Newest features of HALCON 25.11

Watch the HALCON 25.11 webinar

You can watch the recorded webinar about the new features in HALCON 25.11 on-demand. 

Register now

What's changing?

Continual Learning – Classification

HALCON 25.11 introduces Continual Learning – Classification, a new technology that makes training and maintaining classification models faster and more flexible. Users can create models with only few images per class and adapt them at any time – for example, to refine existing classes or add new ones.

Unlike conventional deep learning, this approach prevents catastrophic forgetting and keeps maintenance effort low. Based on MVTec’s pretrained models optimized for industrial scenarios, applications can be updated quickly without full retraining. Because the method requires minimal computing power, updates can even be performed directly on edge devices, eliminating the need for external training hardware while ensuring efficient, long-term operation.

The result is a flexible solution that evolves with changing production conditions and remains suitable for embedded and edge environments such as smart cameras, sensors, and inspection modules.

Score Visualization for Shape Matching

With Score Visualization for Shape Matching in HALCON 25.11, users gain increased transparency when setting up shape matching applications. Instead of only returning an overall score, the feature provides a breakdown of how different model parts contribute to the final result. By configuring color-coded bins, users can immediately see which areas match well and which perform poorly, for example due to shadows or unwanted textures. This visual feedback makes it much easier to refine models, remove problematic parts, and optimize applications – a major usability advantage especially for non-expert users.

The feature can also support advanced scenarios in robotics, helping determine which object in a stack is least covered and should be picked first. 

Optimized Deep OCR models for faster, resource-efficient OCR

With new Deep OCR recognition models in HALCON 25.11, text reading becomes faster and more resource-efficient without compromising accuracy. The models deliver up to 50× faster inference    on embedded devices. All models are pretrained by MVTec on industrial image data, and include the proven alignment preprocessing, which improves  recognition when text varies in position or orientation. Thanks to their optimized architecture, they enable real-time OCR applications on low-power devices   while maintaining high accuracy. This makes the models ideal for demanding inline applications such as serial number inspection, label verification, or lot tracking OCR tasks, across industries from logistics and packaging to pharmaceuticals, consumer goods, and medical technology. 

Built-in SBOMs for easier compliance

With HALCON 25.11, MVTec provides Software Bills of Materials (SBOMs), giving users transparent insight into the software components included in the product. SBOMs are becoming a key requirement under new regulations such as the EU Cyber Resilience Act and are increasingly demanded in process- and safety-critical industries.

By providing SBOMs directly with HALCON, MVTec simplifies compliance and reduces workload for customers. Delivered as machine-readable SPDX JSON files, SBOMs make it easier to perform vulnerability and license analyses, fulfill regulatory obligations, and react quickly to newly discovered risks. The result is less integration effort, lower long-term costs, and greater confidence in meeting both regulatory and customer requirements.

Syntax highlighting for HALCON Script files in HDevelopEVO 25.11 

HDevelopEVO 25.11 introduces redesigned syntax highlighting for HALCON Script files, making code easier to read, navigate, and maintain. Instead of uniform coloring, operators, variables, and comments are now displayed in distinct colors, giving scripts a clear visual structure. This improves orientation in the code, reduces errors, and speeds up debugging and refactoring – resulting in a more efficient workflow and a smoother development experience.

HALCON Script Engine and C++ API in HDevelopEVO

With HDevelopEVO 25.11, MVTec introduces the first preview of the HALCON Script Engine, the successor to the HDevEngine. It provides a runtime environment for executing  HALCON Script  files created in HDevelopEVO. The HALCON Script Engine can initially be integrated into applications via a C++ API. Further interfaces such as .NET and Python are planned for future releases. This bridges the gap between prototyping in HDevelopEVO and productive use in custom solutions.

As a preview version, the HALCON Script Engine already enables embedding HALCON Scripts into applications. While not all language features are supported yet, these will follow in future releases. In the meantime, users can try it out and gain early experience with the new workflow.

Additional features

Also included in this release are several improvements that make working with HDevelopEVO more efficient. A new script converter simplifies the migration of existing HDevelop procedures and example programs into HDevelopEVO, supporting stepwise conversion and reuse of established code. Usability has been enhanced with interactive tools: a real-time histogram integrated into the threshold operator for intuitive parameter adjustment, and a live display of grayscale values on mouse hover for instant pixel-level analysis. Together, these features simplify migration, speed up troubleshooting, and streamline everyday image processing workflows.