Machine learning method for predicting the influence of scanning parameters on random measurement error

Urbas, Uroš (author), Vlah, Daria (author), Vukašinović, Nikola (author)

Measurements of technical objects can be done with contact and non-contact approaches. Contact methods are accurate; but slow. On the other hand, non-contact methods deliver rapid point acquisition and are increasingly being used as their precision mounts. However, multiple scanning parameters, such as incident angle, object colour, and scanning distance influence the measurement error and uncertainty when capturing the geometry of the object. With the aim to create a generalized model, which considers the influence of the aforementioned scanning parameters with satisfactory accuracy, a model for predicting the random measurement error based on machine learning is proposed in this study. Data acquired from measurements with varying scanning distances, incident angles, and surface colours were used to train machine learning models. The tested machine learning methods included linear regression, support vector machine, neural network, k-nearest neighbour, AdaBoost, and random forest. The best performing trained model was the random forest, with a standard deviation of relative differences of 1.46 % for the case of red surfaces, and 5.2 % for the case of an arbitrarily coloured surface, which is comparable to results achieved with model-based methods. The trained models and the data are available online.

• Language: English
• Keywords: scanning parameters, machine learning, random measurement error
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FS - Faculty of Mechanical Engineering
• Publication status: Published
• Publication version: Version of Record
• Year: 2021
• Number of pages: 9 str.
• Numbering: Vol. 32, no. 6
• PID: 20.500.12556/RUL-182520
• UDC: 004.85
• ISSN on article: 0957-0233
• DOI: 10.1088/1361-6501/abd57a
• COBISS.SI-ID: 49131523
• Publication date in RUL: 14.05.2026

Record is a part of a journal

• Title: Measurement science & technology
• Shortened title: Meas. sci. technol.
• Publisher: IOP Publishing
• ISSN: 0957-0233
• COBISS.SI-ID: 6000901

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: parametri skeniranja, strojno učenje, naključna merilna napaka

Projects

• Funder: ARRS - Slovenian Research Agency
• Project number: 51899
• Name: Young researchers