Self-paced learning to improve text row detection in historical documents with missing lables. (arXiv:2201.12216v1 [cs.CV])

Web: http://arxiv.org/abs/2201.12216

An important preliminary step of optical character recognition systems is the
detection of text rows. To address this task in the context of historical data
with missing labels, we propose a self-paced learning algorithm capable of
improving the row detection performance. We conjecture that pages with more
ground-truth bounding boxes are less likely to have missing annotations. Based
on this hypothesis, we sort the training examples in descending order with
respect to the number of ground-truth bounding boxes, and organize …

arxiv cv detection learning text