The LAM Dataset: A Novel Benchmark for Line-Level Handwritten Text Recognition

TL;DR

This paper introduces the LAM dataset, a large line-level handwritten text recognition benchmark for Italian ancient manuscripts, designed to advance research in recognizing historical handwritten texts with variability over time.

Contribution

The paper presents the LAM dataset, a new large-scale benchmark for line-level HTR of Italian manuscripts, including two data splits to evaluate recognition across different time periods.

Findings

State-of-the-art HTR models achieve baseline performance on LAM.

The dataset enables studying handwriting variability over 60 years.

LAM outperforms existing line-level HTR benchmarks.

Abstract

Handwritten Text Recognition (HTR) is an open problem at the intersection of Computer Vision and Natural Language Processing. The main challenges, when dealing with historical manuscripts, are due to the preservation of the paper support, the variability of the handwriting -- even of the same author over a wide time-span -- and the scarcity of data from ancient, poorly represented languages. With the aim of fostering the research on this topic, in this paper we present the Ludovico Antonio Muratori (LAM) dataset, a large line-level HTR dataset of Italian ancient manuscripts edited by a single author over 60 years. The dataset comes in two configurations: a basic splitting and a date-based splitting which takes into account the age of the author. The first setting is intended to study HTR on ancient documents in Italian, while the second focuses on the ability of HTR systems to recognize text written by the same writer in time periods for which training data are not available. For both configurations, we analyze quantitative and qualitative characteristics, also with respect to other line-level HTR benchmarks, and present the recognition performance of state-of-the-art HTR architectures. The dataset is available for download at \url{https://aimagelab.ing.unimore.it/go/lam}.