Skip to main content

Halcon version 21.05

MVTec Software GmbH (, a leading international software provider for machine vision, will publish a new release of its HALCON standard machine vision software (version 21.05) on May 21, 2021. The new version implements new features in the areas of deep learning and matching as well as improvements to the subpixel bar code reader, Deep OCR, and the integrated development environment HDevelop. HALCON 21.05 Progress gives users the benefit of even more robust machine vision processes and improved usability.

A major highlight in the new HALCON 21.05 version is the Generic Shape Matching feature, which makes MVTec's industry-proven shape matching technologies even more user-friendly and future proof. Users can now implement their solutions much faster and more easily, thanks to a significant reduction in the number of operators required. Moreover, thanks to the unification of HALCON’s different shape matching methods into a single set of operators, users can now integrate new shape-matching-related features more easily. The HALCON Deep Learning Framework is another new feature that enables experienced users to create their own model within the software. As a result, experts can now implement even the most demanding and complex applications in HALCON directly, without being dependent on pretrained networks or frameworks from third-party suppliers. HALCON 21.05 also supports the NVIDIA® TensorRT™ inference engine, which can significantly improve the inference performance of applications. In addition to the speedup, users also benefit from significantly lower memory consumption, giving them greater flexibility in their choice of hardware.

Continuous improvement for better performance and greater user-friendliness

In addition to the new functions, HALCON 21.05 also improves upon recently released features. For example, the integrated subpixel bar code reader has been optimized for low-resolution codes. Thanks to these improvements, the decoding rate for such codes can increase by up to 50 percent. The Deep OCR feature has also been further expanded: The holistic deep-learning-based approach to OCR now offers much better performances and even greater usability. It handles large images more robustly and words of different lengths can be detected without parameter tuning. Customers also benefit from improved overall stability as well as a greater range of possible applications, thanks to additional character support.

Finally, the MVTec experts have also made the integrated development environment HDevelop even more user-friendly. The new window docking feature has been optimized, so that users have more options for controlling where floating windows open. In addition, a new docking feature known as "Auto-hide" allows widgets that are not currently needed to be quickly minimized to the sidebar and redisplayed as needed. Finally, graphics windows can now be grouped and organized much more conveniently in HDevelop.

Optimized software, thanks to user feedback

"With HALCON 21.05 we continue to follow our proven strategy of quickly converting valuable feedback from our users into powerful new features and improvements in our product. Thanks to the short release cycle of the HALCON Progress edition, our customers are always up to date and able to benefit from MVTec’s constant innovation," explains Mario Bohnacker, Technical Product Manager HALCON at MVTec Software GmbH.


Read more about:


Media Partners