Scene text detection has received attention for years and achieved an impressive performance across various benchmarks. In this work, we propose an efficient and accurate approach to detect multioriented text in scene images. The proposed feature fusion mechanism allows us to use a shallower network to reduce the computational complexity. A self-attention mechanism is adopted to suppress false positive detections. Experiments on public benchmarks including ICDAR 2013, ICDAR 2015 and MSRA-TD500 show that our proposed approach can achieve better or comparable performances with fewer parameters and less computational cost.
@article{arxiv.2002.03741,
title = {Efficient Scene Text Detection with Textual Attention Tower},
author = {Liang Zhang and Yufei Liu and Hang Xiao and Lu Yang and Guangming Zhu and Syed Afaq Shah and Mohammed Bennamoun and Peiyi Shen},
journal= {arXiv preprint arXiv:2002.03741},
year = {2020}
}