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

Abdelrahman G. Abubakr; Igor Jovancevic; Nour Islam Mokhtari; Hamdi Ben Abdallah; Jean-José Orteu

doi:10.1117/12.2589040

16 July 2021 On learning deep domain-invariant features from 2D synthetic images for industrial visual inspection

Abdelrahman G. Abubakr, Igor Jovancevic, Nour Islam Mokhtari, Hamdi Ben Abdallah, Jean-José Orteu

Author Affiliations +

Proceedings Volume 11794, Fifteenth International Conference on Quality Control by Artificial Vision; 1179418 (2021) https://doi.org/10.1117/12.2589040
Event: Fifteenth International Conference on Quality Control by Artificial Vision, 2021, Tokushima, Japan

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.

Citation Download Citation

Abdelrahman G. Abubakr, Igor Jovancevic, Nour Islam Mokhtari, Hamdi Ben Abdallah, and Jean-José Orteu "On learning deep domain-invariant features from 2D synthetic images for industrial visual inspection", Proc. SPIE 11794, Fifteenth International Conference on Quality Control by Artificial Vision, 1179418 (16 July 2021); https://doi.org/10.1117/12.2589040

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Optical inspection

RGB color model

Solid modeling

Cameras

Computer aided design

Convolutional neural networks

Inspection

Show All Keywords

Keywords/Phrases

Search In:

Publication Years