Abstract

Recently, a variety of real-world applications have trig-gered huge demand for techniques that can extract textualinformation from natural scenes. Therefore, scene text de-tection and recognition have become active research topics in computer vision. In this work, we investigate the problem of scene text detection from an alternative perspective and propose a novel algorithm for it. Different fromtraditional methods, which mainly make use of the properties of single characters or strokes, the proposed algorithm exploits the symmetry property of character groups and allows for direct extraction of text lines from natural images. The experiments on the latest ICDAR benchmarks demonstrate that the proposed algorithm achieves state-ofthe-art performance. Moreover, compared to conventional approaches, the proposed algorithm shows stronger adaptability to texts in challenging scenarios.