A review on modern defect detection models using DCNNs – Deep convolutional neural networks

doi:10.1016/j.jare.2021.03.015

Paper

A review on modern defect detection models using DCNNs – Deep convolutional neural networks

Published Apr 23, 2021 · Andrei-Alexandru Tulbure, A. Tulbure, E. Dulf

Journal of Advanced Research

Q1 SJR score

164

Citations

1

Influential Citations

Full text

Semantic Scholar

Abstract

Abstract removed due to Elsevier request; this does not indicate any issues with the research. Click the full text link above to read the abstract and view the original source.

Literature Review

Highly Cited

Study Snapshot

Key takeawayDeep learning models like Region based CNNs, YOLO, SSD, and cascaded architectures can be easily re-purposed for defect detection, contributing to increased productivity in the manufacturing industry.

PopulationOlder adults (50-71 years)

Sample size24

MethodsObservational

OutcomesBody Mass Index projections

ResultsSocial networks mitigate obesity in older groups.

Sign up to use Study Snapshot

Consensus is limited without an account. Create an account or sign in to get more searches and use the Study Snapshot.

Create an account

Paper

A review on modern defect detection models using DCNNs – Deep convolutional neural networks

Sign up to use Study Snapshot

References

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Pure transformers applied directly to image patches can perform well on image classification tasks, outperforming state-of-the-art convolutional networks while requiring fewer computational resources to train.

Defect Detection in Printed Circuit Boards Using You-Only-Look-Once Convolutional Neural Networks

The proposed YOLO/CNN model accurately detects defects in printed circuit boards with a 98.79% detection accuracy, improving quality inspection efficiency.

Detecting Defects on Solid Wood Panels Based on an Improved SSD Algorithm

The improved SSD algorithm with DenseNet network effectively detects wood defects, such as live knots, dead knots, and checking, with a mean average precision of 96.1%.

PP-YOLO: An Effective and Efficient Implementation of Object Detector

PP-YOLO, a new object detector based on YOLOv3, achieves a better balance between effectiveness (45.2% mAP) and efficiency (72.9 FPS) than existing state-of-the-art detectors like EfficientDet and YOLOv4.

Semi-Supervised Recognition under a Noisy and Fine-grained Dataset

Our method, combining generic image recognition and fine-grained image recognition, successfully identified similar birds with small differences, winning third place in the Simi-Supervised Recognition Challenge-FGVC7.

Citations