PT Journal
AU Andres Mafla
   Ruben Tito
   Sounak Dey
   Lluis Gomez
   Marçal Rusiñol
   Ernest Valveny
   Dimosthenis Karatzas
TI Real-time Lexicon-free Scene Text Retrieval
SO Pattern Recognition
JI PR
PY 2021
BP 107656
VL 110
AB In this work, we address the task of scene text retrieval: given a text query, the system returns all images containing the queried text. The proposed model uses a single shot CNN architecture that predicts bounding boxes and builds a compact representation of spotted words. In this way, this problem can be modeled as a nearest neighbor search of the textual representation of a query over the outputs of the CNN collected from the totality of an image database. Our experiments demonstrate that the proposed model outperforms previous state-of-the-art, while offering a significant increase in processing speed and unmatched expressiveness with samples never seen at training time. Several experiments to assess the generalization capability of the model are conducted in a multilingual dataset, as well as an application of real-time text spotting in videos.
ER