The main feature of the new Halcon version 23.05 by MVTec is Deep Counting, a Deep Learning based method that can count large amounts of objects. In addition, improvements for DL training of 3D Gripping Point Detection as well as Deep OCR have been integrated. Besides, it is now possible to further optimize the respective underlying DL networks for one’s own application. This means that more robust recognition rates can be achieved in Deep OCR applications and matching gripping surfaces can be recognized even more reliably.
Real-time classification of multimodal data
EVK’s Alpha G100 CS real-time image processing system combines the classification of multimodal data, such as hyperspectral, RGB and conductivity data, with advanced functions for sorting applications.