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

Layout Analysis (the identification of zones and their classification) is thefirst step along line segmentation in Optical Character Recognition and similartasks. The ability of identifying main body of text from marginal text orrunning titles makes the difference between extracting the work full text of adigitized book and noisy outputs. We show that most segmenters focus on pixelclassification and that polygonization of this output has not been used as atarget for the latest competition on historical document (ICDAR 2017 andonwards), despite being the focus in the early 2010s. We propose to shift, forefficiency, the task from a pixel classification-based polygonization to anobject detection using isothetic rectangles. We compare the output of Krakenand YOLOv5 in terms of segmentation and show that the later severelyoutperforms the first on small datasets (1110 samples and below). We releasetwo datasets for training and evaluation on historical documents as well as anew package, YALTAi, which injects YOLOv5 in the segmentation pipeline ofKraken 4.1.

You Actually Look Twice At it (YALTAi): using an object detection approach instead of region segmentation within the Kraken engine