Word spotting use a query word image to find any instances of that word among document images. The obtained list of words is ranked according to similarity to the query word. Ideally, any false positives should only occur in the end of that list. However, in reality they often occur higher up, which decreases the so called mean average precision. The idea of Consensus Ranking is to create n new ranked lists by re-scoring using the top n occurrences in the original list, and then fusing the scores. This will often increase the mean average precision.
The figure above shows the difference between the original list (a) and the list ranked using consensus ranking (b). Generally a better ranking is created when the top n words are true positives, but it can also handle quite well cases when there happen to be a few a false positives among them.
Another advantage with this approach is that the confidence value is recomputed in the fusion process. This means that some words will have a lower score than the one computed in the original search (the paper also discuss how to use it with Query Expansion). The advantage with the fused score is that it is possible to purge the list by removing those words that fall under a certain threshold.
- Consensus Ranking for Increasing Mean Average Precision in Keyword Spotting.
A. Hast.
VIPERC 2020, Proceedings of 2nd International Workshop on Visual Pattern Extraction and Recognition for Cultural Heritage Understanding. co-located with 16th Italian Research Conference on Digital Libraries (IRCDL 2020) Bari, Italy, January 29, 2020.
pp. 46-57, 2020. pdf
Like this:
Like Loading...
Related
Published by Anders
Anders Hast received a PhD in Computerised Image processing at Uppsala university in 2004. In 2011 he spent one year at IIT, CNR, Pisa in Italy as an ERCIM fellow and after that he received a full time position as associate professor and in 2019 he became professor in image processing, both at Uppsala University. He has been affiliated with UPPMAX super computer centre where he worked as an application expert in Scientific Visualisation and later in the field of digital humanities together with the Centre for digital humanities in Uppsala. His recent research has focused on image processing and computer vision, for applications in microscopy, aerial photography, object recognition and especially hand written text recognition and face recognition.
View all posts by Anders