# Introduction This is a master's thesis project in applied informatics at Brno BUT university. The main paper is published under Brno BUT and is publicly available at [BUT pages](https://www.vut.cz/studenti/zav-prace/detail/161094). The full text as [pdf](https://osf.io/z9txm) and [Overleaf project](https://osf.io/t49e2/) is also available in project files. The work is dedicated to Automated Optical Inspection for PCB defects. ![Open AOI portal.][2] # Abstract The paper contains research part where PCB production process is studied and theory of quality and reliability is built as introduction to optical inspection task. The optical inspection is studied as part of the production process and a brief theoretical and historical background is provided. The culminative sections of this parts are dedicated to reviewing state-of-the-art algorithms for assembly related defects of PCB. The practical part describes the development process of open source inspection framework, built on top of ROS2. The framework is called [**Open AOI**](https://github.com/ChrnyaevEK/open-aoi) and it is licensed under MIT license and is available for any one. The main concept will be described here as well. Framework contains default inspection algorithms developed for studied defect types. Experimental setup was also developed for algorithm implementation and collected dataset is released as part of this paper ([available in OSF files](https://osf.io/hrvy8)). ![High level Open AOI architecture.][1] # Keywords Machine Vision, Automated optical inspection, PCB, Automation, ROS2 # Cite this work *CHERNIAEV, E.Vizuální kontrola osazení DPS. Brno: Vysoké učení technické v Brně, Fakulta strojního inženýrství, 2024. 60 s. Vedoucí prof. Ing. Radomil Matoušek, Ph.D.* [1]: https://files.osf.io/v1/resources/xr2gd/providers/osfstorage/66426a1a419d006043fe9e2f?mode=render [2]: https://files.osf.io/v1/resources/xr2gd/providers/osfstorage/6647b3937250fa00524e7a05?mode=render