Handwriting Analysis Tool (HAT)

We developed a state-of-the-art learning-free pattern classification method ‘Normalised Local Naïve Bayes Nearest-Neighbour Classifier for Offline Writer Identification’ for the task of automatic handwriting style analysis in images of written artefacts. The main goal of this computational method is to analyse handwritten documents (or manuscripts) in order to measure the similarities between different handwriting styles as demonstrated in [cite]. These similarity measurements can be used, for example, to provide supporting information for the scholars related to the task of scribe identification. Other deep-learning-based approaches have been developed at our centre for this task; however, these methods are currently operational exclusively on our servers.
HAT is a software tool based on the method in [cite], and can be used to analyse handwriting. Multiple and different handwriting styles can be analysed concurrently and sorted according to their similarity to a questioned or unknown style. A similarity score can be calculated for each predefined style to create a relative comparison between them with respect to an unknown style. More details can be found here.
