Publication
How Salient is Scene Text?
Asif Shahab; Faisal Shafait; Andreas Dengel; Seiichi Uchida
In: IAPR International Workshop on Document Analysis Systems. IAPR International Workshop on Document Analysis Systems (DAS-12), 10th, March 27-29, Gold Coast, Queensland, Australia, IEEE, 3/2012.
Abstract
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.