Using of Attention for Scene Text Detection

Abstract

<p indent=0mm>In view of the issue that current mainstream segmentation-based text detection methods is difficult to achieve high detection speed due to complex post-processing to ensure detection accuracy, a scene text detection method is proposed which applies pyramid attention network and position attention module. First, it adopts pyramid attention network to perform feature extraction and semantic segmentation. Meanwhile, it adopts position attention module in high-level features, which strengthens the weights of similar objects in the image to enhance the effect of text detection. Finally, it adopts a simple and effective post-processing algorithm to increase detection speed under the premise of high detection accuracy. Experimental results show that in Total-text datasets, using light-weight backbone network, the method has great advantages on detection speed, and while using deeper backbone network, the method achieves the state of the art result and has a 2.0% lead on detection accuracy.