Baseline detection is a simplified text-line extraction that typically serves as pre-processing for Automated Text Recognition. The cBAD competition benchmarks state-of-the-art baseline detection algorithms on archival documents.
It is the successor of cBAD 2017 with a larger dataset that contains more diverse document pages. The winning method of cBAD 2017 was evaluated on the newly introduced dataset and serves as baseline for the participating methods.
This competition shows that the performance of automated baseline detection increased substantially since 2017.