Markus Diem is a senior scientist at the Computer Vision Lab, TU Wien, Austria. His research interests are Cultural Heritage Applications and Document Analysis.
ICDAR 2019 Competition on Baseline Detection (cBAD)
The database consists of 3021 manually annotated images collected from seven European archives. It is split into a train, eval, and test. The train and eval sets comprise manually annotated groundtruth baselines as PAGE XMLs . The groundtruth of the test-set will be released after evaluating all submitted methods and the final results being made public. A more detailed introduction can be found in . PAGE XML documentation with reference implementations
 Competition description
The ICDAR 2017 cBAD evaluation scheme is used to measure baseline errors. A detailed description of the evaluation scheme is available here. The evaluation tool which will be used for the competition is available as standalone jar .
Submission ProtocolThe submitted result file has to be a compressed tar file (.tar.gz), containing separate result files (imagename.txt or imagename.xml) for each image in the test set. The folder structure must not be changed! If the test-set contains 3 different images:
You can submit your results multiple times using the following links.
News02-04-2019 Submission is open
18-02-2019 Training data is available
24-01-2019 Competition page is online
01st February 2019
5th May 2019
5th May 2019
20th-25th Sep. 2019