Semi-Supervised Pixel-Level Scene Text Segmentation by Mutually Guided Network
Lists
Only you see this
Abstract
In this paper we present a new data-driven method for pixel-level scene text segmentation from a single natural image. Although scene text detection, i.e. producing a text region mask, has been well studied in the past decade, pixel-level text segmentation is still an open problem due to the lack of massive pixel-level labeled data for supervised training. To tackle this issue, we incorporate text region mask as an auxiliary data into this task, considering acquiring large-scale of labeled text region mask is commonly less expensive and time-consuming. To be specific, we propose a mutually guided network which produces a polygon-level mask in one branch and a pixel-level text mask in the other. The two branches’ outputs serve as guidance for each other and the whole network is trained via a semi-supervised learning strategy. Extensive experiments are conducted to demonstrate the effectiveness of our mutually guided network, and experimental results show our network outperforms the state-of-the-art in pixel-level scene text segmentation. We also demonstrate the mask produced by our network could improve the text recognition performance besides the trivial image editing application.
BibTeX
@article{wang2021semi,
author = {Chuan Wang and Shan Zhao and Li Zhu and Kunming Luo and Yanwen Guo and Jue Wang and Shuaicheng Liu},
title = {{Semi-Supervised Pixel-Level Scene Text Segmentation by Mutually Guided Network}},
journal = {IEEE Trans. Image Process.},
year = {2021},
url = {https://openreview.net/forum?id=cm1U4BtKVOm},
}Loading related content...