Handwriting Analysis Tool v2.0
HAT-2 is a software tool that can be used to analyse handwriting styles. Several different handwriting styles (scribal hands) can be analysed concurrently and sorted according to their similarity to a questioned or unknown style (query). A similarity score will be calculated for each predefined style (scribal hand) to create a relative comparison between them with respect to an unknown style.
The handwriting styles (scribes) do not need to be known, only discriminative labels must be used for each different style (hand).
This tool is being developed by Hussein Mohammed, researcher in sub-project Z03 of CSMC at Universität Hamburg and is based on the method presented in the following publication:
- Mohammed, V. Märgner, T. Konidaris, and H. S. Stiehl, “Normalised local näive bayes nearest-neighbour classifier for offline writer identification”, in 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). IEEE, 2017, pp. 1013–1018.
HAT-2 uses the EMGU library, which is free for open source software and for non-commercial usage.
HAT-2 also uses Scale Invariant Feature Transform (SIFT) algorithm which is patented in the U.S., but it requires to buy a license only for commercial software.
EMGU and SIFT license information: http://www.emgu.com/wiki/files/Emgu.CV.Commercial.License.3.0.pdf
The .zip file includes:
- a Windows installer that works for both x32 and x64 platforms (MacOS via a virtual machine or Wine)
- a manual that provides a description of the directory structure, usage procedure and some necessary remarks.
Centre for the Study of Manuscript Cultures
Hussein Adnan Mohammed
Tel: +49 40 42838 - 9397
Fax: +49 40 42838 - 4899