DongbaBPN: Dongba Character Detection Based on Boundary GCN
Open Access
- 18 December 2025
- journal article
- Published by Association for Computing Machinery (ACM) in Journal on Computing and Cultural Heritage
- Vol. 18 (4) , 1-22
Abstract
Dongba script is a unique primitive pictographic writing system. Due to its complex layout structure and highly variable glyph shapes, detecting Dongba characters poses a significant challenge. To address this, we have established a high-quality Dongba script dataset, Dongba1800, which comprehensively covers various layout structures and spatial features found in ancient Dongba manuscripts. We also propose a character detection model named DongbaBPN, capable of precisely locating and detecting Dongba characters at the character level in complex pages. Specifically, our method directly models the boundaries of Dongba characters and consists of a feature extraction backbone similar to an FPN, an initial boundary proposal module, and a GCN-based boundary iterative refinement module. The boundary proposal module generates initial Dongba character boundary proposals by extracting feature semantic information, and then, the boundary iterative refinement module progressively refines these proposals until the boundaries can accurately locate and cover individual Dongba characters. Additionally, we conducted comparative experiments with other state-of-the-art text detection models, and our method achieved the best performance in the Dongba character detection task.Keywords
This publication has 32 references indexed in Scilit:
- STEF: a Swin Transformer-Based Enhanced Feature Pyramid Fusion Model for Dongba character detectionHeritage Science, 2024
- Arbitrary Shape Text Detection via Boundary TransformerIEEE Transactions on Multimedia, 2023
- TextField: Learning a Deep Direction Field for Irregular Scene Text DetectionIEEE Transactions on Image Processing, 2019
- TextBoxes++: A Single-Shot Oriented Scene Text DetectorIEEE Transactions on Image Processing, 2018
- Arbitrary-Oriented Scene Text Detection via Rotation ProposalsIEEE Transactions on Multimedia, 2018
- Mask R-CNN2017
- Deep Residual Learning for Image Recognition2016
- Text-Attentional Convolutional Neural Network for Scene Text DetectionIEEE Transactions on Image Processing, 2016
- Shape-based detection of Maya hieroglyphs using weighted bag representationsPattern Recognition, 2015
- Detecting Text Areas and Decorative Elements in Ancient Manuscripts2010