GDB: Gated Convolutions-based Document Binarization

Zongyuan Yang, Baolin Liu, Yongping Xiong, Guibin Wu

Abstract: Highlights•We propose a novel end-to-end document binarization method using gated convolutions.•We solve the problem of imprecise stroke edge extraction by gated convolutions.•We visualize the gating values to explain the effectiveness of gated convolutions.•The network with multi-scale fusion and edge branch is trained on multiple losses.•The proposed method outperforms state-of-the-art methods on DIBCO datasets.