TwinCAT 3 Vision OCR contains functions for optical character recognition (OCR). The functions identify characters in an image and return the recognized character string. The functions are based on pre-trained machine learning models. No additional settings or training are required. A wide range of different sans serif, non-proportional fonts can be recognized. Models with different character ranges are available to adapt the character recognition to the specific application. The recognition rate can be further increased by specifying the expected character classes. Application examples include verification of best-before dates and batch numbers.