Handwriting Analysis Tool (HAT)

Download HAT from UHH RDR

Source Code in GitHub

HAT is a software tool that can be used to analyse handwriting styles. 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. The handwriting styles (scribes) do not need to be known, only discriminative labels must be used for each different style (hand).

In order to download HAT to your computer, please follow these steps:

1. Download the ".zip" file, then extract it to a folder in your local computer.
2. You can run the HAT application by double-clicking the executable file "HAT3p5" in your extracted folder. It might require some administrative privileges depending on your system settings.
3. A command window will start, then the HAT will run in your default internet browser. Although it uses your internet browser, it is an offline application running on your local computer, you do not need internet connection.
4. When you finish using HAT, you can simply close the command window.

Relevant Publications:

• El-Khatib, A. (2023). Editing MSS Leiden Or. 14.545 b–c: The Oldest Qurʾān Fragments in Leiden University Library. Journal of Islamic Manuscripts, 14(2-4), 235-278.
• Blezer, H. (2023). Towards a Definition of Local Orthographies of Bon Manuscripts: A Pilot Study. In A. Helman-Ważny, & C. Ramble (Eds.), Bon and Naxi Manuscripts (Vol. 28, pp. 1-21). (Studies in Manuscript Cultures; Vol. 28). De Gruyter. https://doi.org/10.1515/9783110776478-002.
• Marco Heiles, Johannes Hartliebs Leben und Werk vor 1441. Zugleich ein Beitrag zur Schreiberidentifizierung, in: Zeitschrift für deutsches Alterum und deutsche Literatur 150 (2021), S. 337–379, https://doi.org/10.3813/zfda-2021-0012.
• Mohammed, H., Helman-Wazny, A. . Understanding the Zhangzhung Nyengyu tsakali Collection using Computational Pattern Analysis. In CHAI workshop at 45th German Conference on Artificial Intelligence. 2022.
• Pattern Analysis Software Tools (PAST) for Written Artefacts, Springer Nature,Document Analysis Systems 2022.
• A Comparison of Arabic Handwriting-Style Analysis Using Conventional and Computational Methods, manuscript cultures, 2020.
• Writer Identification for Historical Manuscripts: Analysis and Optimisation of a Classifier as an Easy-to-Use Tool for Scholars from the Humanities, ICFHR, 2018.
• Normalised local näive bayes nearest-neighbour classifier for offline writer identification, Springer Nature, ICDAR, 2017.

License:
HAT is licensed under the Creative Commons Attibution Non Commercial No Derivatives 4.0 International.

Video Tutorial