TY  - CONF
AU  - Y. Patel
AU  - Lluis Gomez
AU  - Marçal Rusiñol
AU  - Dimosthenis Karatzas
A2  - ECCVW
PY  - 2016//
TI  - Dynamic Lexicon Generation for Natural Scene Images
BT  - 14th European Conference on Computer Vision Workshops
SP  - 395
EP  - 410
KW  - scene text
KW  - photo OCR
KW  - scene understanding
KW  - lexicon generation
KW  - topic modeling
KW  - CNN
N2  - 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.
L1  - http://refbase.cvc.uab.es/files/PGR2016.pdf
N1  - DAG; 600.084
ID  - Y. Patel2016
ER  -