Robust Anomaly Map Assisted Multiple Defect Detection with Supervised Classification Techniques
This work addresses defect detection in manufacturing for Industry 4.0 applications, presenting an incremental improvement by integrating unsupervised anomaly maps into supervised classification.
The paper tackles the problem of detecting multiple defects in manufacturing by using anomaly maps from unsupervised methods to enhance supervised classification models, achieving the best performance when both the image and its anomaly map are used as input, with consistent results across binary and multiclass tasks and unaffected by class balancing.
Industry 4.0 aims to optimize the manufacturing environment by leveraging new technological advances, such as new sensing capabilities and artificial intelligence. The DRAEM technique has shown state-of-the-art performance for unsupervised classification. The ability to create anomaly maps highlighting areas where defects probably lie can be leveraged to provide cues to supervised classification models and enhance their performance. Our research shows that the best performance is achieved when training a defect detection model by providing an image and the corresponding anomaly map as input. Furthermore, such a setting provides consistent performance when framing the defect detection as a binary or multiclass classification problem and is not affected by class balancing policies. We performed the experiments on three datasets with real-world data provided by Philips Consumer Lifestyle BV.