no code implementations • 24 Mar 2020 • Tomas Wilkinson, Carl Nettelblad
In this paper, we propose an approach that utilises transcripts without bounding box annotations to train segmentation-free query-by-string word spotting models, given a partially trained model.
Weakly supervised segmentation Word Spotting In Handwritten Documents
1 code implementation • 6 Dec 2018 • Tomas Wilkinson, Jonas Lindström, Anders Brun
This is commonly referred to as "word spotting".
1 code implementation • ICCV 2017 • Tomas Wilkinson, Jonas Lindström, Anders Brun
One interesting real-life application of our approach is to help historians to find and count specific words in court records that are related to women's sustenance activities and division of labor.