Skip to Main content Skip to Navigation
Conference papers

On learning deep domain-invariant features from 2D synthetic images for industrial visual inspection

Abstract : Deep learning resulted in a huge advancement in computer vision. However, deep models require a large amount of manually annotated data, which is not easy to obtain, especially in a context of sensitive industries. Rendering of Computer Aided Design (CAD) models to generate synthetic training data could be an attractive workaround. This paper focuses on using Deep Convolutional Neural Networks (DCNN) for automatic industrial inspection of mechanical assemblies, where training images are limited and hard to collect. The ultimate goal of this work is to obtain a DCNN classification model trained on synthetic renders, and deploy it to verify the presence of target objects in never-seen-before real images collected by RGB cameras. Two approaches are adopted to close the domain gap between synthetic and real images. First, Domain Randomization technique is applied to generate synthetic data for training. Second, a novel approach is proposed to learn better features representations by means of self-supervision: we used an Augmented Auto-Encoder (AAE) and achieved results competitive to our baseline model trained on real images. In addition, this approach outperformed baseline results when the problem was simplified to binary classification for each object individually.
Complete list of metadata
Contributor : Jean-José Orteu Connect in order to contact the contributor
Submitted on : Thursday, July 22, 2021 - 5:19:25 PM
Last modification on : Tuesday, October 19, 2021 - 11:17:38 PM
Long-term archiving on: : Saturday, October 23, 2021 - 7:12:25 PM


Files produced by the author(s)



Abdelrahman G. Abubakr, Igor Jovančević, Nour Islam Mokhtari, Hamdi Ben Abdallah, Jean-José Orteu. On learning deep domain-invariant features from 2D synthetic images for industrial visual inspection. QCAV’2021- 15th International Conference on Quality Control by Artificial Vision, May 2021, Tokushima (online), Japan. 9 p., ⟨10.1117/12.2589040⟩. ⟨hal-03230285⟩



Record views


Files downloads