In this paper we address the problem of unconstrained Word Spotting in scene images. We train a Fully Convolutional Network to produce heatmaps of all the character classes. Then, we employ the Text Proposals approach and, via a rectangle classifier, detect the most likely rectangle for each query word based on the character attribute maps. We evaluate the proposed method on ICDAR2015 and show that it is capable of identifying and recognizing query words in natural scene images.

Word spotting in scene images based on character recognition / Bazazian, Dena; Karatzas, Dimosthenis; Bagdanov, Andrew D.. - ELETTRONICO. - 2018-:(2018), pp. 1953-1955. (Intervento presentato al convegno 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 tenutosi a usa nel 2018) [10.1109/CVPRW.2018.00244].

Word spotting in scene images based on character recognition

Bagdanov, Andrew D.
2018

Abstract

In this paper we address the problem of unconstrained Word Spotting in scene images. We train a Fully Convolutional Network to produce heatmaps of all the character classes. Then, we employ the Text Proposals approach and, via a rectangle classifier, detect the most likely rectangle for each query word based on the character attribute maps. We evaluate the proposed method on ICDAR2015 and show that it is capable of identifying and recognizing query words in natural scene images.
2018
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
usa
2018
Bazazian, Dena; Karatzas, Dimosthenis; Bagdanov, Andrew D.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1151115
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 1
social impact