Single Shot Text Detector with Regional Attention

TL;DR

This paper introduces a single-shot text detection method using regional attention and hierarchical inception modules, achieving state-of-the-art accuracy on the ICDAR 2015 benchmark.

Contribution

It proposes a novel attention mechanism and hierarchical inception module for robust, single-scale, multi-orientation text detection in natural images.

Findings

Achieved 77% F-measure on ICDAR 2015 benchmark

Outperformed recent FCN-based text detectors

Effective at detecting small and multi-scale text

Abstract

We present a novel single-shot text detector that directly outputs word-level bounding boxes in a natural image. We propose an attention mechanism which roughly identifies text regions via an automatically learned attentional map. This substantially suppresses background interference in the convolutional features, which is the key to producing accurate inference of words, particularly at extremely small sizes. This results in a single model that essentially works in a coarse-to-fine manner. It departs from recent FCN- based text detectors which cascade multiple FCN models to achieve an accurate prediction. Furthermore, we develop a hierarchical inception module which efficiently aggregates multi-scale inception features. This enhances local details, and also encodes strong context information, allow- ing the detector to work reliably on multi-scale and multi- orientation text with single-scale images. Our text detector achieves an F-measure of 77% on the ICDAR 2015 bench- mark, advancing the state-of-the-art results in [18, 28]. Demo is available at: http://sstd.whuang.org/.