Metadata enrichment

A hand on a book

Add value to your digital images by extracting information and enhancing the metadata

'The Road Acts are 18th century Acts of Parliament stored at the British Library. Using OCR and artificial intelligence, we could identify and extract key data such as: act title, publisher, publication date and pagination from scanned images and subsequently create good quality catalogue records. This digitisation work has made the Acts much more visible and searchable by Library users.' 
Jennie Grimshaw, Government Documents Collection Manager at the British Library

Process

Contact us to discuss the metadata (eg. title, author, dates and notes) associated with your documents and find out how to improve the discoverability of your digitised files.

Using automated data extraction and enrichment tools, including optical character recognition (OCR) for full-text search, we can apply artificial intelligence to create and enrich the metadata within your digital files.

We can extract key information from images for cataloguing, indexing or file-naming; split images of journals down to article level; apply handwriting recognition; and translate tables in printed matter into usable formats. Outputs are flexible to meet your needs and meet rigorous metadata standards.

Benefits

  • Enables search and discoverability across large data sets and facilitates categorisation.
  • Unlocks information held within your images.
  • Adds value to your archive as enhanced data can be ingested into your existing library.

Speak to one of our experts to discuss your requirements further.