HANA: A HAndwritten NAme Database for Offline Handwritten Text Recognition

TL;DR

HANA is a large-scale handwritten name database designed to improve offline handwritten text recognition, especially for personal names, by providing extensive data for training and benchmarking deep learning models, leading to enhanced transcription accuracy.

Contribution

The paper introduces HANA, a comprehensive database of over 3.3 million handwritten names, enabling transfer learning and benchmarking for improved handwritten text recognition models.

Findings

Significantly improved transcription accuracy on Danish and US census data.

HANA enables transfer learning for handwritten name recognition.

Benchmark results demonstrate state-of-the-art performance.

Abstract

Methods for linking individuals across historical data sets, typically in combination with AI based transcription models, are developing rapidly. Probably the single most important identifier for linking is personal names. However, personal names are prone to enumeration and transcription errors and although modern linking methods are designed to handle such challenges, these sources of errors are critical and should be minimized. For this purpose, improved transcription methods and large-scale databases are crucial components. This paper describes and provides documentation for HANA, a newly constructed large-scale database which consists of more than 3.3 million names. The database contain more than 105 thousand unique names with a total of more than 1.1 million images of personal names, which proves useful for transfer learning to other settings. We provide three examples hereof, obtaining significantly improved transcription accuracy on both Danish and US census data. In addition, we present benchmark results for deep learning models automatically transcribing the personal names from the scanned documents. Through making more challenging large-scale databases publicly available we hope to foster more sophisticated, accurate, and robust models for handwritten text recognition.