Deep learning for automatic vision-based recognition of industrial surface defects: a survey

M Prunella, RM Scardigno, D Buongiorno… - IEEE …, 2023 - ieeexplore.ieee.org
Automatic vision-based inspection systems have played a key role in product quality
assessment for decades through the segmentation, detection, and classification of defects …

SPEED: Semantic prior and extremely efficient dilated convolution network for real-time metal surface defects detection

B Guo, Y Wang, S Zhen, R Yu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Automatic defect detection on the metal surface is a vital task for product inspection in
industrial assembly lines or production processes. Owing to miscellaneous patterns of …

A new foreground-perception cycle-consistent adversarial network for surface defect detection with limited high-noise samples

Y Wang, W Hu, L Wen, L Gao - IEEE Transactions on Industrial …, 2023 - ieeexplore.ieee.org
Surface defect detection (SDD) is critical in the smart manufacturing systems to ensure
product quality. Nevertheless, the defective samples are always insufficient, and there exists …

Generating synthetic training images to detect split defects in stamped components

AR Singh, T Bashford-Rogers, S Hazra… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Detecting rare and costly defects, such as necks and splits in sheet metal stam**, remains
challenging for deep learning models due to low failure rates entailing few available …

A stable diffusion enhanced YOLOV5 model for metal stamped part defect detection based on improved network structure

Y Liang, S Feng, Y Zhang, F Xue, F Shen… - Journal of Manufacturing …, 2024 - Elsevier
Abstract Machine-vision-based defect detection for large metal stam** is a fundamental
requirement for improving product quality and inspection speed. However, the performance …

[HTML][HTML] Deep Learning-Based Defects Detection in Keyhole TIG Welding with Enhanced Vision

X Zhang, S Zhao, M Wang - Materials, 2024 - mdpi.com
Keyhole tungsten inert gas (keyhole TIG) welding is renowned for its advanced efficiency,
necessitating a real-time defect detection method that integrates deep learning and …

Computer vision defect detection on unseen backgrounds for manufacturing inspection

AM Mezher, AE Marble - Expert Systems with Applications, 2024 - Elsevier
Visual defect detection is an important aspect of quality inspection. High performance
manufacturing can benefit from automating defect detection, and deep learning techniques …

Robust unsupervised-learning based crack detection for stamped metal products

P Zhang, H Ryu, Y Miao, S Jo, G Park - Journal of Manufacturing Systems, 2024 - Elsevier
Crack detection plays an important role in the industrial inspection of stamped metal
products. While supervised learning methods are commonly used in the quality assessment …

An Optimized Image Annotation Method Utilizing Integrating Neural Networks Model and Slantlet Transformation

MM Hashim, AA Al-Hilali, HB Qasim… - … on Advances in …, 2023 - ieeexplore.ieee.org
The inconceivable volume of online images produced by websites and personal collections
has made it difficult to retrieve images from vast databases accurately. Practically …

Real-time detection of surface cracking defects for large-sized stamped parts

X Dong, C Zhang, J Wang, Y Chen, D Wang - Computers in Industry, 2024 - Elsevier
This study presents a framework for the real-time detection of surface cracking in large-sized
stamped metal parts. The framework aims to address the challenges of low detection …