STEMMER IMAGING

The latest version of HALCON includes the introduction of DotCode reading, a 2D code that is used in many high-speed applications where a code needs to be printed and read/verified during production runs.

HALCON 20.11 also includes another new feature called Deep OCR. MVTec developed this holistic deep-learning-based approach for optical character recognition (OCR) to localise and recognise numbers and letters much more robustly – regardless of their orientation, font type, and polarity.

The ability to group characters automatically also allows the identification of whole words. This improves the recognition performance significantly and avoids the misinterpretation of characters with similar appearances.

Edge detection is greatly improved in HALCON 20.11 by harnessing the power of deep learning. The new and unique method for robustly extracting edges is perfect in scenarios where there may be a large number of edges. The deep-learning-based edge extraction function can be trained with only a few images to reliably extract only the desired edges – greatly reducing the programming effort for processes of this type.

Even with low contrast and high noise situations, the pretrained network is able to robustly detect edges, right out of the box. This makes it possible to also extract edges that cannot be identified with conventional edge detection filters.

In addition, “Pruning for Deep Learning” now enables users to subsequently optimize a fully trained deep learning network. They can now control the priority of the parameters speed, storage, and accuracy and thus modify the network precisely according to application-specific requirements.

The latest release demonstrates significant improvements in the 3D environment as well. Edge-supported, surface-based 3D matching is now significantly faster for 3D scenes with many objects and edges.

Usability has also been improved by removing the need to set a viewpoint. All of this is further enhanced with parameters that are estimated automatically, improving user-friendliness and performance in challenging situations that have low contrast and/or high noise.