R2 CNN: Rotational Region CNN for Arbitrarily-Oriented Scene Text Detection

Yingying Jiang, Xiangyu Zhu, Xiaobing Wang, Shuli Yang, Wei Li, Hua Wang, Pei Fu, Zhenbo Luo

Abstract: Scene text detection is challenging as the input may have different orientations, sizes, font styles, lighting conditions, perspective distortions and languages. This paper addresses the problem by designing a Rotational Region CNN (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> CNN). R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> CNN includes a Text Region Proposal Network (Text-RPN) to estimate approximate text regions and a multitask refinement network to get the precise inclined box. Our work has the following features. First, we use a novel multi-task regression method to support arbitrarily-oriented scene text detection. Second, we introduce multiple ROIPoolings to address the scene text detection problem for the first time. Third, we use an inclined Non-Maximum Suppression (NMS) to post-process the detection candidates. Experiments show that our method outperforms the state-of-the-art on standard benchmarks: ICDAR 2013, ICDAR 2015, COCO-Text and MSRA-TD500.