Error-corrected deep learning approach to handwritten text recognition of Gregg shorthand

Abstract

Shorthand, also known as pen stenography, is a family of writing systems for English and other languages that emerged out of a need for a fast and efficient writing system in a predigital age. Of the many English shorthand systems, Gregg shorthand is the most prevalent (Zhai et al., 2018). While largely made obsolete by general-purpose computers, the cultural and legal value within old shorthand documents means that being able to efficiently scan shorthand documents into modern computer systems holds significant value. This investigation explored the implementation of a model built around a Gated Convolutional Neural network for purposes of handwritten text recognition of Gregg shorthand. An accuracy of 40.04% was achieved after minimal training. The finalized model is freely licensed and made available online for public access.