Textile Anomaly Detection: Evaluation of the State-of-the-Art for Automated Quality Inspection of Carpet
This addresses the problem of automated quality inspection for carpet manufacturers, but it is incremental as it applies existing methods to a new dataset.
The study evaluated state-of-the-art unsupervised models for detecting anomalies in wool carpets, finding that student-teacher network methods achieved the highest accuracy and lowest false detection rates, with an average GPU inference time of 0.16s per image.
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.