Page Layout Analysis System for Unconstrained Historic Documents

TL;DR

This paper introduces an enhanced CNN-based system for extracting detailed layout information from historic documents, including text regions, lines, and orientations, improving transcription readiness.

Contribution

It extends existing CNN models by adding line height, block boundary predictions, and orientation detection, and provides new benchmark datasets for layout analysis.

Findings

System performs well on cBAD dataset

Effective multi-orientation processing

Introduces and benchmarks on new PERO dataset

Abstract

Extraction of text regions and individual text lines from historic documents is necessary for automatic transcription. We propose extending a CNN-based text baseline detection system by adding line height and text block boundary predictions to the model output, allowing the system to extract more comprehensive layout information. We also show that pixel-wise text orientation prediction can be used for processing documents with multiple text orientations. We demonstrate that the proposed method performs well on the cBAD baseline detection dataset. Additionally, we benchmark the method on newly introduced PERO layout dataset which we also make public.