Combined Metrics for Quality Assessment of 3D Printed Surfaces for Aesthetic Purposes: Towards Higher Accordance with Subjective Evaluations
- 15 June 2020
- book chapter
- Published by Springer Nature
- Vol. 12143, 326-339
Abstract
Objective quality assessment for 3D printing purposes may be considered as one of the most useful applications of machine vision in smart monitoring related to the development of the Industry 4.0 solutions. During recent years several approaches have been proposed, assuming observing the side surfaces, mainly based on the analysis of the regularity of visible patterns, which represent the consecutive printed layers. These methods, based on the use of general purpose image quality assessment (IQA) metrics, Hough transform, entropy and texture analysis, make it possible to classify the printed samples, independently of the filament’s colour, into low and high quality classes, with the use of photos or 3D scans of the side surfaces. The next step of research, investigated in this paper, is the combination of various proposed approaches to develop a combined metric, possibly highly correlated with subjective opinions. Since the correlation of single metrics developed mainly for classification is relatively low, their combination makes it possible to achieve much better results, verified using an original, newly developed database containing 107 captured images and 3D scans of the 3D printed surfaces with various colours and local distortions caused by external factors, together with Mean Opinion Scores (MOS) gathered from independent observers. Obtained results are promising and may be a starting point for further research towards the optimisation of the newly developed metrics for the automatic assessment of the 3D printed surfaces, mainly for aesthetic purposes.Keywords
This publication has 35 references indexed in Scilit:
- Objective 3D Printed Surface Quality Assessment Based on Entropy of Depth MapsEntropy, 2019
- Automated Process Monitoring in 3D Printing Using Supervised Machine LearningProcedia Manufacturing, 2018
- Fault detection and classification in automated assembly machines using machine visionThe International Journal of Advanced Manufacturing Technology, 2016
- Texture Based Quality Assessment of 3D Prints for Different Lighting Conditions2016
- Emissions of Ultrafine Particles and Volatile Organic Compounds from Commercially Available Desktop Three-Dimensional Printers with Multiple FilamentsEnvironmental Science & Technology, 2016
- A Comparative Study of Machine Vision Based Methods for Fault Detection in an Automated Assembly MachineProcedia Manufacturing, 2015
- Optical Properties of 3D Printable Plastics in the THz Regime and their Application for 3D Printed THz OpticsJournal of Infrared, Millimeter, and Terahertz Waves, 2014
- Vision-Based Online Process Control in Manufacturing ApplicationsIEEE Transactions on Automation Science and Engineering, 2008
- Signature analysis and defect detection in layered manufacturing of ceramic sensors and actuatorsMachine Vision and Applications, 2003
- Online defect detection in layered manufacturing using process signature2002