Industrial X-ray Image Analysis with Deep Neural Networks Robust to Unexpected Input Data
Open Access
Abstract
X-ray inspection is often an essential part of quality control within quality critical manufacturing industries. Within such industries, X-ray image interpretation is resource intensive and typically conducted by humans. An increased level of automatization would be preferable, and recent advances in artificial intelligence (e.g., deep learning) have been proposed as solutions. However, typically, such solutions are overconfident when subjected to new data far from the training data, so-called out-of-distribution (OOD) data; we claim that safe automatic interpretation of industrial X-ray images, as part of quality control of critical products, requires a robust confidence estimation with respect to OOD data. We explored if such a confidence estimation, an OOD detector, can be achieved by explicit modeling of the training data distribution, and the accepted images. For this, we derived an autoencoder model trained unsupervised on a public dataset with X-ray images of metal fusion welds and synthetic data. We explicitly demonstrate the dangers with a conventional supervised learning-based approach and compare it to the OOD detector. We achieve true positive rates of around at false positive rates of around on samples similar to the training data and correctly detect some example OOD data.
Keywords
Funding Information
- Stiftelsen Åforsk (19-546)
This publication has 41 references indexed in Scilit:
- Statistical detection of defects in radiographic images using an adaptive parametric modelSignal Processing, 2014
- X-ray modeling of realistic synthetic radiographs of thin titanium weldsNDT & E International, 2012
- Concepts for evaluation of image quality in digital radiologyAIP Conference Proceedings, 2012
- A Connection Between Score Matching and Denoising AutoencodersNeural Computation, 2011
- An automatic system of classification of weld defects in radiographic imagesNDT & E International, 2009
- Detection of line weld defects based on multiple thresholds and support vector machineNDT & E International, 2008
- Automatic identification of different types of welding defects in radiographic imagesNDT & E International, 2002
- Statistical detection of defects in radiographic images in nondestructive testingSignal Processing, 2002
- Estimating the Support of a High-Dimensional DistributionNeural Computation, 2001
- Defect detection in X-ray images using fuzzy reasoningImage and Vision Computing, 2001