OG-HFYOLO :Orientation gradient guidance and heterogeneous feature fusion for deformation table cell instance segmentation
This work addresses table structure recognition for document analysis, specifically targeting deformed tables where geometric deformation weakens content-structure correlation, which is an incremental improvement in a domain-specific area.
The paper tackles the problem of table structure recognition in deformed tables by proposing OG-HFYOLO, a model that achieves excellent segmentation accuracy on all mainstream instance segmentation models, and introduces a new dataset called Deformation Wired Table (DWTAL) to address the lack of data for fine-grained deformation table cell spatial coordinate localization.
Table structure recognition is a key task in document analysis. However, the geometric deformation in deformed tables causes a weak correlation between content information and structure, resulting in downstream tasks not being able to obtain accurate content information. To obtain fine-grained spatial coordinates of cells, we propose the OG-HFYOLO model, which enhances the edge response by Gradient Orientation-aware Extractor, combines a Heterogeneous Kernel Cross Fusion module and a scale-aware loss function to adapt to multi-scale objective features, and introduces mask-driven non-maximal suppression in the post-processing, which replaces the traditional bounding box suppression mechanism. Furthermore, we also propose a data generator, filling the gap in the dataset for fine-grained deformation table cell spatial coordinate localization, and derive a large-scale dataset named Deformation Wired Table (DWTAL). Experiments show that our proposed model demonstrates excellent segmentation accuracy on all mainstream instance segmentation models. The dataset and the source code are open source: https://github.com/justliulong/OGHFYOLO.