Findmypast Announces New Method of Extracting Data from Printed Text Identified by Optical Character Recognition for its Newspaper Collection
- Historical newspaper, the Essex Newsman, now available to search with greater accuracy than ever before
- New search allows researchers to accurately identify names among billions of lines of newsprint adding colour, context and depth to their family history research
- This new method of searching OCR generated text is being tested for the first time and will be developed further in the near future
Leading British and Irish family history website, Findmypast, has today announced the release of a revolutionary new newspapers search.
Findmypast’s Essex Newsman collection is searchable by name and publication year, contains over 1.2 million names and covers a complete run of the publication from 31st October 1881 to 6th November 1943.
The collection has been created by implementing a new method of extracting first and last names from printed text identified by optical character recognition. This allows customers to search for their ancestor’s names across millions of pages of newsprint with greater accuracy and efficiency than ever before. Customers will also start to receive hints against Essex Newsman articles containing names that match those stored on their Findmypast family tree.
While this first iteration of the new search is focused on accurately identifying names, Findmypast plan to extract other details such as locations, events and relationships in 2019. This will further improve the search experience and will dramatically increase the number of hints generated by the collection.
The Essex Newsman has been taken from Findmypast’s wider archive of historical British and Irish newspapers. Today’s release is essentially a trial for this new technology and other titles from the archive will receive similar search upgrades in the future.
Improved access to the millions of articles that make up the collection will enable family historians to discover a wide variety of details relating to the lives of their ancestors. While searching for a notice of a birth, marriage and death, they may be presented with a report relating to any number of important life events, ranging from court cases, convictions and business notices to letters, advertisements for family businesses and even photographs.
Estelle Calfe, Product manager at Findmypast, said: “The stories you find in newspapers really add colour to your family tree and tug at your heart strings. The team have done some great work using machine learning to make the names in newspapers searchable. We plan to continue this work into 2019 and look forward to helping customers uncover yet more fascinating articles about their family.”
PLEASE NOTE: The post content above contains affiliate links. This means I make a percentage of sales via these links. This does not INCREASE the price you pay as a consumer. It simply supplements my income so I can continue providing as much free genealogy content as possible through my “abundance model.”
Disclaimer: All prices and offers are subject to change. Some items may be sold out and have limited inventory. Also check to see if you have automated purchase settings enabled, such as Amazon Buy with 1-Click: it is your responsibility to make sure you are getting the correct price for an item before you check out and finalize the transaction.
Disclosure Statement: I have material connections with various vendors and organizations. To review the material connections I have in the genealogy industry, please see Disclosure Statement.
Content and Images: All product content including images have been used by permission from the vendor.
©2018, copyright Thomas MacEntee. All rights reserved.