit\'`a di Bologna, V.le Risorgimento 2, 40136 Bologna, Italy. E-mail: pmello@deis.unibo.it;Dipartimento di Ingegneria, Universit\'`a di Ferrara, Via G. Saragat 1, 44100 Ferrara, Italy. E-mail: {mpiccardi, friguzzi}@ing.unife.it;Dipartimento di Ingegneria, Universit\'`a di Ferrara, Via G. Saragat 1, 44100 Ferrara, Italy. E-mail: {mpiccardi, friguzzi}@ing.unife.it
Venue:
Intelligent Data Analysis
Year:
2001

Citing 8
Cited 0

A survey of the Hough transform

Computer Vision, Graphics, and Image Processing
The cascade-correlation learning architecture

Advances in neural information processing systems 2
C4.5: programs for machine learning

C4.5: programs for machine learning
Supervised Learning of Descriptions for Image Recognition Purposes

IEEE Transactions on Pattern Analysis and Machine Intelligence
Approximate statistical tests for comparing supervised classification learning algorithms

Neural Computation
Learning Shape Classes

IEEE Transactions on Pattern Analysis and Machine Intelligence
Goal-Directed Classification Using Linear Machine Decision Trees

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning by a Generation Approach to Appearance-Based Object Recognition

ICPR '96 Proceedings of the 1996 International Conference on Pattern Recognition (ICPR '96) Volume I - Volume 7270

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an application of machine learning and statistics to the problem of distinguishing between defective and non-defective industrial workpieces, where the defect takes the form of a long and thin crack on the surface of the piece. From the images of pieces a number of features are extracted by using the Hough transform and the Correlated Hough transform. Two datasets are considered, one containing only features related to the Hough transform and the other containing also features related to the Correlated Hough transform. On these datasets we have compared six different learning algorithms: an attribute-value learner, C4.5, a backpropagation neural network, NeuralWorks Predict, a k-nearest neighbour algorithm, and three statistical techniques, linear, logistic and quadratic discriminant. The experiments show that C4.5 performs best for both feature sets and gives an average accuracy of 93.3% for the first dataset and 95.9% for the second dataset.