What does this research mean for the field?

Deep learning-driven 2D and 3D image analysis techniques enable highly accurate, real-time defect detection in additive manufacturing, though widespread industrial adoption remains hindered by data scarcity, cross-domain generalization failures, and interpretability gaps. Novelty: ClaimNovelty.SYNTHESIS. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This review aims to identify recent advancements in deep learning techniques for quality control in additive manufacturing, focusing on defect detection and surface characterisation.

June 11, 2026Recent Advances in Computer Science and Communications

Deep Learning Driven 2D/3D Image Analysis Techniques for SurfaceCharacterisation and Defect Detection in Additive Manufacturing: AnOverview

View Full Paper

Ask AI

Bookmark

Authors

APAastha PaltaChandigarh University PPPrachi PaltaChandigarh University VKVirinder KumarChandigarh University

Discussion

Member takes

Implication

Systematic review synthesizes advances in image analysis and defect detection, indicating significant improvements across additive manufacturing technologies.

Key Points

This review aims to identify recent advancements in deep learning techniques for quality control in additive manufacturing, focusing on defect detection and surface characterisation.
Systematic review of over 200 peer-reviewed publications from major scientific databases.
Selection focused on empirical additive manufacturing studies with quantitative performance metrics.
Data extracted included imaging modalities, neural architectures, and evaluation protocols.
2D detection models achieved a mean average precision of 97.5% at real-time speeds of 71.9 FPS.
3D models obtained subsurface defect detection accuracies of 98.9% with IoU values over 88.4%.
Multi-modal sensor fusion reached 98.5% defect prediction accuracy without using thermal modalities.

Cite This Study

Palta et al. (2026) studied this question.

synapsesocial.com/papers/6a2a528480c8f91e7f39e8d2 https://doi.org/10.2174/0126662558442163260226071649

View Full Paper

Ask AI

Bookmark

June 11, 2026Recent Advances in Computer Science and Communications

Deep Learning Driven 2D/3D Image Analysis Techniques for SurfaceCharacterisation and Defect Detection in Additive Manufacturing: AnOverview

View Full Paper

Ask AI

Bookmark

Authors

APAastha PaltaChandigarh University PPPrachi PaltaChandigarh University VKVirinder KumarChandigarh University

Discussion

Member takes

Implication

Systematic review synthesizes advances in image analysis and defect detection, indicating significant improvements across additive manufacturing technologies.

Key Points

This review aims to identify recent advancements in deep learning techniques for quality control in additive manufacturing, focusing on defect detection and surface characterisation.
Systematic review of over 200 peer-reviewed publications from major scientific databases.
Selection focused on empirical additive manufacturing studies with quantitative performance metrics.
Data extracted included imaging modalities, neural architectures, and evaluation protocols.
2D detection models achieved a mean average precision of 97.5% at real-time speeds of 71.9 FPS.
3D models obtained subsurface defect detection accuracies of 98.9% with IoU values over 88.4%.
Multi-modal sensor fusion reached 98.5% defect prediction accuracy without using thermal modalities.

Cite This Study

Palta et al. (2026) studied this question.

synapsesocial.com/papers/6a2a528480c8f91e7f39e8d2 https://doi.org/10.2174/0126662558442163260226071649

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark