Optical surface inspection: A novelty detection approach based on CNN-encoded texture features
- In inspection systems for textured surfaces, a reference texture is typically known before novel examples are inspected. Mostly, the reference is only available in a digital format. As a consequence, there is no dataset of defective examples available that could be used to train a classifier. We propose a texture model approach to novelty detection. The texture model uses features encoded by a convolutional neural network (CNN) trained on natural image data. The CNN activations represent the specific characteristics of the digital reference texture which are learned by a one-class classifier. We evaluate our novelty detector in a digital print inspection scenario. The inspection unit is based on a camera array and a flashing light illumination which allows for inline capturing of multichannel images at a high rate. In order to compare our results to manual inspection, we integrated our inspection unit into an industrial single-pass printing system.
Author: | Michael Grunwald, Matthias Hermann, Fabian Freiberg, Pascal Laube, Matthias O. FranzORCiDGND |
---|---|
DOI: | https://doi.org/10.1117/12.2320657 |
Parent Title (English): | Applications of Digital Image Processing XLI, 19-23 August 2018, San Diego, California (Proceedings of SPIE Optical Engineering & Applications, Vol. 10752) |
Document Type: | Conference Proceeding |
Language: | English |
Year of Publication: | 2018 |
Release Date: | 2019/01/08 |
Page Number: | 13 |
Institutes: | Institut für Optische Systeme - IOS |
Open Access?: | Nein |