HAM: Hidden Anchor Mechanism for Scene Text Detection

Jie-Bo Hou, Xiaobin Zhu, Chang Liu, Kekai Sheng, Long-Huang Wu, Hongfa Wang, Xu-Cheng Yin

Abstract

Direct regression and anchor are the two mainly effective and prevailing mechanisms in the paradigm of scene text detection. However, the use of direct regression-based methods may be challenging during optimization without the help of anchors as references. Unfortunately, the anchor-based methods always suffer from the careful design of the anchors, degrading the robustness to complex scenes. To address the above-mentioned problems, we propose a novel hidden anchor mechanism (HAM) especially for scene text detection. The predictions of anchors are innovatively regarded as hidden layers, and the weighted sum of the predictions is integrated into a direct regression-based network. Hence, the architecture of our HAM still has the characteristic of simplicity as with direct regression-based methods. Moreover, it is easier to optimize anchors as references with this type of method than with direct regression-based methods. In this way, our network can take advantage of both direct regression and anchor mechanisms. In addition, we decouple three kinds of one-dimensional anchors from three-dimensional anchors, greatly reducing the number of anchors in text bounding box matching without performance degradation. We also propose a post-processing technique for long text detection, named iterative regression box (IRB), which takes a few additional computational costs and can be easily generalized to other methods. Experiments on several public datasets demonstrate that the proposed method achieves state-of-the-art performance. Code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/hjbplayer/HAM</uri> .
BibTeX
@article{hou2020ham,
  author = {Jie-Bo Hou and Xiaobin Zhu and Chang Liu and Kekai Sheng and Long-Huang Wu and Hongfa Wang and Xu-Cheng Yin},
  title = {{HAM: Hidden Anchor Mechanism for Scene Text Detection}},
  journal = {IEEE Trans. Image Process.},
  year = {2020},
  doi = {10.1109/tip.2020.3008863},
}

Loading related content...

Figure