Uncovering the Handwritten Text in the Margins: End-to-end Handwritten Text Detection and Recognition

TL;DR

This paper introduces an end-to-end system for detecting and recognizing handwritten marginalia in historical documents, utilizing data augmentation and transfer learning to address limited training data, and demonstrating effectiveness on library collection data.

Contribution

It presents a novel integrated framework combining detection and recognition for handwritten marginalia, with techniques to mitigate data scarcity, and evaluates on real historical document data.

Findings

Effective detection and recognition of marginalia achieved

Data augmentation and transfer learning improve performance

Open-source code and models provided

Abstract

The pressing need for digitization of historical documents has led to a strong interest in designing computerised image processing methods for automatic handwritten text recognition. However, not much attention has been paid on studying the handwritten text written in the margins, i.e. marginalia, that also forms an important source of information. Nevertheless, training an accurate and robust recognition system for marginalia calls for data-efficient approaches due to the unavailability of sufficient amounts of annotated multi-writer texts. Therefore, this work presents an end-to-end framework for automatic detection and recognition of handwritten marginalia, and leverages data augmentation and transfer learning to overcome training data scarcity. The detection phase involves investigation of R-CNN and Faster R-CNN networks. The recognition phase includes an attention-based sequence-to-sequence model, with ResNet feature extraction, bidirectional LSTM-based sequence modeling, and attention-based prediction of marginalia. The effectiveness of the proposed framework has been empirically evaluated on the data from early book collections found in the Uppsala University Library in Sweden. Source code and pre-trained models are available at Github.