In image classification, objects are assigned to one or more categories based on previously defined properties. The objective is to get a decision about the category of the individual image. This technology is used, for example, for inspection tasks in quality control.
Deep-learning-based image classification with MVTec software allows to easily assign images to trained classes without the need of specially labeled data – a simple grouping of the images after data folders is sufficient. Thus, the labeling and developing effort is low, what enables particularly short set-up times. Moreover, applying the classifier to new data is especially fast. Additionally, the error rates compared to manually handled inspection tasks are significantly low.
Technology available in HALCON and MERLIC.