Document Layout Analysis with Aesthetic-Guided Image Augmentation
This addresses a specific bottleneck in document understanding for non-Manhattan layouts, but appears incremental as it builds on existing DLA methods.
The paper tackles the challenge of document layout analysis for non-Manhattan layouts by proposing an image layer modeling method, resulting in improved performance on fine-grained segmentation with a new dataset FPD and edge embedding network L-E^3Net.
Document layout analysis (DLA) plays an important role in information extraction and document understanding. At present, document layout analysis has reached a milestone achievement, however, document layout analysis of non-Manhattan is still a challenge. In this paper, we propose an image layer modeling method to tackle this challenge. To measure the proposed image layer modeling method, we propose a manually-labeled non-Manhattan layout fine-grained segmentation dataset named FPD. As far as we know, FPD is the first manually-labeled non-Manhattan layout fine-grained segmentation dataset. To effectively extract fine-grained features of documents, we propose an edge embedding network named L-E^3Net. Experimental results prove that our proposed image layer modeling method can better deal with the fine-grained segmented document of the non-Manhattan layout.