HALCON Progress Key Visual shows a person running at high speed

HALCON 19.05

HALCON 19.05 Progress was released in May 2019. Below, you will find an overview of some of the features included in this release. To learn about the features of the most current version, click here.


Below you find an overview over the most prominent features of this release. For a detailed list, please have a look at the release notes.

Deep Learning Inference on Arm Processors

Deep learning inference

With HALCON 19.05, customers can execute the deep learning inference directly on Arm® processors. This allows them to deploy deep learning applications on embedded devices without the need of any further dedicated hardware. All three deep learning technologies image classification, object detection, and semantic segmentation are supported and run on Arm-based embedded devices out of the box.

Enhanced Object Detection

Object detection

HALCON's deep-learning-based object detection localizes trained object classes and identifies them with a surrounding rectangle. HALCON 19.05 now also gives users the option to have these rectangles aligned according to the orientation of the object. This results in a more precise detection, as rectangles now match the shape of the object more closely.

Improved Surface-based Matching

Edge-supported surface-based matching is now more robust against noisy point clouds: Users can control the impact of surface and edge information via multiple min-scores. Additionally, in case that no xyz-images are available, a new parameter now allows switching off 3D edge alignment entirely. This enables users to eliminate the influence of insufficient 3D data on matching results, while keeping the valuable 2D information for surface and 2D edge alignment.

Enhanced Shape-based Matching

With HALCON 19.05, users can now specifically define so-called "clutter" regions when using shape-based matching. These are areas within a search model that should not contain any contours. Adding such clutter information to the search model leads to more robust matching results, for example in the context of repetitive structures.
Arm is a registered trademark of Arm Limited (or its subsidiaries) in the EU and/or elsewhere. All rights reserved.