How Salient is Scene Text?

Asif Shahab, Faisal Shafait, Andreas Dengel, Seiichi Uchida
IAPR International Workshop on Document Analysis Systems, Gold Coast, Queensland, Australia, IEEE, 3/2012


Computational models of visual attention use image features to identify salient locations in an image that are likely to attract human attention. Attention models have been quite effectively used for various object detection tasks. However, their use for scene text detection is under-investigated. As a general observation, scene text often conveys important information and is usually prominent or salient in the scene itself. In this paper, we evaluate four state-of-the-art attention models for their response to scene text. Initial results indicate that saliency maps produced by these attention models can be used for aiding scene text detection algorithms by suppressing non-text regions.




@inproceedings{ SHAH2012,
	Title = {How Salient is Scene Text?},
	Author = {Asif Shahab and Faisal Shafait and Andreas Dengel and Seiichi Uchida},
	BookTitle = {IAPR International Workshop on Document Analysis Systems},
	Month = {3},
	Year = {2012},
	Publisher = {IEEE}

Last modified:: 30.08.2016