%0 Conference Proceedings
%T Dynamic Lexicon Generation for Natural Scene Images
%A Y. Patel
%A Lluis Gomez
%A Marçal Rusiñol
%A Dimosthenis Karatzas
%B 14th European Conference on Computer Vision Workshops
%D 2016
%F Y. Patel2016
%O DAG; 600.084
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2825), last updated on Fri, 26 Feb 2021 14:23:28 +0100
%X Many scene text understanding methods approach the endtoend recognition problem from a word-spotting perspective and take huge benet from using small per-image lexicons. Such customized lexicons are normally assumed as given and their source is rarely discussed.In this paper we propose a method that generates contextualized lexiconsfor scene images using only visual information. For this, we exploitthe correlation between visual and textual information in a dataset consistingof images and textual content associated with them. Using the topic modeling framework to discover a set of latent topics in such a dataset allows us to re-rank a xed dictionary in a way that prioritizes the words that are more likely to appear in a given image. Moreover, we train a CNN that is able to reproduce those word rankings but using only the image raw pixels as input. We demonstrate that the quality of the automatically obtained custom lexicons is superior to a generic frequency-based baseline.
%K scene text
%K photo OCR
%K scene understanding
%K lexicon generation
%K topic modeling
%K CNN
%U http://refbase.cvc.uab.es/files/PGR2016.pdf
%P 395-410