Abstract
To reduce the number of ship painting inspections in shipyards, there are trials to use visible fluorescent paint with a thickness of paint that can be visually inspected. However, due to the problem that the paint color varies depending on the illuminance and the type of light source, the reliability of the visual inspection is not consistent depending on the inspectors. Therefore, this study proposes a painting inspection method using machine learning technique instead of visual inspection. We propose automation of paint measurements using CNN model to find color variations in captured images according to the illuminance of paint. The actual thickness value of the paint was obtained from the specimen using a contact thickness measuring device. The color model was used to create a deep learning model suitable for the thickness characteristics of the image data. As a result, the proposed CNN model can measure the thickness of the paint within ±20 μm.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have