MOST: A Multi-Oriented Scene Text Detector with Localization Refinement

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021(2021)

引用 71|浏览53
暂无评分
摘要
Over the past few years, the field of scene text detection has progressed rapidly that modern text detectors are able to hunt text in various challenging scenarios. However, they might still fall short when handling text instances of extreme aspect ratios and varying scales. To tackle such difficulties, we propose in this paper a new algorithm for scene text detection, which puts forward a set of strategies to significantly improve the quality of text localization. Specifically, a Text Feature Alignment Module (TFAM) is proposed to dynamically adjust the receptive fields of features based on initial raw detections; a Position-Aware Non-Maximum Suppression (PA-NMS) module is devised to selectively concentrate on reliable raw detections and exclude unreliable ones; besides, we propose an Instance-wise IoU loss for balanced training to deal with text instances of different scales. An extensive ablation study demonstrates the effectiveness and superiority of the proposed strategies. The resulting text detection system, which integrates the proposed strategies with a leading scene text detector EAST, achieves state-of-the-art or competitive performance on various standard benchmarks for text detection while keeping a fast running speed.
更多
查看译文
关键词
text localization,localization refinement,MOST,multioriented scene text detector,PA-NMS module,text feature alignment module,position-aware nonmaximum suppression module,EAST scene text detector,TFAM,instance-wise IoU loss
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要