Rotated Box Is Back: An Accurate Box Proposal Network for Scene Text Detection.

Scene text detection is a challenging task because it must be able to handle text in various fonts and from various perspective views. This makes it difficult to use rectangular bounding boxes to detect text locations accurately. To detect multi-oriented text, rotated bounding box-based methods have been explored as an alternative. However, they are not as accurate for scene text detection as rectangular bounding box-based methods. In this paper, we propose a novel region-proposal network to suggest rotated bounding boxes and an iterative region refinement network for final scene text detection. The proposed region-proposal network predicts rotated box candidates from pixels and anchors, which increases recall by creating more candidates around the text. The proposed refinement network improves the accuracy of scene text detection by correcting the differences in the locations between the ground truth and the prediction. In addition, we reduce the backpropagation time by using a new pooling method called rotated box crop and resize pooling. The proposed method achieved state-of-the-art performance on ICDAR 2017, that is, an f-score of 75.0% and competitive results with f-scores of 86.9% and 92.4% on ICDAR 2015 and ICDAR 2013, respectively. Furthermore, our approach achieves a significant increase in performance over previous methods based on rotated bounding boxes.