What can Text Reader read?

Printed text such as part numbers, batch and date codes and labels – including dot-matrix and laser-etched markings, for which settings are included. It returns the full text plus every word with its confidence and position.

How do we make readings reliable?

Define where the text is and which characters may occur – for example digits only – and set a minimum confidence per word. Your PLC then checks the word count and score before relying on the text.

What image quality does OCR need?

As a rule of thumb, characters at least 20 pixels tall (30 or more for small or noisy print), good contrast, sharp focus, no glare and roughly upright text.

Which languages are supported?

English is included. Further languages are added as Tesseract models without a restart; each module can read in its own language. LSTM, legacy or combined OCR engines are selectable.

Does Text Reader run on ctrlX OS and on a PC?

Yes. On ctrlX OS (ctrlX CORE or ctrlX IPC) it uses the ctrlX Data Layer; on a PC with Windows 11 or Ubuntu 24.04 it uses LumiScan Keryx. Node addresses, types and behaviour are the same on both, so a program written against one works against the other. On a PC, a PLC controls it via OPC UA.

LumiScan Ecosystem: Code Text Recognition

LumiScan Text Reader

Industrial OCR for part numbers, batch and date codes – printed, dot-matrix or laser-etched.

LumiScan Text Reader is industrial OCR (optical character recognition) for machine vision: it reads printed text such as part numbers, batch and date codes and labels from a camera image. You define where the text is and which characters may occur, and it returns the text with a confidence for every word.

Restricting the character set and setting a minimum confidence turn a plausible reading into a reliable one, so your PLC can check the result before relying on it. Settings for dot-matrix and laser-etched markings are included.