Effective degrees of freedom for surface finish defect detection and classification
This addresses quality control for automotive manufacturing by improving defect detection, though it appears incremental as it combines existing methods like spline smoothing and k-nearest neighbors in a specific application.
The paper tackles automated detection of small defects on specular car body surfaces in the automotive industry by proposing a statistical learning approach using spline smoothing for feature extraction and a k-nearest neighbor classifier, achieving near-zero misclassification error rates and demonstrating greater efficiency than compared methods in experiments at a Volvo plant.
One of the primary concerns of product quality control in the automotive industry is an automated detection of defects of small sizes on specular car body surfaces. A new statistical learning approach is presented for surface finish defect detection based on spline smoothing method for feature extraction and $k$-nearest neighbour probabilistic classifier. Since the surfaces are specular, structured lightning reflection technique is applied for image acquisition. Reduced rank cubic regression splines are used to smooth the pixel values while the effective degrees of freedom of the obtained smooths serve as components of the feature vector. A key advantage of the approach is that it allows reaching near zero misclassification error rate when applying standard learning classifiers. We also propose probability based performance evaluation metrics as alternatives to the conventional metrics. The usage of those provides the means for uncertainty estimation of the predictive performance of a classifier. Experimental classification results on the images obtained from the pilot system located at Volvo GTO Cab plant in Umeå, Sweden, show that the proposed approach is much more efficient than the compared methods.