Textile Anomaly Detection: Evaluation of the State-of-the-Art for Automated Quality Inspection of Carpet
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916337179164672 |
|---|---|
| author | Forsberg, Briony Williams, Dr Henry MacDonald, Prof Bruce Chen, Tracy Hulse, Dr Kirstine |
| author_facet | Forsberg, Briony Williams, Dr Henry MacDonald, Prof Bruce Chen, Tracy Hulse, Dr Kirstine |
| contents | In this study, state-of-the-art unsupervised detection models were evaluated for the purpose of automated anomaly inspection of wool carpets. A custom dataset of four unique types of carpet textures was created to thoroughly test the models and their robustness in detecting subtle anomalies in complex textures. Due to the requirements of an inline inspection system in a manufacturing use case, the metrics of importance in this study were accuracy in detecting anomalous areas, the number of false detections, and the inference times of each model for real-time performance. Of the evaluated models, the student-teacher network based methods were found on average to yield the highest detection accuracy and lowest false detection rates. When trained on a multi-class dataset the models were found to yield comparable if not better results than single-class training. Finally, in terms of detection speed, with exception to the generative model, all other evaluated models were found to have comparable inference times on a GPU, with an average of 0.16s per image. On a CPU, most of these models typically produced results between 1.5 to 2 times the respective GPU inference times. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_18450 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Textile Anomaly Detection: Evaluation of the State-of-the-Art for Automated Quality Inspection of Carpet Forsberg, Briony Williams, Dr Henry MacDonald, Prof Bruce Chen, Tracy Hulse, Dr Kirstine Computer Vision and Pattern Recognition Machine Learning In this study, state-of-the-art unsupervised detection models were evaluated for the purpose of automated anomaly inspection of wool carpets. A custom dataset of four unique types of carpet textures was created to thoroughly test the models and their robustness in detecting subtle anomalies in complex textures. Due to the requirements of an inline inspection system in a manufacturing use case, the metrics of importance in this study were accuracy in detecting anomalous areas, the number of false detections, and the inference times of each model for real-time performance. Of the evaluated models, the student-teacher network based methods were found on average to yield the highest detection accuracy and lowest false detection rates. When trained on a multi-class dataset the models were found to yield comparable if not better results than single-class training. Finally, in terms of detection speed, with exception to the generative model, all other evaluated models were found to have comparable inference times on a GPU, with an average of 0.16s per image. On a CPU, most of these models typically produced results between 1.5 to 2 times the respective GPU inference times. |
| title | Textile Anomaly Detection: Evaluation of the State-of-the-Art for Automated Quality Inspection of Carpet |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2407.18450 |