MVTec is setting new standards in machine vision with HALCON 22.11
MVTec Software will launch the new release (22.11) of its HALCON standard machine vision software on November 22, 2022.
In this release, the Munich-based company continues to rely on the successful combination of classic machine vision methods and deep learning. For example, a new feature combines traditional 3D vision methods and AI technology. This approach is particularly beneficial to logistics companies. In HALCON, MVTec is continuously developing the core technologies from both system environments: traditional and AI-based. The new release features a comprehensive toolbox with by now more than 2,100 operators. Users can thus implement powerful machine vision applications for a wide range of industry sectors, which significantly increases production efficiency in companies.
"With HALCON 22.11, we once more demonstrate that the targeted use of deep learning raises existing machine vision technologies to a new level. The 3D Gripping Point Detection, for example, offers an easy way to efficiently automate a complex application. With the new release, we are once again delivering on our promise to provide users with one of the world's most powerful and technologically advanced machine vision software solutions," remarks Mario Bohnacker, Technical Product Manager HALCON at MVTec.
Different editions available
The new HALCON 22.11 release comes in a Steady edition and a Progress edition. While the latter is available by subscription and has a six-month release cycle, the Steady version is available through a one-off purchase with a release cycle of two years.
The new 3D Gripping Point Detection technology is a highlight of HALCON 22.11. It can be used to robustly detect surfaces on any object that are suitable for gripping with suction. In contrast to classic bin-picking applications, this new technology eliminates the need to train object surfaces. This means that no prior knowledge of the specific objects is required, enabling a much faster and therefore, more cost-efficient implementation of typical bin-picking applications, such as those in the logistics industry.
HALCON 22.11 also introduces a new data type called “memory block”, which can be used to store and transfer binary data in HALCON as well as further process it with other applications. This increases the software's compatibility with machine communication protocols, such as OPC UA or image acquisition interfaces, e.g., for storing camera configuration files. Furthermore, there is the option to encrypt all data that can be serialized, which significantly increases data security. In this way, trained deep learning models can now also be protected. This allows users to protect their expertise and investment that has gone into collecting the data and training the models. Moreover, it can be ensured that only authorized users use the respective model.
Better traceability of deep learning decisions
Another new feature sheds more light on the deep learning black box, thereby increasing the traceability of corresponding processes. The Guided GradCam supplies even more precise clues, in the form of a heat map, as to which regions of the image are relevant for the decision made by the deep learning network. For example, this makes it possible to investigate misclassifications.
HALCON 22.11 now also supports HAILO AI acceleration hardware, which can be used via a plug-in to execute deep learning inferences very quickly. This broadens the range of available hardware and increases flexibility when it comes to using the best components for each application.
Finally, the new release also provides the option of licensing HALCON via a network. This is implemented via floating licenses. Here, developers share a predefined number of licenses using a network connection. Customers benefit from more flexible user allocation, while developers enjoy greater independence and flexibility in terms of their work location. Distributed development teams, or developers working remotely, can thus use HALCON's powerful machine vision algorithms even more effectively. In addition, working in virtual environments without a permanent physical host ID is possible.