Advances in Automated Defect Detection and Quality Control

The field of automated defect detection and quality control is rapidly advancing, with a focus on developing innovative methods and systems that can accurately identify defects and ensure the quality of products. Recent research has explored the use of deep learning models, such as YOLO and U-Net, for defect detection in various industries, including manufacturing, healthcare, and automotive. These models have shown promising results in detecting defects and improving quality control. Additionally, researchers have investigated the use of multi-camera systems, domain adaptation, and feature disentanglement to improve the accuracy and robustness of defect detection systems. Noteworthy papers include: Unsupervised Defect Detection for Surgical Instruments, which proposes a versatile method for detecting defects in surgical instruments, and Multi-View Camera System for Variant-Aware Autonomous Vehicle Inspection and Defect Detection, which presents an end-to-end perception system for variant-aware quality control in real-time. These advancements have the potential to significantly improve the efficiency and accuracy of quality control processes, reducing the risk of defects and improving product safety.

Sources

Unsupervised Defect Detection for Surgical Instruments

B\'ezier Meets Diffusion: Robust Generation Across Domains for Medical Image Segmentation

A Multi-Camera Vision-Based Approach for Fine-Grained Assembly Quality Control

Using Images from a Video Game to Improve the Detection of Truck Axles

YOLO-Based Defect Detection for Metal Sheets

Causally Guided Gaussian Perturbations for Out-Of-Distribution Generalization in Medical Imaging

Multi-View Camera System for Variant-Aware Autonomous Vehicle Inspection and Defect Detection

Multi-Domain Brain Vessel Segmentation Through Feature Disentanglement

Defect Segmentation in OCT scans of ceramic parts for non-destructive inspection using deep learning

Automated Defect Detection for Mass-Produced Electronic Components Based on YOLO Object Detection Models

Built with on top of