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

We focus on electronic theses and dissertations (ETDs), aiming to improveaccess and expand their utility, since more than 6 million are publiclyavailable, and they constitute an important corpus to aid research andeducation across disciplines. The corpus is growing as new born-digitaldocuments are included, and since millions of older theses and dissertationshave been converted to digital form to be disseminated electronically ininstitutional repositories. In ETDs, as with other scholarly works, figures andtables can communicate a large amount of information in a concise way. Althoughmethods have been proposed for extracting figures and tables from born-digitalPDFs, they do not work well with scanned ETDs. Considering this problem, ourassessment of state-of-the-art figure extraction systems is that the reasonthey do not function well on scanned PDFs is that they have only been trainedon born-digital documents. To address this limitation, we present ScanBank, anew dataset containing 10 thousand scanned page images, manually labeled byhumans as to the presence of the 3.3 thousand figures or tables found therein.We use this dataset to train a deep neural network model based on YOLOv5 toaccurately extract figures and tables from scanned ETDs. We pose and answerimportant research questions aimed at finding better methods for figureextraction from scanned documents. One of those concerns the value fortraining, of data augmentation techniques applied to born-digital documentswhich are used to train models better suited for figure extraction from scanneddocuments. To the best of our knowledge, ScanBank is the first manuallyannotated dataset for figure and table extraction for scanned ETDs. AYOLOv5-based model, trained on ScanBank, outperforms existing comparableopen-source and freely available baseline methods by a considerable margin.

ScanBank: A Benchmark Dataset for Figure Extraction from Scanned Electronic Theses and Dissertations