Real-time Lexicon-free Scene Text Retrieval
Mafla Delgado, Andres Patricio (Centre de Visió per Computador)
Pérez Tito, Rubèn (Centre de Visió per Computador)
Sounak, Dey (Centre de Visió per Computador)
Gomez Bigorda, Lluis (Centre de Visió per Computador)
Rossinyol, Marçal (Centre de Visió per Computador)
Valveny Llobet, Ernest (Centre de Visió per Computador)
Karatzas, Dimosthenis (Centre de Visió per Computador)

Date:	2021
Abstract:	In this work, we address the task of scene text retrieval: given a text query, the system returns all im- ages 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.
Grants:	Agencia Estatal de Investigación TIN2017-89779-P Generalitat de Catalunya 2019/FI_B01233 European Commission 712949
Note:	Altres ajuts: European Social Fund 2014-2020 (CCI: 2014ES05SFOP007); CERCA Programme / Generalitat de Catalunya; UAB Ph.D. scholarship No B18P0070
Rights:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.
Language:	Anglès
Document:	Article ; recerca ; Versió acceptada per publicar
Subject:	Convolutional neural networks ; Image retrieval ; PHOC ; Region proposal networks ; Scene text detection ; Scene text recognition ; Word spotting
Published in:	Pattern Recognition, Vol. 110 (February 2021) , art. 107656, ISSN 0031-3203

DOI: 10.1016/j.patcog.2020.107656

Postprint 31 p, 5.0 MB

The record appears in these collections:
Articles > Research articles
Articles > Published articles