Today, MVTec published the latest HALCON version: HALCON 19.11 is now available for download and brings these advantages for your image processing applications:
With HALCON's anomaly detection, deep-learning-based inspection tasks can be implemented even more efficiently, since only a few images of defect-free objects are required to train the deep learning network. The technology is then able to unerringly and independently localize deviations, i.e., defects of any type, on subsequent images. This means, defects of varying appearance can be detected without any previous knowledge or any labeling efforts in advance.
HALCON 19.11 also brings advantages for the logistics and pharmaceutical industries: Thanks to the new generic box finder, arbitrary boxes of any size can be identified and localized within 3D point clouds. Dimensions of the respective boxes are reliably determined without having to train a model for each box size.
Another innovation is that reading of ECC 200 data codes has been significantly accelerated for multi-core systems. The biggest improvement was achieved for codes that are particularly hard to detect and read. Reading is up to three times faster, which also increases viability on embedded systems.
With HALCON 19.11, it is also now possible to import deep learning models in ONNX (Open Neural Network Exchange) format. This allows developers to use an even broader range of deep learning networks within HALCON.
Furthermore, the MVTec experts have extended HALCON by a new model for line scan cameras with telecentric lenses.
Read more about the new features of HALCON 19.11 here. The technical details can be found in the documentation. Registered customers can download the new version here. If you are not registered yet, you can register here.