Search Results for author:
Found 3 papers, 2 papers with code
Bootstrapping Weakly Supervised Segmentation-free Word Spotting through HMM-based Alignment
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
Neural Word Search in Historical Manuscript Collections
This is commonly referred to as "word spotting".
Neural Ctrl-F: Segmentation-free Query-by-String Word Spotting in Handwritten Manuscript Collections
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.
