Laypa: A Novel Framework for Applying Segmentation Networks to Historical Documents

Abstract

We present novel software to process scans of historical documents to extract their layout information. We do this using a ResNet backbone with a feature pyramid head. We extract region information directly into PageXML. For baseline extraction, we use a two stage processing approach. The software has been applied successfully to several projects. The results show the feasibility to automatically label text lines and regions in historical documents.