MVTec HALCON 26.05: Speed and performance in machine vision 

HALCON 26.05

Precise shape matching and data matrix rectification

MVTec Software GmbH will release the new version of its machine vision software, MVTec HALCON, on May 20, 2026. This release focuses primarily on speed, ensuring that applications across all industrial sectors operate robustly and precisely at exceptional speeds. By improving both deep learning methods and rule-based approaches, HALCON 26.05 addresses demanding automation scenarios where performance is critical.  

 

Summary of key technical changes

The 26.05 release features several innovations that automate complex tasks and significantly boost processing performance:    

Next-generation AI object detection: A new deep-learning architecture delivers up to 5x faster AI inference while maintaining high detection accuracy. This anchor-free approach improves bounding-box localization and performs reliably for small objects and varying object sizes.

Automatic contour optimisation for shape matching: This feature allows users to provide sample images to automatically identify and remove unstable or misleading contours caused by reflections, shadows, or random textures. Focusing the model on robust contours makes matching faster, more stable, and more accurate.  

Data matrix rectification:  HALCON 26.05 can now compensate for geometric distortions when codes are printed on curved, deformed, or non-flat surfaces. This optional rectification step improves decoding reliability for cylindrical components and flexible materials.  

Enhanced data augmentation: New configurable operators integrate directly into deep-learning pipelines, replacing previous procedure-based methods. Developers can programmatically define transformations like geometric changes and colour variations to improve model robustness and reduce the need for large training datasets.  

HDevelopEVO preview:  The latest preview of MVTec’s next-generation integrated development environment (IDE) is included, offering advanced tools and improved workflows for vision developers.  

Applications

Packaging and logistics: Reading Data Matrix codes on curved packaging, cylindrical components, and flexible materials using new rectification capabilities.  
High-speed manufacturing:  Implementing AI-based object detection that performs up to 5x faster for rapid production line monitoring.  
Automated inspection: Using automatic contour optimisation to reliably identify parts despite reflections, shadows, or complex textures.
Deformed surface analysis: Decoding distorted code geometries on non-flat surfaces before processing. 

Upgrade Your Machine Vision Performance

The focus of HALCON 26.05 is to ensure your automation scenarios operate with exceptional speed and robustness. With enhancements ranging from GPU-accelerated deep learning to automated contour cleanup, this version is designed to eliminate bottlenecks in your vision workflow.