Summary of Textile Anomaly Detection: Evaluation Of the State-of-the-art For Automated Quality Inspection Of Carpet, by Briony Forsberg et al.
Textile Anomaly Detection: Evaluation of the State-of-the-Art for Automated Quality Inspection of Carpet
by Briony Forsberg, Dr Henry Williams, Prof Bruce MacDonald, Tracy Chen, Dr Kirstine Hulse
First submitted to arxiv on: 26 Jul 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A state-of-the-art unsupervised detection approach is evaluated for automated anomaly inspection in wool carpets. A custom dataset of four unique carpet textures is created to test model robustness and accuracy. The primary metrics are detection accuracy, false detections, and inference time for real-time performance. Student-teacher network-based methods exhibit the highest average detection accuracy and lowest false detection rates. Multi-class training yields comparable or better results than single-class training. Inference times on a GPU average 0.16s per image, while CPU times are approximately 1.5 to 2 times slower. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this study, researchers test different computer models for finding problems in wool carpets. They make a special collection of carpet textures and see which model is best at finding the problems. The most important things they look at are how well the model works, how many mistakes it makes, and how long it takes to make its decisions. Some models work better than others when looking at different types of carpets. It also takes longer for these models to make their decisions on a computer compared to a special machine. |
Keywords
» Artificial intelligence » Inference » Unsupervised
