With HALCON 13, a giant leap in performance for shape-based matching, one of HALCON’s core technologies, has been accomplished. For example, speedups of more than 300% can be achieved on machines with AVX2-compatible processors, when searching byte images with a small number of pyramid levels. But not only that, HALCON 13 also offers significant speedups for all related technologies, i.e., shape-based 3D matching, local and perspective deformable matching, and component-based matching.
Texture inspection can be a challenging task because textures often have very different characteristics like scale or brightness. Thus, setting up a texture inspection system is often tricky. HALCON 13 therefore offers an easy-to-use texture inspection, which is configured by simply passing some training images. The algorithm automatically adjusts the necessary parameters based on training images that show flawless texture. The trained texture inspection model can then be used to detect potential texture defects.
3D Matching and 3D Reconstruction
In HALCON 13, surface-based 3D matching has been improved to be more robust when dealing with flat surfaces. This improvement particularly supports applications like picking of boxes. HALCON 13 also offers a new method to reconstruct 3D objects from multiple cameras with high quality. This new method uses the information of all camera views at once leading to more robust results than provided by common stereo reconstruction methods.
Major improvements in identification technologies
With HALCON 13, MVTec offers deep-learning-based OCR for the first time: HALCON now contains a new OCR classifier based on deep learning technology, which can be used via a number of pretrained fonts. With these, it is possible to achieve higher reading rates than with all previous classification methods. Further, the automatic text reader in HALCON 13 is faster and now also supports reading of dot print characters.
HALCON 13 also reads bar codes even if large parts of the code are either defective or not visible at all. Additionally, the QR code reader has been improved and is now much more robust against common challenges like blur or distortion.
Debugging of HDevEngine applications
With HALCON 13, HDevEngine applications can now be debugged directly within HDevelop. HDevEngine allows developers to execute HDevelop code within their C# or C++ application. By attaching HDevelop to this application, the machine vision part can now be debugged using HDevelop. This debugging enables the developer to inspect call stack and variable values while executing procedures step by step, making error tracking a lot easier.
You can even connect HDevelop to an HDevEngine application running on a different computer for remote debugging. For example, debugging a machine on the factory floor can be done directly from the office with this connection. This functionality is also extremely useful for debugging HALCON Embedded devices such as smart cameras.