Optical Character Recognition (OCR)

"With the built-in OCR feature in Quartex, we are able to process items for transcription in the normal course of providing the metadata, and those items can go live within an hour of uploading."
Cecilia Williams, Technical Services Manager, Harris County Public Library


Make printed material in your collections full-text searchable using Optical Character Recognition (OCR).

OCR extends search of your printed text assets beyond metadata, helping users of your digitized materials to uncover rich detail such as the names of people, places and events, and deepening exploration and appreciation of your collections.

This in-platform service uses ABBYY OCR technology to generate a plain text transcript that displays alongside your original asset for an optimized user experience.

OCR transcripts can be generated with a single click, or, if you have existing transcripts, these can be imported instead. Additionally, transcripts can be edited in-platform for enhanced accuracy.

Click the link below to access the Quartex demo site where you can explore OCR in action in samples from the American Indian Newspapers collection.



Get in touch to find out more

If you have any queries regarding the Quartex platform please contact us.