Author: Vincent Christlein

Great achievement by Alexander Mattick, Martin Mayr, Mathias Seuret, Andreas Maier, and Vincent Christlein! Their paper "SmartPatch: Improving Handwritten Word Imitation with Patch Discriminators" received the Best Student Paper Award by the 16th International Conference on Document Analysis an...

We are pleased that the German Research Foundation (DFG) funded our project "Font Group Recognition for Improved OCR". It will be part of Phase III of OCR-D, the German initiative for OCR development. In total, FAU will receive 210.000 Eur for 24 months. This project aims to improve OCR for book...

This competition investigates the performance of historical document classification. The analysis of historical documents is a difficult challenge commonly solved by trained humanists. We provide three different classification tasks, which can be solved individually or jointly: font group, location...

Great achievement by Martin Leipert, Georg Vogeler, Mathias Seuret, Andreas Maier, Vincent Christlein! Their paper "The Notary in the Haystack -- Countering Class Imbalance in Document Processing with CNNs" received the Honorable Mention Best Student Paper Award by the 14th IAPR Workshop on Docume...

This competition investigates the performance of large-scale retrieval of historical document fragments based on writer recognition. The analysis of historic fragments is a difficult challenge commonly solved by trained humanists. To simulate fragments, we extract random text patches from histo...

Today a BR film crew came to the lab and shot a feature for the "Abendschau" about our work on handwriting imitation . We demonstrated in detail how one's handwriting can automatically be synthesized. It was broadcast on BR Fernsehen Monday 20th of July in the "Abendschau" and can now be watched...

You think handwriting is unique and cannot be imitated? We show the contrary in our work. To the best of our knowledge, it is the first paper that synthesizes realistic Western cursive handwriting by mimicking the actual temporal writing process. Our method works nearly fully automatic, e.g. no manual cutting out of characters, and is able to render full lines instead of glyphs/words as in other works.

This dataset was used in the ICDAR2017 Competition on Historical Document Writer Identification (Historical-WI). The dataset used in this competition consists of 3600 handwritten pages originating from 13th to 20th century. It contains manuscripts from 720 different writers where each writer ...

For this year's ICFHR'20, we organize a large-scale image retrieval competition. The task is to find fragments of the same image/from the same writer given a query fragment. To train your system, we created a 100k large training set of fragments. This competition is co-organized by the IRHT/CNRS. F...