RefineText: Refining Multi-oriented Scene Text Detection with a Feature Refinement Module
Pengyuan Xie, Jing Xiao, Yang Cao, Jia Hu Zhu, Asad Khan · 2019
Scene text detection is one of the most challenging tasks in many computer vision applications due to the large variety of scene text appearance and the complexity of scene context. In this paper, we propose an end-to-end trainable framework RefineText for multi-oriented scene text detection, which has a strong ability to detect different-scale texts and split them precisely. High-resolution semantic features are first generated by our designed Feature Refinement Module, which refines features progressively at multiple levels of abstraction. Then text regions are densely produced on the high-level semantic features and followed by Non-Maximum Suppression(NMS) to get final detection results. Experiments on benchmark datasets including ICDAR 2015, ICDAR 2013 and MSRA TD500 demonstrate that our proposed method has competitive performance and strong robustness.