Detekcija napak na površinah z uporabo anotiranih slik in globokim učenjem

Automated surface anomaly detection using machine learn-ing has become an interesting area of research with a very high direct impact to the application domain of visual inspection. Deep learning approaches seem to be very appropriate for enabling to teach inspection systems detecting surface anomalies by showing them a number of exemplar images. In this paper we present and analyze a deep learning architecture for segmentation of surface anomalies upgraded with a simple classification function that differentiates between images of faulty and defect free surfaces. The preliminary results show that the approach is very promising and that the deep learning paradigm is appropriate to be applied in the domain of automated visual inspection.