English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Handwritten Text Recognition (HTR) is an open problem at the intersection ofComputer Vision and Natural Language Processing. The main challenges, whendealing with historical manuscripts, are due to the preservation of the papersupport, the variability of the handwriting -- even of the same author over awide time-span -- and the scarcity of data from ancient, poorly representedlanguages. With the aim of fostering the research on this topic, in this paperwe present the Ludovico Antonio Muratori (LAM) dataset, a large line-level HTRdataset of Italian ancient manuscripts edited by a single author over 60 years.The dataset comes in two configurations: a basic splitting and a date-basedsplitting which takes into account the age of the author. The first setting isintended to study HTR on ancient documents in Italian, while the second focuseson the ability of HTR systems to recognize text written by the same writer intime periods for which training data are not available. For bothconfigurations, we analyze quantitative and qualitative characteristics, alsowith respect to other line-level HTR benchmarks, and present the recognitionperformance of state-of-the-art HTR architectures. The dataset is available fordownload at \url{https://aimagelab.ing.unimore.it/go/lam}.

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