Wouldn’t it be wonderful if Optical Character Recognition (OCR) software could be developed to read handwriting as well as printed text? University College London is part of a consortium aiming to do just that. The aim of the tranScriptorium project is to develop innovative, efficient and cost-effective solutions for the indexing, search and full transcription of historical handwritten document images, using modern, holistic Handwritten Text Recognition (HTR) technology.You can find out more about the project on its website.
To see the magic in action, take a look at some of the examples on the website (click on this link and then on a picture to start). The examples are in constant development as the computer code behind the process is being uploaded and tweaked, so it’s worth revisiting the site to keep an eye on what’s going on.