OCR Report
dc.contributor.author
Charlton, Ash
dc.date.accessioned
2023-09-05T13:32:49Z
dc.date.available
2023-09-05T13:32:49Z
dc.date.issued
2023-07
dc.description.abstract
Optical Character Recognition (OCR) is the most commonly known method of text extraction from digitised documents used in the cultural heritage sector. It is a process that transforms images of text into a machine-readable format. Traditionally, OCR uses technology to digitally scan text and identify letters individually, therefore recognising one character at a time. Advancements have been made over time that introduce aspects of machine learning into OCR which change this dynamic slightly, which will be explored in more detail later in this report. This report explores OCR software options broadly, in addition to past, current and future proposed OCR processes and workflows that the University of Edinburgh library may introduce.
en
dc.identifier.uri
https://hdl.handle.net/1842/40899
dc.identifier.uri
http://dx.doi.org/10.7488/era/3652
dc.language.iso
en
en
dc.subject
OCR
en
dc.subject
Optical Character Recognition
en
dc.subject
Digitisation
en
dc.subject
Machine Learning
en
dc.subject
Artificial Intelligence
en
dc.subject
Transcription
en
dc.title
OCR Report
en
dc.type
Technical Report
en
Files
Original bundle
1 - 1 of 1
- Name:
- OCR Report Final.pdf
- Size:
- 839.63 KB
- Format:
- Adobe Portable Document Format
- Description:
This item appears in the following Collection(s)