Special access to our historical OCR tools for researchers and educators
Get assistance from our historical document specialists for your research projects
Processing multiple documents simultaneously with consistent settings.
A measure of how certain the OCR engine is about its text recognition.
A shared environment for multiple users to work on documents.
Converting text documents into numerical vectors for machine learning.
Matching text to its corresponding position in the original document image.
Connecting related documents across collections.
The chronology of ownership or location of a historical document.
Grouping similar documents together based on content.
Dividing documents into structural elements.
The identification and classification of key elements in text such as names, places, and dates.
A geographical directory of historical places.
AI model that adapts to individual handwriting styles.
International Image Interoperability Framework - a standard for delivering images over the web.
Data that provides information about other data.
Using light beyond the visible spectrum to reveal hidden text.
A technique that examines sequences of n items from a given text.
Standardizing historical name variations to consistent forms.
Optical Character Recognition - technology that converts images of text into machine-readable text.
Improving OCR results through post-processing.
Identifying the specific writing system used in a document.
The process of converting handwritten documents into digital text.
Text Encoding Initiative - a standard for representing texts in digital form.
Identifying instances where text has been reused across documents.
Examining how language and content change over time.
Managing changes to documents over time.
Help us improve our glossary by suggesting new terms or improvements to existing definitions.