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

    2022 Male “AI Based Actors Identification with High Intra-Class Variations, 2nd IEEE Conference on Electrical, Computer, Communications and Mechatronics Engineering, Nov 16th, 2022. Wien „Digitaler intelligenter Assistent in Pflegeanwendungen”: Blickpunkt Forschung TU Wien , Oct 10th, Invited Presentation Belgrad “Bee Pollen Recognition and  Quantity Estimation”, EurBee9-9th European Congress of Apidology, Sept 20th, 2022. … 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 https://github.com/hollaus/msbin. 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

Preliminary Schedule

Topic summer term 2023: Document Analysis Lessons take place in Seminarraum FAV 01 A (Seminarraum 183/2) on Tuesday 13:00 – 17:00 c.t. March 14, 2023, 13:00-15:00: Introduction and Oral Presentations Introduction to the course Topic: Planning and holding oral presentations Speaking exercise: students introduce themselves March 14, 2023, 15:00-17:00:  CVs Function assignment Topic assignment Topic: Writing … Continue reading Preliminary Schedule

CVL-Database

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