Search Results for author: Tobias Grüning

Found 9 papers, 4 papers with code

Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes

1 code implementation12 Oct 2021 Christoph Wick, Jochen Zöllner, Tobias Grüning

The CTC confidences are computed on the encoder while the Transformer is only used for character-wise S2S decoding.

Handwritten Text Recognition Language Modelling

End-To-End Measure for Text Recognition

no code implementations26 Aug 2019 Gundram Leifert, Roger Labahn, Tobias Grüning, Svenja Leifert

However, there is no sophisticated evaluation scheme to measure the quality of a combined text line detection and text recognition system.

Information Retrieval Line Detection +1

Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition

1 code implementation18 Mar 2019 Johannes Michael, Roger Labahn, Tobias Grüning, Jochen Zöllner

Encoder-decoder models have become an effective approach for sequence learning tasks like machine translation, image captioning and speech recognition, but have yet to show competitive results for handwritten text recognition.

Handwritten Text Recognition Image Captioning +6

A Two-Stage Method for Text Line Detection in Historical Documents

2 code implementations9 Feb 2018 Tobias Grüning, Gundram Leifert, Tobias Strauß, Johannes Michael, Roger Labahn

For example, for the complex track of the cBAD: ICDAR2017 Competition on Baseline Detection the F-value is increased from 0. 859 to 0. 922.

Clustering Data Augmentation +2

READ-BAD: A New Dataset and Evaluation Scheme for Baseline Detection in Archival Documents

4 code implementations9 May 2017 Tobias Grüning, Roger Labahn, Markus Diem, Florian Kleber, Stefan Fiel

Well established text line segmentation evaluation schemes such as the Detection Rate or Recognition Accuracy demand for binarized data that is annotated on a pixel level.

Binarization Keyword Spotting +1

CITlab ARGUS for historical handwritten documents

no code implementations26 May 2016 Gundram Leifert, Tobias Strauß, Tobias Grüning, Roger Labahn

We describe CITlab's recognition system for the HTRtS competition attached to the 13. International Conference on Document Analysis and Recognition, ICDAR 2015.

General Classification

Regular expressions for decoding of neural network outputs

no code implementations15 Sep 2015 Tobias Strauß, Gundram Leifert, Tobias Grüning, Roger Labahn

This article proposes a convenient tool for decoding the output of neural networks trained by Connectionist Temporal Classification (CTC) for handwritten text recognition.

General Classification Handwritten Text Recognition +2

CITlab ARGUS for historical data tables

no code implementations15 Dec 2014 Gundram Leifert, Tobias Grüning, Tobias Strauß, Roger Labahn, for the University of Rostock - CITlab

We describe CITlab's recognition system for the ANWRESH-2014 competition attached to the 14. International Conference on Frontiers in Handwriting Recognition, ICFHR 2014.

General Classification Handwriting Recognition

CITlab ARGUS for historical handwritten documents

no code implementations12 Dec 2014 Tobias Strauß, Tobias Grüning, Gundram Leifert, Roger Labahn, for the University of Rostock - CITlab

We describe CITlab's recognition system for the HTRtS competition attached to the 14. International Conference on Frontiers in Handwriting Recognition, ICFHR 2014.

General Classification Handwriting Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.