Researching Early Modern History

Home » Uncategorized » Research blog entry 2 – T.D. Jacobs

Research blog entry 2 – T.D. Jacobs

In the last two weeks, I have conducted research to address a personal weakness with regard to this project: my lack of paleographical talent. I have difficulty in reading my own handwriting, let alone that of anyone else, and the only semi-regular practice I have comes from marking student exams. Clearly, this is an issue that I must address. My first thought was to examine what progress has been made in applying Optical Character Recognition (OCR) software to the problem. This has proven to be somewhat of a dead end. OCR is hindered by variations in letter formation, joins, and image quality. In other words, issues which prevent the automatic isolation of characters. Even software – such as that incorporated into pdf processing programs like WebShare – for translating pdfs of modern print has trouble dealing with images that are distorted in some fashion, or containing any non-textual elements.

Paleographers and historians are instead turning to Handwritten Text Recognition (HTR), which is being designed to recognize textual elements in their entirety. Until recently, accuracy ranged from 20 to 60% error rates when analyzing high quality modern images (Juan, et al., 2010). However, the EU funded tranScriptorium project (2013 to 2016), has now been replaced by the READ (Recognition and Enrichment of Archival Documents) project, incorporating its earlier incarnation’s results. A prototype service platform, Transkribus, is now available to help transcribing handwritten documents, but it relies upon users to help train the program.

For now, however, I have committed to improving my paleographical skills both for the sake of my own research, and as a possible Transkribus user/trainer. There are several online tutorials and guides for ‘secretary hand,’ the style of handwriting and abbreviating I am most likely to come across in my research on mid-seventeenth century English diplomacy. I intend to make use of them. I have also found two published beginner’s guides, A secretary hand ABC book, which was self-published by Alf Ison, and Reading Tudor and Stuart handwriting, by Steve Hobbs.

References:

Hobbs, Steve. Reading Tudor and Stuart handwriting. Chichester: Phillimore & Co Ltd., 2003.

Ison, Alf. A secretary hand ABC book. A. Ison, 1982.

Juan, Alfons, Verónica Romero, Joan Andreu Sánchez, Nicolás Serrano, Alejandro H. Toselli, Enrique Vidal. “Handwritten text recognition for ancient documents.” JMLR: Workshop and Conference Proceedings 11 (2010), 58-65.


Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: