GDB: Gated Convolutions-based Document Binarization

Zongyuan Yang

doi:10.1016/j.patcog.2023.109989

2024-02-01

Zongyuan Yang

Baolin Liu

熊

熊永平 (Yongping Xiong) *

Guibin Wu

DOI：10.1016/j.patcog.2023.109989

原文链接

查看原文

摘要

En 中文

Document binarization is a crucial pre-processing step for various document analysis tasks. However, existing methods fail to accurately capture stroke edges, primarily due to the inherent limitations of vanilla convolutions and the absence of adequate boundary-related supervision during stroke edge extraction. In this paper, we formulate text extraction as the learning of gating values and propose an end-to-end network architecture based on gated convolutions, named GDB, to address the problem of imprecise stroke edge extraction. The gated convolutions enable the selective extraction of stroke feature with different attention. Our proposed framework comprises two stages. Firstly, a coarse sub-network with an extra edge branch is trained to enhance the precision of feature maps by incorporating a priori mask and edge information. Secondly, a refinement sub-network is cascaded to enhance the output of the first stage using gated convolutions based on the sharp edges. To effectively incorporate global information, GDB also integrates a parallelized multi-scale operation that combines local and global features. We conduct comprehensive experiments on ten Document Image Binarization Contest (DIBCO) datasets from 2009 to 2019 and Document Deblurring Datasets. Experimental results show that our proposed methods outperform the state-of-the-art methods across all metrics on average. Extensive ablation studys demonstrate the efficacy of key components. Available codes: https://github.com/Royalvice/GDB.

Keyword:

Document binarization

Gated convolutions

Generative adversarial networks

Multi-scale fusion

Multi-branch learning