A novel method for fast arbitrary-oriented scene text detection

作者：Ruan Shaohui; Lu Junguo; Xie Fengming; Jin Zhongxiao^*

来源：30th Chinese Control and Decision Conference, CCDC 2018, 2018-06-09 To 2018-06-11.

DOI：10.1109/CCDC.2018.8407393

In this paper, we propose a novel method for fast arbitrary-oriented text detection in scene images. Our proposed method is simple and effective which can predict word-level bounding boxes via a single fully convolutional network. Our method extracts features from the input images by residual network and apply multi-level fusion over the extracted features. It has two outputs, pixel-wise classification between text and non-text and word-level bounding boxes. Our method achieves an F-measure of 83.46% and 56.39% on ICDAR2015 Incidental Scene Text benchmark and COCO-Text dataset respectively, outperforming the previous methods by a large margin. Also, it can run at over 11 FPS on 704 ×1280 images, which is much faster than the previous works.

• 出版日期2018
• 单位上海交通大学