ā˜° Scribal Handwriting

Initial Research

Our initial research consisted of analysis of similar projects on scribal handwriting recognition and their correlation with paleography, to better understand the field in which the application would have been used in. By researching what paleographers' needs are, we found out the majority of them require a tool to find the occurrences of a specific character in multiple documents as shown in the example below.

Capital ā€˜Dā€™ with a flat extender

By analysing and studying similar projects we refined the idea for our design and outlined our goals to improve in specific sectors such as irregular-organised-text recognition and performance optimisation to reduce the computational time.

Multi-Language Online Handwriting Recognition[1]. Handwriting online character recognition program. Very fast, usable online since it process data on the cloud, supports multiple languages. Require a lot of power on the server side, cannot recognise non horizontal handwriting.
Handwritten Text Detection[2]. Handwriting language independent character recognition. Works on poor quality images, separate text from the background, identify text in non-linear rows. Accuracy is not ideal.

Team 33 - Francesco Benintende / Kamil Zajac / Andrei Maxim