All posts by Fabian Hollaus

Handwritten Text Recognition

Offline Handwritten Text Recognition (HTR) describes the task of transcribing handwritten text into digital texts. Compared to Optical Character Recognition (OCR), HTR is much more challenging and still an open problem.Recently, a transformer based framework named TrOCR was suggested in [1]. Goal The aim of this internship is to fine-tune existing HTR models in [1] … Continue reading Handwritten Text Recognition

Martin Kampel – Presentations

    2021 Wien „MENSCHZENTRIERTE KI-FORSCHUNG: faire Algorithmen”, Wirtschaftsagentur Wien, Austrian Institute of Technology, June 15th, Online Presentation. Wien „Social Tech – Assistierende Technologien erfolgreich pilotieren”, Wirtschaftsagentur Wien, Business Treff, Aug. 31st, Invited Presentation Wien „Pflege, Demenz und Künstliche Intelligenz”, Digitaler Humanismus: digital Health: TU Wien und Wirtschaftsagentur Wien, Business Treff, Oct 20th, Invited Presentation … Continue reading Martin Kampel – Presentations

MSBin – MultiSpectral Document Binarization

This dataset is named MSBin which stands for MultiSpectral Document Binarization. The dataset is dedicated to the (document image) binarization of multispectral images. A description of the dataset is given at The dataset can be downloaded from Zenodo: The dataset is introduced in: Fabian Hollaus, Simon Brenner, Robert Sablatnig: CNN Based Binarization of MultiSpectral … Continue reading MSBin – MultiSpectral Document Binarization


An Off-line Database for Writer Retrieval, Writer Identification and Word Spotting The CVL Database is a public database for writer retrieval, writer identification and word spotting. The database consists of 7 different handwritten texts (1 German and 6 Englisch Texts). In total 310 writers participated in the dataset. 27 of which wrote 7 texts and … Continue reading CVL-Database

ICDAR2013 – Handwritten Digit and Digit String Recognition Competition

Introduction Handwriting recognition is an open research topic in the document analysis community. We provide two new, freely available real world datasets for an established problem. The competition consists of two independent tasks, namely segmented single Arabic digits and Arabic digit strings. Contributions will be accepted for either of the competitions. The dataset of segmented … Continue reading ICDAR2013 – Handwritten Digit and Digit String Recognition Competition