Please note, that the classification approach shown here is legacy from HALCON 19.11 on. With HALCON 19.11, classification is done using the same operators and workflow as the deep learning methods object detection and semantic segmentation. Get more information here.
With HALCON 17.12, deep learning can be used to classify objects and defects. In this video, we learn how to prepare our labeled images so they can be used to train a deep learning-based classifier.
We will have a look at how to organize the images so that the labels can be extracted easily by HALCON. Additionally, we will learn how to apply preprocessing so the images can be processed by the pretrained networks provided with HALCON, and why custom application-specific preprocessing can be useful.
You can download the HDevelop example used in this video below.