Image classification
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.
Example images
Continual Learning – Classification
HALCON 25.11 introduces Continual Learning – Classification, a new technology that makes training and maintaining classification models faster and more flexible. Users can create models with only few images per class and adapt them at any time – for example, to refine existing classes or add new ones.
Unlike conventional deep learning, this approach prevents catastrophic forgetting and keeps maintenance effort low. Based on MVTec’s pretrained models optimized for industrial scenarios, applications can be updated quickly without full retraining. Because the method requires minimal computing power, updates can even be performed directly on edge devices, eliminating the need for external training hardware while ensuring efficient, long-term operation.
The result is a flexible solution that evolves with changing production conditions and remains suitable for embedded and edge environments such as smart cameras, sensors, and inspection modules.
Tutorial to learn how to use "Classify Image"-Tool in MERLIC
