OCR (Optical Character Recognition)
Technology that extracts text from scanned documents or images.
Glossary Hub
Explore all AI and translation terms beginning with O.
Technology that extracts text from scanned documents or images.
Words or tokens that do not appear in a model’s training vocabulary and therefore cannot be directly recognised or translated by the system.
An AI model whose architecture, code, or weights are publicly available, allowing researchers and developers to inspect, modify, and deploy it.
A machine learning problem where a model learns the training data too closely and performs poorly on new or unseen inputs.