# A Study on Deep CNN Structures for Defect Detection From Laser Ultrasonic Visualization Testing Images

arXiv: https://arxiv.org/abs/2305.18327 · HTML: https://mlsanity.com/paper/2305.18327/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 42 references that are in the map.
- First posted on arXiv 23 May 2023.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [The Effects of Regularization and Data Augmentation are Class Dependent](https://mlsanity.com/paper/2204.03632/) (2022)
- [Frank-Wolfe algorithm for learning SVM-type multi-category classifiers](https://mlsanity.com/paper/2008.08894/) (2020)
- [Adaptive Signal Variances: CNN Initialization Through Modern Architectures](https://mlsanity.com/paper/2008.06885/) (2020)

## Built on by (most cited first, 1 of 1)

- [A Study on Unsupervised Anomaly Detection and Defect Localization using Generative Model in Ultrasonic Non-Destructive Testing](https://mlsanity.com/paper/2405.16580/) (2024)

## Abstract (arXiv)

The importance of ultrasonic nondestructive testing has been increasing in recent years, and there are high expectations for the potential of laser ultrasonic visualization testing, which combines laser ultrasonic testing with scattered wave visualization technology. Even if scattered waves are visualized, inspectors still need to carefully inspect the images. To automate this, this paper proposes a deep neural network for automatic defect detection and localization in LUVT images. To explore the structure of a neural network suitable to this task, we compared the LUVT image analysis problem with the generic object detection problem. Numerical experiments using real-world data from a SUS304 flat plate showed that the proposed method is more effective than the general object detection model in terms of prediction performance. We also show that the computational time required for prediction is faster than that of the general object detection model.