The main feature is deep counting, a method based on deep learning that can robustly count large amounts of objects. In addition, improvements for training the deep learning technologies 3D Gripping Point Detection and Deep OCR have been integrated into the new version.

With Halcon 23.05 it is now possible to optimize the underlying deep learning networks, which are already pre-trained on industry-related images, for your own application. This means that more robust recognition rates can be achieved in deep OCR applications and suitable gripping surfaces can be recognized more reliably in applications with 3D Gripping Point Detection technology.