{"Page SDG":"SDG09 Industry innovation and infrastructure","Page URL":"https://www.appropedia.org/Synthetic-to-real_Composite_Semantic_Segmentation_in_Additive_Manufacturing","Page affiliations":"Category:FAST, Western","Page authors":"User:J.M.Pearce, Aliaksei L. Petsiuk","Page description":"The application of computer vision and machine learning methods for semantic segmentation of the structural elements of 3D-printed products in the field of additive manufacturing (AM) can improve real-time failure analysis systems and potentially reduce the number of defects by providing additional tools for in situ corrections. This work demonstrates the possibilities of using physics-based rendering for labeled image dataset generation, as well as image-to-image style transfer capabilities to improve the accuracy of real image segmentation for AM systems. Multi-class semantic segmentation experiments were carried out based on the U-Net model and the cycle generative adversarial network. The test results demonstrated the capacity of this method to detect such structural elements of 3D-printed parts as a top (last printed) layer, infill, shell, and support. A basis for further segmentation system enhancement by utilizing image-to-image style transfer and domain adaptation technologies was also considered. The results indicate that using style transfer as a precursor to domain adaptation can improve real 3D printing image segmentation in situations where a model trained on synthetic data is the only tool available. The mean intersection over union (mIoU) scores for synthetic test datasets included 94.90% for the entire 3D-printed part, 73.33% for the top layer, 78.93% for the infill, 55.31% for the shell, and 69.45% for supports.","Page is part of":"Category:FAST Completed","Page keywords":"[[3D printing]], [[additive manufacturing]], g-code segmentation, sim-to-real, semantic segmentation, synthetic data, machine learning, open source software, [[open-source hardware]], [[RepRap]], computer vision, quality assurance, real-time monitoring, anomaly detection; Blender, synthetic images","Page language":"en","Page license":"CC-BY-SA-4.0","Page title":"Synthetic-to-real Composite Semantic Segmentation in Additive Manufacturing","Page title tag":"In-Situ Layer-Wise 3D Printing Anomaly Detection","Page views":"45","Page year":"Monday, 01-Jan-24 00:00:00 UTC","Project authors":"User:J.M.Pearce, Aliaksei L. Petsiuk, H. Singh, H. Dadhwal","Project coordinates":"42.983675, -81.249605555556","Project location":"London, ON","Project status":"Designed, Modelled, Prototyped, Verified","Project type":"3D Printing, AI, computer vision, machine learning","Project was made":"1","Project year":"Monday, 01-Jan-24 00:00:00 UTC","Modification date":"Thursday, 06-Mar-25 13:04:10 UTC"}